1
|
Villegas F, Dal Bello R, Alvarez-Andres E, Dhont J, Janssen T, Milan L, Robert C, Salagean GAM, Tejedor N, Trnková P, Fusella M, Placidi L, Cusumano D. Challenges and opportunities in the development and clinical implementation of artificial intelligence based synthetic computed tomography for magnetic resonance only radiotherapy. Radiother Oncol 2024; 198:110387. [PMID: 38885905 DOI: 10.1016/j.radonc.2024.110387] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/29/2023] [Revised: 06/13/2024] [Accepted: 06/13/2024] [Indexed: 06/20/2024]
Abstract
Synthetic computed tomography (sCT) generated from magnetic resonance imaging (MRI) can serve as a substitute for planning CT in radiation therapy (RT), thereby removing registration uncertainties associated with multi-modality imaging pairing, reducing costs and patient radiation exposure. CE/FDA-approved sCT solutions are nowadays available for pelvis, brain, and head and neck, while more complex deep learning (DL) algorithms are under investigation for other anatomic sites. The main challenge in achieving a widespread clinical implementation of sCT lies in the absence of consensus on sCT commissioning and quality assurance (QA), resulting in variation of sCT approaches across different hospitals. To address this issue, a group of experts gathered at the ESTRO Physics Workshop 2022 to discuss the integration of sCT solutions into clinics and report the process and its outcomes. This position paper focuses on aspects of sCT development and commissioning, outlining key elements crucial for the safe implementation of an MRI-only RT workflow.
Collapse
Affiliation(s)
- Fernanda Villegas
- Department of Oncology-Pathology, Karolinska Institute, Solna, Sweden; Radiotherapy Physics and Engineering, Medical Radiation Physics and Nuclear Medicine, Karolinska University Hospital, Solna, Sweden
| | - Riccardo Dal Bello
- Department of Radiation Oncology, University Hospital Zurich and University of Zurich, Zurich, Switzerland
| | - Emilie Alvarez-Andres
- OncoRay - National Center for Radiation Research in Oncology, Medical Faculty and University Hospital Carl Gustav Carus, TUD Dresden University of Technology, Helmholtz-Zentrum Dresden-Rossendorf, Dresden, Germany; Faculty of Medicine Carl Gustav Carus, TUD Dresden University of Technology, Dresden, Germany
| | - Jennifer Dhont
- Université libre de Bruxelles (ULB), Hôpital Universitaire de Bruxelles (H.U.B), Institut Jules Bordet, Department of Medical Physics, Brussels, Belgium; Université Libre De Bruxelles (ULB), Radiophysics and MRI Physics Laboratory, Brussels, Belgium
| | - Tomas Janssen
- Department of Radiation Oncology, The Netherlands Cancer Institute, Amsterdam, The Netherlands
| | - Lisa Milan
- Medical Physics Unit, Imaging Institute of Southern Switzerland (IIMSI), Ente Ospedaliero Cantonale, Bellinzona, Switzerland
| | - Charlotte Robert
- UMR 1030 Molecular Radiotherapy and Therapeutic Innovations, ImmunoRadAI, Paris-Saclay University, Institut Gustave Roussy, Inserm, Villejuif, France; Department of Radiation Oncology, Gustave Roussy, Villejuif, France
| | - Ghizela-Ana-Maria Salagean
- Faculty of Physics, Babes-Bolyai University, Cluj-Napoca, Romania; Department of Radiation Oncology, TopMed Medical Centre, Targu Mures, Romania
| | - Natalia Tejedor
- Department of Medical Physics and Radiation Protection, Hospital de la Santa Creu i Sant Pau, Barcelona, Spain
| | - Petra Trnková
- Department of Radiation Oncology, Medical University of Vienna, Vienna, Austria
| | - Marco Fusella
- Department of Radiation Oncology, Abano Terme Hospital, Italy
| | - Lorenzo Placidi
- Fondazione Policlinico Universitario Agostino Gemelli, IRCCS, Department of Diagnostic Imaging, Oncological Radiotherapy and Hematology, Rome, Italy.
| | - Davide Cusumano
- Mater Olbia Hospital, Strada Statale Orientale Sarda 125, Olbia, Sassari, Italy
| |
Collapse
|
2
|
Singh SB, Sarrami AH, Gatidis S, Varniab ZS, Chaudhari A, Daldrup-Link HE. Applications of Artificial Intelligence for Pediatric Cancer Imaging. AJR Am J Roentgenol 2024. [PMID: 38809123 DOI: 10.2214/ajr.24.31076] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 05/30/2024]
Abstract
Artificial intelligence (AI) is transforming medical imaging of adult patients. However, its utilization in pediatric oncology imaging remains constrained, in part due to the inherent data scarcity associated with childhood cancers. Pediatric cancers are rare, and imaging technologies are evolving rapidly, leading to insufficient data of a particular type to effectively train these algorithms. The small market size of pediatrics compared to adults could also contribute to this challenge, as market size is a driver of commercialization. This article provides an overview of the current state of AI applications for pediatric cancer imaging, including applications for medical image acquisition, processing, reconstruction, segmentation, diagnosis, staging, and treatment response monitoring. While current developments are promising, impediments due to diverse anatomies of growing children and nonstandardized imaging protocols have led to limited clinical translation thus far. Opportunities include leveraging reconstruction algorithms to achieve accelerated low-dose imaging and automating the generation of metric-based staging and treatment monitoring scores. Transfer-learning of adult-based AI models to pediatric cancers, multi-institutional data sharing, and ethical data privacy practices for pediatric patients with rare cancers will be keys to unlocking AI's full potential for clinical translation and improved outcomes for these young patients.
Collapse
Affiliation(s)
- Shashi B Singh
- Department of Radiology, Division of Pediatric Radiology, Stanford University School of Medicine, Stanford, CA, 94305
| | - Amir H Sarrami
- Department of Radiology, Division of Pediatric Radiology, Stanford University School of Medicine, Stanford, CA, 94305
| | - Sergios Gatidis
- Department of Radiology, Division of Pediatric Radiology, Stanford University School of Medicine, Stanford, CA, 94305
| | - Zahra S Varniab
- Department of Radiology, Division of Pediatric Radiology, Stanford University School of Medicine, Stanford, CA, 94305
| | - Akshay Chaudhari
- Department of Radiology, Integrative Biomedical Imaging Informatics (IBIIS), Stanford University School of Medicine, Stanford University, Stanford, CA, 94304
- Department of Biomedical Data Science, Stanford University School of Medicine, Stanford University, Stanford, CA, 94304
| | - Heike E Daldrup-Link
- Department of Radiology, Division of Pediatric Radiology, Stanford University School of Medicine, Stanford, CA, 94305
- Department of Pediatrics, Pediatric Hematology/Oncology, Lucile Packard Children's Hospital, Stanford University, Stanford, CA, 94305
| |
Collapse
|
3
|
Wahid KA, Kaffey ZY, Farris DP, Humbert-Vidan L, Moreno AC, Rasmussen M, Ren J, Naser MA, Netherton TJ, Korreman S, Balakrishnan G, Fuller CD, Fuentes D, Dohopolski MJ. Artificial Intelligence Uncertainty Quantification in Radiotherapy Applications - A Scoping Review. MEDRXIV : THE PREPRINT SERVER FOR HEALTH SCIENCES 2024:2024.05.13.24307226. [PMID: 38798581 PMCID: PMC11118597 DOI: 10.1101/2024.05.13.24307226] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/29/2024]
Abstract
Background/purpose The use of artificial intelligence (AI) in radiotherapy (RT) is expanding rapidly. However, there exists a notable lack of clinician trust in AI models, underscoring the need for effective uncertainty quantification (UQ) methods. The purpose of this study was to scope existing literature related to UQ in RT, identify areas of improvement, and determine future directions. Methods We followed the PRISMA-ScR scoping review reporting guidelines. We utilized the population (human cancer patients), concept (utilization of AI UQ), context (radiotherapy applications) framework to structure our search and screening process. We conducted a systematic search spanning seven databases, supplemented by manual curation, up to January 2024. Our search yielded a total of 8980 articles for initial review. Manuscript screening and data extraction was performed in Covidence. Data extraction categories included general study characteristics, RT characteristics, AI characteristics, and UQ characteristics. Results We identified 56 articles published from 2015-2024. 10 domains of RT applications were represented; most studies evaluated auto-contouring (50%), followed by image-synthesis (13%), and multiple applications simultaneously (11%). 12 disease sites were represented, with head and neck cancer being the most common disease site independent of application space (32%). Imaging data was used in 91% of studies, while only 13% incorporated RT dose information. Most studies focused on failure detection as the main application of UQ (60%), with Monte Carlo dropout being the most commonly implemented UQ method (32%) followed by ensembling (16%). 55% of studies did not share code or datasets. Conclusion Our review revealed a lack of diversity in UQ for RT applications beyond auto-contouring. Moreover, there was a clear need to study additional UQ methods, such as conformal prediction. Our results may incentivize the development of guidelines for reporting and implementation of UQ in RT.
Collapse
Affiliation(s)
- Kareem A. Wahid
- Department of Imaging Physics, The University of Texas MD Anderson Cancer Center, Houston, Texas, USA
- Department of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, Texas, USA
| | - Zaphanlene Y. Kaffey
- Department of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, Texas, USA
| | - David P. Farris
- Research Medical Library, The University of Texas MD Anderson Cancer Center, Houston, Texas, USA
| | - Laia Humbert-Vidan
- Department of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, Texas, USA
| | - Amy C. Moreno
- Department of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, Texas, USA
| | | | - Jintao Ren
- Department of Oncology, Aarhus University Hospital, Denmark
| | - Mohamed A. Naser
- Department of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, Texas, USA
| | - Tucker J. Netherton
- Department of Radiation Physics, University of Texas MD Anderson Cancer Center, Houston, TX, USA
| | - Stine Korreman
- Department of Oncology, Aarhus University Hospital, Denmark
| | | | - Clifton D. Fuller
- Department of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, Texas, USA
| | - David Fuentes
- Department of Imaging Physics, The University of Texas MD Anderson Cancer Center, Houston, Texas, USA
| | - Michael J. Dohopolski
- Department of Radiation Oncology, The University of Texas Southwestern Medical Center, Dallas, Texas, USA
| |
Collapse
|
4
|
Galapon AV, Thummerer A, Langendijk JA, Wagenaar D, Both S. Feasibility of Monte Carlo dropout-based uncertainty maps to evaluate deep learning-based synthetic CTs for adaptive proton therapy. Med Phys 2024; 51:2499-2509. [PMID: 37956266 DOI: 10.1002/mp.16838] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/02/2023] [Accepted: 10/28/2023] [Indexed: 11/15/2023] Open
Abstract
BACKGROUND Deep learning has shown promising results to generate MRI-based synthetic CTs and to enable accurate proton dose calculations on MRIs. For clinical implementation of synthetic CTs, quality assurance tools that verify their quality and reliability are required but still lacking. PURPOSE This study aims to evaluate the predictive value of uncertainty maps generated with Monte Carlo dropout (MCD) for verifying proton dose calculations on deep-learning-based synthetic CTs (sCTs) derived from MRIs in online adaptive proton therapy. METHODS Two deep-learning models (DCNN and cycleGAN) were trained for CT image synthesis using 101 paired CT-MR images. sCT images were generated using MCD for each model by performing 10 inferences with activated dropout layers. The final sCT was obtained by averaging the inferred sCTs, while the uncertainty map was obtained from the HU variance corresponding to each voxel of 10 sCTs. The resulting uncertainty maps were compared to the observed HU-, range-, WET-, and dose-error maps between the sCT and planning CT. For range and WET errors, the generated uncertainty maps were projected along the 90-degree angle. To evaluate the dose distribution, a mask based on the 5%-isodose curve was applied to only include voxels along the beam paths. Pearson's correlation coefficients were calculated to determine the correlation between the uncertainty maps and HUs, range, WET, and dose errors. To evaluate the dosimetric accuracy of synthetic CTs, clinical proton treatment plans were recalculated and compared to the pCTs RESULTS: Evaluation of the correlation showed an average of r = 0.92 ± 0.03 and r = 0.92 ± 0.03 for errors between uncertainty-HU, r = 0.66 ± 0.09 and r = 0.62 ± 0.06 between uncertainty-range, r = 0.64 ± 0.06 and r = 0.58 ± 0.07 between uncertainty-WET, and r = 0.65 ± 0.09 and r = 0.67 ± 0.07 between uncertainty and dose difference for DCNN and cycleGAN model, respectively. Dosimetric comparison for target volumes showed an average 3%/3 mm gamma pass rate of 99.76 ± 0.43 (DCNN) and 99.10 ± 1.27 (cycleGAN). CONCLUSION The observed correlations between uncertainty maps and the various metrics (HU, range, WET, and dose errors) demonstrated the potential of MCD-based uncertainty maps as a reliable QA tool to evaluate the accuracy of deep learning-based sCTs.
Collapse
Affiliation(s)
- Arthur Villanueva Galapon
- Department of Radiation Oncology, University Medical Center Groningen, University of Groningen, Groningen, The Netherlands
| | - Adrian Thummerer
- Department of Radiation Oncology, University Medical Center Groningen, University of Groningen, Groningen, The Netherlands
- Department of Radiation Oncology, LMU University Hospital, LMU Munich, Germany
| | - Johannes Albertus Langendijk
- Department of Radiation Oncology, University Medical Center Groningen, University of Groningen, Groningen, The Netherlands
| | - Dirk Wagenaar
- Department of Radiation Oncology, University Medical Center Groningen, University of Groningen, Groningen, The Netherlands
| | - Stefan Both
- Department of Radiation Oncology, University Medical Center Groningen, University of Groningen, Groningen, The Netherlands
| |
Collapse
|
5
|
Emin S, Rossi E, Myrvold Rooth E, Dorniok T, Hedman M, Gagliardi G, Villegas F. Clinical implementation of a commercial synthetic computed tomography solution for radiotherapy treatment of glioblastoma. Phys Imaging Radiat Oncol 2024; 30:100589. [PMID: 38818305 PMCID: PMC11137592 DOI: 10.1016/j.phro.2024.100589] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/13/2023] [Revised: 05/12/2024] [Accepted: 05/13/2024] [Indexed: 06/01/2024] Open
Abstract
Background and Purpose Magnetic resonance (MR)-only radiotherapy (RT) workflow eliminates uncertainties due to computed tomography (CT)-MR image registration, by using synthetic CT (sCT) images generated from MR. This study describes the clinical implementation process, from retrospective commissioning to prospective validation stage of a commercial artificial intelligence (AI)-based sCT product. Evaluation of the dosimetric performance of the sCT is presented, with emphasis on the impact of voxel size differences between image modalities. Materials and methods sCT performance was assessed in glioblastoma RT planning. Dose differences for 30 patients in both commissioning and validation cohorts were calculated at various dose-volume-histogram (DVH) points for target and organs-at-risk (OAR). A gamma analysis was conducted on regridded image plans. Quality assurance (QA) guidelines were established based on commissioning phase results. Results Mean dose difference to target structures was found to be within ± 0.7 % regardless of image resolution and cohort. OARs' mean dose differences were within ± 1.3 % for plans calculated on regridded images for both cohorts, while differences were higher for plans with original voxel size, reaching up to -4.2 % for chiasma D2% in the commissioning cohort. Gamma passing rates for the brain structure using the criteria 1 %/1mm, 2 %/2mm and 3 %/3mm were 93.6 %/99.8 %/100 % and 96.6 %/99.9 %/100 % for commissioning and validation cohorts, respectively. Conclusions Dosimetric outcomes in both commissioning and validation stages confirmed sCT's equivalence to CT. The large patient cohort in this study aided in establishing a robust QA program for the MR-only workflow, now applied in glioblastoma RT at our center.
Collapse
Affiliation(s)
- Sevgi Emin
- Department of Medical Radiation Physics and Nuclear Medicine, Karolinska University Hospital, 171 76 Stockholm, Sweden
| | - Elia Rossi
- Department of Radiation Oncology, Karolinska University Hospital, 171 76 Stockholm, Sweden
| | | | - Torsten Dorniok
- Department of Medical Radiation Physics and Nuclear Medicine, Karolinska University Hospital, 171 76 Stockholm, Sweden
| | - Mattias Hedman
- Department of Radiation Oncology, Karolinska University Hospital, 171 76 Stockholm, Sweden
- Department of Oncology-Pathology, Karolinska Institute, 171 77 Stockholm, Sweden
| | - Giovanna Gagliardi
- Department of Medical Radiation Physics and Nuclear Medicine, Karolinska University Hospital, 171 76 Stockholm, Sweden
- Department of Oncology-Pathology, Karolinska Institute, 171 77 Stockholm, Sweden
| | - Fernanda Villegas
- Department of Medical Radiation Physics and Nuclear Medicine, Karolinska University Hospital, 171 76 Stockholm, Sweden
- Department of Oncology-Pathology, Karolinska Institute, 171 77 Stockholm, Sweden
| |
Collapse
|
6
|
Sherwani MK, Gopalakrishnan S. A systematic literature review: deep learning techniques for synthetic medical image generation and their applications in radiotherapy. FRONTIERS IN RADIOLOGY 2024; 4:1385742. [PMID: 38601888 PMCID: PMC11004271 DOI: 10.3389/fradi.2024.1385742] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 02/13/2024] [Accepted: 03/11/2024] [Indexed: 04/12/2024]
Abstract
The aim of this systematic review is to determine whether Deep Learning (DL) algorithms can provide a clinically feasible alternative to classic algorithms for synthetic Computer Tomography (sCT). The following categories are presented in this study: ∙ MR-based treatment planning and synthetic CT generation techniques. ∙ Generation of synthetic CT images based on Cone Beam CT images. ∙ Low-dose CT to High-dose CT generation. ∙ Attenuation correction for PET images. To perform appropriate database searches, we reviewed journal articles published between January 2018 and June 2023. Current methodology, study strategies, and results with relevant clinical applications were analyzed as we outlined the state-of-the-art of deep learning based approaches to inter-modality and intra-modality image synthesis. This was accomplished by contrasting the provided methodologies with traditional research approaches. The key contributions of each category were highlighted, specific challenges were identified, and accomplishments were summarized. As a final step, the statistics of all the cited works from various aspects were analyzed, which revealed that DL-based sCTs have achieved considerable popularity, while also showing the potential of this technology. In order to assess the clinical readiness of the presented methods, we examined the current status of DL-based sCT generation.
Collapse
Affiliation(s)
- Moiz Khan Sherwani
- Section for Evolutionary Hologenomics, Globe Institute, University of Copenhagen, Copenhagen, Denmark
| | | |
Collapse
|
7
|
Moglioni M, Carra P, Arezzini S, Belcari N, Bersani D, Berti A, Bisogni MG, Calderisi M, Ceppa I, Cerello P, Ciocca M, Ferrero V, Fiorina E, Kraan AC, Mazzoni E, Morrocchi M, Pennazio F, Retico A, Rosso V, Sbolgi F, Vitolo V, Sportelli G. Synthetic CT imaging for PET monitoring in proton therapy: a simulation study. Phys Med Biol 2024; 69:065011. [PMID: 38373343 DOI: 10.1088/1361-6560/ad2a99] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/26/2023] [Accepted: 02/19/2024] [Indexed: 02/21/2024]
Abstract
Objective.This study addresses a fundamental limitation of in-beam positron emission tomography (IB-PET) in proton therapy: the lack of direct anatomical representation in the images it produces. We aim to overcome this shortcoming by pioneering the application of deep learning techniques to create synthetic control CT images (sCT) from combining IB-PET and planning CT scan data.Approach.We conducted simulations involving six patients who underwent irradiation with proton beams. Leveraging the architecture of a visual transformer (ViT) neural network, we developed a model to generate sCT images of these patients using the planning CT scans and the inter-fractional simulated PET activity maps during irradiation. To evaluate the model's performance, a comparison was conducted between the sCT images produced by the ViT model and the authentic control CT images-serving as the benchmark.Main results.The structural similarity index was computed at a mean value across all patients of 0.91, while the mean absolute error measured 22 Hounsfield Units (HU). Root mean squared error and peak signal-to-noise ratio values were 56 HU and 30 dB, respectively. The Dice similarity coefficient exhibited a value of 0.98. These values are comparable to or exceed those found in the literature. More than 70% of the synthetic morphological changes were found to be geometrically compatible with the ones reported in the real control CT scan.Significance.Our study presents an innovative approach to surface the hidden anatomical information of IB-PET in proton therapy. Our ViT-based model successfully generates sCT images from inter-fractional PET data and planning CT scans. Our model's performance stands on par with existing models relying on input from cone beam CT or magnetic resonance imaging, which contain more anatomical information than activity maps.
Collapse
Affiliation(s)
- Martina Moglioni
- Istituto Nazionale di Fisica Nucleare, Sezione di Pisa, I-56127 Pisa, Italy
- Dipartimento di Fisica, Università di Pisa, I-56127 Pisa, Italy
| | - Pietro Carra
- Istituto Nazionale di Fisica Nucleare, Sezione di Pisa, I-56127 Pisa, Italy
- Dipartimento di Fisica, Università di Pisa, I-56127 Pisa, Italy
| | - Silvia Arezzini
- Dipartimento di Fisica, Università di Pisa, I-56127 Pisa, Italy
| | - Nicola Belcari
- Istituto Nazionale di Fisica Nucleare, Sezione di Pisa, I-56127 Pisa, Italy
- Dipartimento di Fisica, Università di Pisa, I-56127 Pisa, Italy
| | - Davide Bersani
- Istituto Nazionale di Fisica Nucleare, Sezione di Pisa, I-56127 Pisa, Italy
| | - Andrea Berti
- Istituto Nazionale di Fisica Nucleare, Sezione di Pisa, I-56127 Pisa, Italy
- Dipartimento di Fisica, Università di Pisa, I-56127 Pisa, Italy
| | - Maria Giuseppina Bisogni
- Istituto Nazionale di Fisica Nucleare, Sezione di Pisa, I-56127 Pisa, Italy
- Dipartimento di Fisica, Università di Pisa, I-56127 Pisa, Italy
| | | | | | - Piergiorgio Cerello
- Istituto Nazionale di Fisica Nucleare, Sezione di Torino, I-10125 Torino, Italy
| | - Mario Ciocca
- Centro Nazionale di Adroterapia Oncologica, I-27100 Pavia, Italy
| | - Veronica Ferrero
- Istituto Nazionale di Fisica Nucleare, Sezione di Torino, I-10125 Torino, Italy
| | - Elisa Fiorina
- Istituto Nazionale di Fisica Nucleare, Sezione di Torino, I-10125 Torino, Italy
| | | | - Enrico Mazzoni
- Istituto Nazionale di Fisica Nucleare, Sezione di Pisa, I-56127 Pisa, Italy
| | - Matteo Morrocchi
- Istituto Nazionale di Fisica Nucleare, Sezione di Pisa, I-56127 Pisa, Italy
- Dipartimento di Fisica, Università di Pisa, I-56127 Pisa, Italy
| | - Francesco Pennazio
- Istituto Nazionale di Fisica Nucleare, Sezione di Torino, I-10125 Torino, Italy
| | - Alessandra Retico
- Istituto Nazionale di Fisica Nucleare, Sezione di Pisa, I-56127 Pisa, Italy
| | - Valeria Rosso
- Istituto Nazionale di Fisica Nucleare, Sezione di Pisa, I-56127 Pisa, Italy
- Dipartimento di Fisica, Università di Pisa, I-56127 Pisa, Italy
| | | | - Viviana Vitolo
- Centro Nazionale di Adroterapia Oncologica, I-27100 Pavia, Italy
| | - Giancarlo Sportelli
- Istituto Nazionale di Fisica Nucleare, Sezione di Pisa, I-56127 Pisa, Italy
- Dipartimento di Fisica, Università di Pisa, I-56127 Pisa, Italy
| |
Collapse
|
8
|
Rossi E, Emin S, Gubanski M, Gagliardi G, Hedman M, Villegas F. Contouring practices and artefact management within a synthetic CT-based radiotherapy workflow for the central nervous system. Radiat Oncol 2024; 19:27. [PMID: 38424642 DOI: 10.1186/s13014-024-02422-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/04/2023] [Accepted: 02/19/2024] [Indexed: 03/02/2024] Open
Abstract
BACKGROUND The incorporation of magnetic resonance (MR) imaging in radiotherapy (RT) workflows improves contouring precision, yet it introduces geometrical uncertainties when registered with computed tomography (CT) scans. Synthetic CT (sCT) images could minimize these uncertainties and streamline the RT workflow. This study aims to compare the contouring capabilities of sCT images with conventional CT-based/MR-assisted RT workflows, with an emphasis on managing artefacts caused by surgical fixation devices (SFDs). METHODS The study comprised a commissioning cohort of 100 patients with cranial tumors treated using a conventional CT-based/MR-assisted RT workflow and a validation cohort of 30 patients with grade IV glioblastomas treated using an MR-only workflow. A CE-marked artificial-intelligence-based sCT product was utilized. The delineation accuracy comparison was performed using dice similarity coefficient (DSC) and average Hausdorff distance (AHD). Artefacts within the commissioning cohort were visually inspected, classified and an estimation of thickness was derived using Hausdorff distance (HD). For the validation cohort, boolean operators were used to extract artefact volumes adjacent to the target and contrasted to the planning treatment volume. RESULTS The combination of high DSC (0.94) and low AHD (0.04 mm) indicates equal target delineation capacity between sCT images and conventional CT scans. However, the results for organs at risk delineation were less consistent, likely because of voxel size differences between sCT images and CT scans and absence of standardized delineation routines. Artefacts observed in sCT images appeared as enhancements of cranial bone. When close to the target, they could affect its definition. Therefore, in the validation cohort the clinical target volume (CTV) was expanded towards the bone by 3.5 mm, as estimated by HD analysis. Subsequent analysis on cone-beam CT scans showed that the CTV adjustment was enough to provide acceptable target coverage. CONCLUSION The tested sCT product performed on par with conventional CT in terms of contouring capability. Additionally, this study provides both the first comprehensive classification of metal artefacts on a sCT product and a novel method to assess the clinical impact of artefacts caused by SFDs on target delineation. This methodology encourages similar analysis for other sCT products.
Collapse
Affiliation(s)
- Elia Rossi
- Department of Radiation Oncology, Karolinska University Hospital, Solna, Sweden
| | - Sevgi Emin
- Radiotherapy Physics and Engineering, Medical Radiation Physics and Nuclear Medicine, Karolinska University Hospital, Solna, Sweden
| | - Michael Gubanski
- Department of Radiation Oncology, Karolinska University Hospital, Solna, Sweden
- Department of Oncology-Pathology, Karolinska Institutet, Solna, Sweden
| | - Giovanna Gagliardi
- Radiotherapy Physics and Engineering, Medical Radiation Physics and Nuclear Medicine, Karolinska University Hospital, Solna, Sweden
- Department of Oncology-Pathology, Karolinska Institutet, Solna, Sweden
| | - Mattias Hedman
- Department of Radiation Oncology, Karolinska University Hospital, Solna, Sweden
- Department of Oncology-Pathology, Karolinska Institutet, Solna, Sweden
| | - Fernanda Villegas
- Radiotherapy Physics and Engineering, Medical Radiation Physics and Nuclear Medicine, Karolinska University Hospital, Solna, Sweden.
- Department of Oncology-Pathology, Karolinska Institutet, Solna, Sweden.
| |
Collapse
|
9
|
Dayarathna S, Islam KT, Uribe S, Yang G, Hayat M, Chen Z. Deep learning based synthesis of MRI, CT and PET: Review and analysis. Med Image Anal 2024; 92:103046. [PMID: 38052145 DOI: 10.1016/j.media.2023.103046] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/05/2023] [Revised: 11/14/2023] [Accepted: 11/29/2023] [Indexed: 12/07/2023]
Abstract
Medical image synthesis represents a critical area of research in clinical decision-making, aiming to overcome the challenges associated with acquiring multiple image modalities for an accurate clinical workflow. This approach proves beneficial in estimating an image of a desired modality from a given source modality among the most common medical imaging contrasts, such as Computed Tomography (CT), Magnetic Resonance Imaging (MRI), and Positron Emission Tomography (PET). However, translating between two image modalities presents difficulties due to the complex and non-linear domain mappings. Deep learning-based generative modelling has exhibited superior performance in synthetic image contrast applications compared to conventional image synthesis methods. This survey comprehensively reviews deep learning-based medical imaging translation from 2018 to 2023 on pseudo-CT, synthetic MR, and synthetic PET. We provide an overview of synthetic contrasts in medical imaging and the most frequently employed deep learning networks for medical image synthesis. Additionally, we conduct a detailed analysis of each synthesis method, focusing on their diverse model designs based on input domains and network architectures. We also analyse novel network architectures, ranging from conventional CNNs to the recent Transformer and Diffusion models. This analysis includes comparing loss functions, available datasets and anatomical regions, and image quality assessments and performance in other downstream tasks. Finally, we discuss the challenges and identify solutions within the literature, suggesting possible future directions. We hope that the insights offered in this survey paper will serve as a valuable roadmap for researchers in the field of medical image synthesis.
Collapse
Affiliation(s)
- Sanuwani Dayarathna
- Department of Data Science and AI, Faculty of Information Technology, Monash University, Clayton VIC 3800, Australia.
| | | | - Sergio Uribe
- Department of Medical Imaging and Radiation Sciences, Faculty of Medicine, Monash University, Clayton VIC 3800, Australia
| | - Guang Yang
- Bioengineering Department and Imperial-X, Imperial College London, W12 7SL, United Kingdom
| | - Munawar Hayat
- Department of Data Science and AI, Faculty of Information Technology, Monash University, Clayton VIC 3800, Australia
| | - Zhaolin Chen
- Department of Data Science and AI, Faculty of Information Technology, Monash University, Clayton VIC 3800, Australia; Monash Biomedical Imaging, Clayton VIC 3800, Australia
| |
Collapse
|
10
|
Law MWK, Tse MY, Ho LCC, Lau KK, Wong OL, Yuan J, Cheung KY, Yu SK. A study of Bayesian deep network uncertainty and its application to synthetic CT generation for MR-only radiotherapy treatment planning. Med Phys 2024; 51:1244-1262. [PMID: 37665783 DOI: 10.1002/mp.16666] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/19/2022] [Revised: 06/05/2023] [Accepted: 07/20/2023] [Indexed: 09/06/2023] Open
Abstract
BACKGROUND The use of synthetic computed tomography (CT) for radiotherapy treatment planning has received considerable attention because of the absence of ionizing radiation and close spatial correspondence to source magnetic resonance (MR) images, which have excellent tissue contrast. However, in an MR-only environment, little effort has been made to examine the quality of synthetic CT images without using the original CT images. PURPOSE To estimate synthetic CT quality without referring to original CT images, this study established the relationship between synthetic CT uncertainty and Bayesian uncertainty, and proposed a new Bayesian deep network for generating synthetic CT images and estimating synthetic CT uncertainty for MR-only radiotherapy treatment planning. METHODS AND MATERIALS A novel deep Bayesian network was formulated using probabilistic network weights. Two mathematical expressions were proposed to quantify the Bayesian uncertainty of the network and synthetic CT uncertainty, which was closely related to the mean absolute error (MAE) in Hounsfield Unit (HU) of synthetic CT. These uncertainties were examined to demonstrate the accuracy of representing the synthetic CT uncertainty using a Bayesian counterpart. We developed a hybrid Bayesian architecture and a new data normalization scheme, enabling the Bayesian network to generate both accurate synthetic CT and reliable uncertainty information when probabilistic weights were applied. The proposed method was evaluated in 59 patients (13/12/32/2 for training/validation/testing/uncertainty visualization) diagnosed with prostate cancer, who underwent same-day pelvic CT- and MR-acquisitions. To assess the relationship between Bayesian and synthetic CT uncertainties, linear and non-linear correlation coefficients were calculated on per-voxel, per-tissue, and per-patient bases. For accessing the accuracy of the CT number and dosimetric accuracy, the proposed method was compared with a commercially available atlas-based method (MRCAT) and a U-Net conditional-generative adversarial network (UcGAN). RESULTS The proposed model exhibited 44.33 MAE, outperforming UcGAN 52.51 and MRCAT 54.87. The gamma rate (2%/2 mm dose difference/distance to agreement) of the proposed model was 98.68%, comparable to that of UcGAN (98.60%) and MRCAT (98.56%). The per-patient and per-tissue linear correlation coefficients between the Bayesian and synthetic CT uncertainties ranged from 0.53 to 0.83, implying a moderate to strong linear correlation. Per-voxel correlation coefficients varied from -0.13 to 0.67 depending on the regions-of-interest evaluated, indicating tissue-dependent correlation. The R2 value for estimating MAE solely using Bayesian uncertainty was 0.98, suggesting that the uncertainty of the proposed model was an ideal candidate for predicting synthetic CT error, without referring to the original CT. CONCLUSION This study established a relationship between the Bayesian model uncertainty and synthetic CT uncertainty. A novel Bayesian deep network was proposed to generate a synthetic CT and estimate its uncertainty. Various metrics were used to thoroughly examine the relationship between the uncertainties of the proposed Bayesian model and the generated synthetic CT. Compared with existing approaches, the proposed model showed comparable CT number and dosimetric accuracies. The experiments showed that the proposed Bayesian model was capable of producing accurate synthetic CT, and was an effective indicator of the uncertainty and error associated with synthetic CT in MR-only workflows.
Collapse
Affiliation(s)
- Max Wai-Kong Law
- Medical Physics Department, Hong Kong Sanatorium and Hospital, Hong Kong SAR, China
| | - Mei-Yan Tse
- Medical Physics Department, Hong Kong Sanatorium and Hospital, Hong Kong SAR, China
| | - Leon Chin-Chak Ho
- Medical Physics Department, Hong Kong Sanatorium and Hospital, Hong Kong SAR, China
| | - Ka-Ki Lau
- Medical Physics Department, Hong Kong Sanatorium and Hospital, Hong Kong SAR, China
| | - Oi Lei Wong
- Research Department, Hong Kong Sanatorium and Hospital, Hong Kong SAR, China
| | - Jing Yuan
- Research Department, Hong Kong Sanatorium and Hospital, Hong Kong SAR, China
| | - Kin Yin Cheung
- Medical Physics Department, Hong Kong Sanatorium and Hospital, Hong Kong SAR, China
| | - Siu Ki Yu
- Medical Physics Department, Hong Kong Sanatorium and Hospital, Hong Kong SAR, China
| |
Collapse
|
11
|
Eidex Z, Ding Y, Wang J, Abouei E, Qiu RLJ, Liu T, Wang T, Yang X. Deep learning in MRI-guided radiation therapy: A systematic review. J Appl Clin Med Phys 2024; 25:e14155. [PMID: 37712893 PMCID: PMC10860468 DOI: 10.1002/acm2.14155] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/21/2023] [Revised: 05/10/2023] [Accepted: 08/21/2023] [Indexed: 09/16/2023] Open
Abstract
Recent advances in MRI-guided radiation therapy (MRgRT) and deep learning techniques encourage fully adaptive radiation therapy (ART), real-time MRI monitoring, and the MRI-only treatment planning workflow. Given the rapid growth and emergence of new state-of-the-art methods in these fields, we systematically review 197 studies written on or before December 31, 2022, and categorize the studies into the areas of image segmentation, image synthesis, radiomics, and real time MRI. Building from the underlying deep learning methods, we discuss their clinical importance and current challenges in facilitating small tumor segmentation, accurate x-ray attenuation information from MRI, tumor characterization and prognosis, and tumor motion tracking. In particular, we highlight the recent trends in deep learning such as the emergence of multi-modal, visual transformer, and diffusion models.
Collapse
Affiliation(s)
- Zach Eidex
- Department of Radiation Oncology and Winship Cancer InstituteEmory UniversityAtlantaGeorgiaUSA
- School of Mechanical EngineeringGeorgia Institute of TechnologyAtlantaGeorgiaUSA
| | - Yifu Ding
- Department of Radiation Oncology and Winship Cancer InstituteEmory UniversityAtlantaGeorgiaUSA
| | - Jing Wang
- Department of Radiation Oncology and Winship Cancer InstituteEmory UniversityAtlantaGeorgiaUSA
| | - Elham Abouei
- Department of Radiation Oncology and Winship Cancer InstituteEmory UniversityAtlantaGeorgiaUSA
| | - Richard L. J. Qiu
- Department of Radiation Oncology and Winship Cancer InstituteEmory UniversityAtlantaGeorgiaUSA
| | - Tian Liu
- Department of Radiation OncologyIcahn School of Medicine at Mount SinaiNew YorkNew YorkUSA
| | - Tonghe Wang
- Department of Medical PhysicsMemorial Sloan Kettering Cancer CenterNew YorkNew YorkUSA
| | - Xiaofeng Yang
- Department of Radiation Oncology and Winship Cancer InstituteEmory UniversityAtlantaGeorgiaUSA
- School of Mechanical EngineeringGeorgia Institute of TechnologyAtlantaGeorgiaUSA
| |
Collapse
|
12
|
Liang X, Yen A, Bai T, Godley A, Shen C, Wu J, Meng B, Lin MH, Medin P, Yan Y, Owrangi A, Desai N, Hannan R, Garant A, Jiang S, Deng J. Bony structure enhanced synthetic CT generation using Dixon sequences for pelvis MR-only radiotherapy. Med Phys 2023; 50:7368-7382. [PMID: 37358195 DOI: 10.1002/mp.16556] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/03/2023] [Accepted: 05/29/2023] [Indexed: 06/27/2023] Open
Abstract
BACKGROUND MRI-only radiotherapy planning (MROP) is beneficial to patients by avoiding MRI/CT registration errors, simplifying the radiation treatment simulation workflow and reducing exposure to ionizing radiation. MRI is the primary imaging modality for soft tissue delineation. Treatment planning CTs (i.e., CT simulation scan) are redundant if a synthetic CT (sCT) can be generated from the MRI to provide the patient positioning and electron density information. Unsupervised deep learning (DL) models like CycleGAN are widely used in MR-to-sCT conversion, when paired patient CT and MR image datasets are not available for model training. However, compared to supervised DL models, they cannot guarantee anatomic consistency, especially around bone. PURPOSE The purpose of this work was to improve the sCT accuracy generated from MRI around bone for MROP. METHODS To generate more reliable bony structures on sCT images, we proposed to add bony structure constraints in the unsupervised CycleGAN model's loss function and leverage Dixon constructed fat and in-phase (IP) MR images. Dixon images provide better bone contrast than T2-weighted images as inputs to a modified multi-channel CycleGAN. A private dataset with a total of 31 prostate cancer patients were used for training (20) and testing (11). RESULTS We compared model performance with and without bony structure constraints using single- and multi-channel inputs. Among all the models, multi-channel CycleGAN with bony structure constraints had the lowest mean absolute error, both inside the bone and whole body (50.7 and 145.2 HU). This approach also resulted in the highest Dice similarity coefficient (0.88) of all bony structures compared with the planning CT. CONCLUSION Modified multi-channel CycleGAN with bony structure constraints, taking Dixon-constructed fat and IP images as inputs, can generate clinically suitable sCT images in both bone and soft tissue. The generated sCT images have the potential to be used for accurate dose calculation and patient positioning in MROP radiation therapy.
Collapse
Affiliation(s)
- Xiao Liang
- Medical Artificial Intelligence and Automation Laboratory and Department of Radiation Oncology, University of Texas Southwestern Medical Center, Dallas, Texas, USA
| | - Allen Yen
- Medical Artificial Intelligence and Automation Laboratory and Department of Radiation Oncology, University of Texas Southwestern Medical Center, Dallas, Texas, USA
| | - Ti Bai
- Medical Artificial Intelligence and Automation Laboratory and Department of Radiation Oncology, University of Texas Southwestern Medical Center, Dallas, Texas, USA
| | - Andrew Godley
- Medical Artificial Intelligence and Automation Laboratory and Department of Radiation Oncology, University of Texas Southwestern Medical Center, Dallas, Texas, USA
| | - Chenyang Shen
- Medical Artificial Intelligence and Automation Laboratory and Department of Radiation Oncology, University of Texas Southwestern Medical Center, Dallas, Texas, USA
| | - Junjie Wu
- Medical Artificial Intelligence and Automation Laboratory and Department of Radiation Oncology, University of Texas Southwestern Medical Center, Dallas, Texas, USA
| | - Boyu Meng
- Medical Artificial Intelligence and Automation Laboratory and Department of Radiation Oncology, University of Texas Southwestern Medical Center, Dallas, Texas, USA
| | - Mu-Han Lin
- Medical Artificial Intelligence and Automation Laboratory and Department of Radiation Oncology, University of Texas Southwestern Medical Center, Dallas, Texas, USA
| | - Paul Medin
- Medical Artificial Intelligence and Automation Laboratory and Department of Radiation Oncology, University of Texas Southwestern Medical Center, Dallas, Texas, USA
| | - Yulong Yan
- Medical Artificial Intelligence and Automation Laboratory and Department of Radiation Oncology, University of Texas Southwestern Medical Center, Dallas, Texas, USA
| | - Amir Owrangi
- Medical Artificial Intelligence and Automation Laboratory and Department of Radiation Oncology, University of Texas Southwestern Medical Center, Dallas, Texas, USA
| | - Neil Desai
- Medical Artificial Intelligence and Automation Laboratory and Department of Radiation Oncology, University of Texas Southwestern Medical Center, Dallas, Texas, USA
| | - Raquibul Hannan
- Medical Artificial Intelligence and Automation Laboratory and Department of Radiation Oncology, University of Texas Southwestern Medical Center, Dallas, Texas, USA
| | - Aurelie Garant
- Medical Artificial Intelligence and Automation Laboratory and Department of Radiation Oncology, University of Texas Southwestern Medical Center, Dallas, Texas, USA
| | - Steve Jiang
- Medical Artificial Intelligence and Automation Laboratory and Department of Radiation Oncology, University of Texas Southwestern Medical Center, Dallas, Texas, USA
| | - Jie Deng
- Medical Artificial Intelligence and Automation Laboratory and Department of Radiation Oncology, University of Texas Southwestern Medical Center, Dallas, Texas, USA
| |
Collapse
|
13
|
Liu C, Liu Z, Holmes J, Zhang L, Zhang L, Ding Y, Shu P, Wu Z, Dai H, Li Y, Shen D, Liu N, Li Q, Li X, Zhu D, Liu T, Liu W. Artificial general intelligence for radiation oncology. META-RADIOLOGY 2023; 1:100045. [PMID: 38344271 PMCID: PMC10857824 DOI: 10.1016/j.metrad.2023.100045] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Indexed: 02/15/2024]
Abstract
The emergence of artificial general intelligence (AGI) is transforming radiation oncology. As prominent vanguards of AGI, large language models (LLMs) such as GPT-4 and PaLM 2 can process extensive texts and large vision models (LVMs) such as the Segment Anything Model (SAM) can process extensive imaging data to enhance the efficiency and precision of radiation therapy. This paper explores full-spectrum applications of AGI across radiation oncology including initial consultation, simulation, treatment planning, treatment delivery, treatment verification, and patient follow-up. The fusion of vision data with LLMs also creates powerful multimodal models that elucidate nuanced clinical patterns. Together, AGI promises to catalyze a shift towards data-driven, personalized radiation therapy. However, these models should complement human expertise and care. This paper provides an overview of how AGI can transform radiation oncology to elevate the standard of patient care in radiation oncology, with the key insight being AGI's ability to exploit multimodal clinical data at scale.
Collapse
Affiliation(s)
- Chenbin Liu
- Department of Radiation Oncology, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital & Shenzhen Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Shenzhen, Guangdong, China
| | | | - Jason Holmes
- Department of Radiation Oncology, Mayo Clinic, USA
| | - Lu Zhang
- Department of Computer Science and Engineering, The University of Texas at Arlington, USA
| | - Lian Zhang
- Department of Radiation Oncology, Mayo Clinic, USA
| | - Yuzhen Ding
- Department of Radiation Oncology, Mayo Clinic, USA
| | - Peng Shu
- School of Computing, University of Georgia, USA
| | - Zihao Wu
- School of Computing, University of Georgia, USA
| | - Haixing Dai
- School of Computing, University of Georgia, USA
| | - Yiwei Li
- School of Computing, University of Georgia, USA
| | - Dinggang Shen
- School of Biomedical Engineering, ShanghaiTech University, China
- Shanghai United Imaging Intelligence Co., Ltd, China
- Shanghai Clinical Research and Trial Center, China
| | - Ninghao Liu
- School of Computing, University of Georgia, USA
| | - Quanzheng Li
- Department of Radiology, Massachusetts General Hospital and Harvard Medical School, USA
| | - Xiang Li
- Department of Radiology, Massachusetts General Hospital and Harvard Medical School, USA
| | - Dajiang Zhu
- Department of Computer Science and Engineering, The University of Texas at Arlington, USA
| | | | - Wei Liu
- Department of Radiation Oncology, Mayo Clinic, USA
| |
Collapse
|
14
|
Tian L, Lühr A. Proton range uncertainty caused by synthetic computed tomography generated with deep learning from pelvic magnetic resonance imaging. Acta Oncol 2023; 62:1461-1469. [PMID: 37703314 DOI: 10.1080/0284186x.2023.2256967] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/25/2023] [Accepted: 09/04/2023] [Indexed: 09/15/2023]
Abstract
BACKGROUND In proton therapy, it is disputed whether synthetic computed tomography (sCT), derived from magnetic resonance imaging (MRI), permits accurate dose calculations. On the one hand, an MRI-only workflow could eliminate errors caused by, e.g., MRI-CT registration. On the other hand, the extra error would be induced due to an sCT generation model. This work investigated the systematic and random model error induced by sCT generation of a widely discussed deep learning model, pix2pix. MATERIAL AND METHODS An open-source image dataset of 19 patients with cancer in the pelvis was employed and split into 10, 5, and 4 for training, testing, and validation of the model, respectively. Proton pencil beams (200 MeV) were simulated on the real CT and generated sCT using the tool for particle simulation (TOPAS). Monte Carlo (MC) dropout was used for error estimation (50 random sCT samples). Systematic and random model errors were investigated for sCT generation and dose calculation on sCT. RESULTS For sCT generation, random model error near the edge of the body (∼200 HU) was higher than that within the body (∼100 HU near the bone edge and <10 HU in soft tissue). The mean absolute error (MAE) was 49 ± 5, 191 ± 23, and 503 ± 70 HU for the whole body, bone, and air in the patient, respectively. Random model errors of the proton range were small (<0.2 mm) for all spots and evenly distributed throughout the proton fields. Systematic errors of the proton range were -1.0(±2.2) mm and 0.4(±0.9)%, respectively, and were unevenly distributed within the proton fields. For 4.5% of the spots, large errors (>5 mm) were found, which may relate to MRI-CT mismatch due to, e.g., registration, MRI distortion anatomical changes, etc. CONCLUSION The sCT model was shown to be robust, i.e., had a low random model error. However, further investigation to reduce and even predict and manage systematic error is still needed for future MRI-only proton therapy.
Collapse
Affiliation(s)
- Liheng Tian
- Department of Physics, TU Dortmund University, Dortmund, Germany
| | - Armin Lühr
- Department of Physics, TU Dortmund University, Dortmund, Germany
| |
Collapse
|
15
|
Tsang B, Gupta A, Takahashi MS, Baffi H, Ola T, Doria AS. Applications of artificial intelligence in magnetic resonance imaging of primary pediatric cancers: a scoping review and CLAIM score assessment. Jpn J Radiol 2023; 41:1127-1147. [PMID: 37395982 DOI: 10.1007/s11604-023-01437-8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/05/2022] [Accepted: 04/18/2023] [Indexed: 07/04/2023]
Abstract
PURPOSES To review the uses of AI for magnetic resonance (MR) imaging assessment of primary pediatric cancer and identify common literature topics and knowledge gaps. To assess the adherence of the existing literature to the Checklist for Artificial Intelligence in Medical Imaging (CLAIM) guidelines. MATERIALS AND METHODS A scoping literature search using MEDLINE, EMBASE and Cochrane databases was performed, including studies of > 10 subjects with a mean age of < 21 years. Relevant data were summarized into three categories based on AI application: detection, characterization, treatment and monitoring. Readers independently scored each study using CLAIM guidelines, and inter-rater reproducibility was assessed using intraclass correlation coefficients. RESULTS Twenty-one studies were included. The most common AI application for pediatric cancer MR imaging was pediatric tumor diagnosis and detection (13/21 [62%] studies). The most commonly studied tumor was posterior fossa tumors (14 [67%] studies). Knowledge gaps included a lack of research in AI-driven tumor staging (0/21 [0%] studies), imaging genomics (1/21 [5%] studies), and tumor segmentation (2/21 [10%] studies). Adherence to CLAIM guidelines was moderate in primary studies, with an average (range) of 55% (34%-73%) CLAIM items reported. Adherence has improved over time based on publication year. CONCLUSION The literature surrounding AI applications of MR imaging in pediatric cancers is limited. The existing literature shows moderate adherence to CLAIM guidelines, suggesting that better adherence is required for future studies.
Collapse
Affiliation(s)
- Brian Tsang
- Department of Medical Imaging, University of Toronto, Toronto, ON, Canada
- Department of Diagnostic Imaging, Research Institute, The Hospital for Sick Children, Toronto, ON, Canada
| | - Aaryan Gupta
- Department of Medical Imaging, University of Toronto, Toronto, ON, Canada
- Department of Diagnostic Imaging, Research Institute, The Hospital for Sick Children, Toronto, ON, Canada
| | - Marcelo Straus Takahashi
- Instituto de Radiologia do Hospital das Clínicas da Faculdade de Medicina da Universidade de São Paulo (InRad/HC-FMUSP), São Paulo, SP, Brazil
- Instituto da Criança do Hospital das Clínicas da Faculdade de Medicina da Universidade de São Paulo (ICr/HC-FMUSP), São Paulo, SP, Brazil
- DasaInova, Diagnósticos da América SA (Dasa), São Paulo, SP, Brazil
| | | | - Tolulope Ola
- Department of Medical Imaging, University of Toronto, Toronto, ON, Canada
- Department of Diagnostic Imaging, Research Institute, The Hospital for Sick Children, Toronto, ON, Canada
| | - Andrea S Doria
- Department of Medical Imaging, University of Toronto, Toronto, ON, Canada.
- Department of Diagnostic Imaging, Research Institute, The Hospital for Sick Children, Toronto, ON, Canada.
| |
Collapse
|
16
|
Chakrabarty N, Mahajan A. Imaging Analytics using Artificial Intelligence in Oncology: A Comprehensive Review. Clin Oncol (R Coll Radiol) 2023:S0936-6555(23)00334-5. [PMID: 37806795 DOI: 10.1016/j.clon.2023.09.013] [Citation(s) in RCA: 3] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/03/2023] [Revised: 08/09/2023] [Accepted: 09/21/2023] [Indexed: 10/10/2023]
Abstract
The present era has seen a surge in artificial intelligence-related research in oncology, mainly using deep learning, because of powerful computer hardware, improved algorithms and the availability of large amounts of data from open-source domains and the use of transfer learning. Here we discuss the multifaceted role of deep learning in cancer care, ranging from risk stratification, the screening and diagnosis of cancer, to the prediction of genomic mutations, treatment response and survival outcome prediction, through the use of convolutional neural networks. Another role of artificial intelligence is in the generation of automated radiology reports, which is a boon in high-volume centres to minimise report turnaround time. Although a validated and deployable deep-learning model for clinical use is still in its infancy, there is ongoing research to overcome the barriers for its universal implementation and we also delve into this aspect. We also briefly describe the role of radiomics in oncoimaging. Artificial intelligence can provide answers pertaining to cancer management at baseline imaging, saving cost and time. Imaging biobanks, which are repositories of anonymised images, are also briefly described. We also discuss the commercialisation and ethical issues pertaining to artificial intelligence. The latest generation generalist artificial intelligence model is also briefly described at the end of the article. We believe this article will not only enrich knowledge, but also promote research acumen in the minds of readers to take oncoimaging to another level using artificial intelligence and also work towards clinical translation of such research.
Collapse
Affiliation(s)
- N Chakrabarty
- Department of Radiodiagnosis, Advanced Centre for Treatment, Research and Education in Cancer, Tata Memorial Centre, Homi Bhabha National Institute (HBNI), Parel, Mumbai, Maharashtra, India.
| | - A Mahajan
- The Clatterbridge Cancer Centre NHS Foundation Trust, Liverpool, UK.
| |
Collapse
|
17
|
McNaughton J, Fernandez J, Holdsworth S, Chong B, Shim V, Wang A. Machine Learning for Medical Image Translation: A Systematic Review. Bioengineering (Basel) 2023; 10:1078. [PMID: 37760180 PMCID: PMC10525905 DOI: 10.3390/bioengineering10091078] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/19/2023] [Revised: 07/30/2023] [Accepted: 09/07/2023] [Indexed: 09/29/2023] Open
Abstract
BACKGROUND CT scans are often the first and only form of brain imaging that is performed to inform treatment plans for neurological patients due to its time- and cost-effective nature. However, MR images give a more detailed picture of tissue structure and characteristics and are more likely to pick up abnormalities and lesions. The purpose of this paper is to review studies which use deep learning methods to generate synthetic medical images of modalities such as MRI and CT. METHODS A literature search was performed in March 2023, and relevant articles were selected and analyzed. The year of publication, dataset size, input modality, synthesized modality, deep learning architecture, motivations, and evaluation methods were analyzed. RESULTS A total of 103 studies were included in this review, all of which were published since 2017. Of these, 74% of studies investigated MRI to CT synthesis, and the remaining studies investigated CT to MRI, Cross MRI, PET to CT, and MRI to PET. Additionally, 58% of studies were motivated by synthesizing CT scans from MRI to perform MRI-only radiation therapy. Other motivations included synthesizing scans to aid diagnosis and completing datasets by synthesizing missing scans. CONCLUSIONS Considerably more research has been carried out on MRI to CT synthesis, despite CT to MRI synthesis yielding specific benefits. A limitation on medical image synthesis is that medical datasets, especially paired datasets of different modalities, are lacking in size and availability; it is therefore recommended that a global consortium be developed to obtain and make available more datasets for use. Finally, it is recommended that work be carried out to establish all uses of the synthesis of medical scans in clinical practice and discover which evaluation methods are suitable for assessing the synthesized images for these needs.
Collapse
Affiliation(s)
- Jake McNaughton
- Auckland Bioengineering Institute, University of Auckland, 6/70 Symonds Street, Auckland 1010, New Zealand; (J.M.)
| | - Justin Fernandez
- Auckland Bioengineering Institute, University of Auckland, 6/70 Symonds Street, Auckland 1010, New Zealand; (J.M.)
- Department of Engineering Science and Biomedical Engineering, University of Auckland, 3/70 Symonds Street, Auckland 1010, New Zealand
| | - Samantha Holdsworth
- Faculty of Medical and Health Sciences, University of Auckland, 85 Park Road, Auckland 1023, New Zealand
- Centre for Brain Research, University of Auckland, 85 Park Road, Auckland 1023, New Zealand
- Mātai Medical Research Institute, 400 Childers Road, Tairāwhiti Gisborne 4010, New Zealand
| | - Benjamin Chong
- Auckland Bioengineering Institute, University of Auckland, 6/70 Symonds Street, Auckland 1010, New Zealand; (J.M.)
- Faculty of Medical and Health Sciences, University of Auckland, 85 Park Road, Auckland 1023, New Zealand
- Centre for Brain Research, University of Auckland, 85 Park Road, Auckland 1023, New Zealand
| | - Vickie Shim
- Auckland Bioengineering Institute, University of Auckland, 6/70 Symonds Street, Auckland 1010, New Zealand; (J.M.)
- Mātai Medical Research Institute, 400 Childers Road, Tairāwhiti Gisborne 4010, New Zealand
| | - Alan Wang
- Auckland Bioengineering Institute, University of Auckland, 6/70 Symonds Street, Auckland 1010, New Zealand; (J.M.)
- Faculty of Medical and Health Sciences, University of Auckland, 85 Park Road, Auckland 1023, New Zealand
- Centre for Brain Research, University of Auckland, 85 Park Road, Auckland 1023, New Zealand
| |
Collapse
|
18
|
Liu H, Sigona MK, Manuel TJ, Chen LM, Dawant BM, Caskey CF. Evaluation of synthetically generated computed tomography for use in transcranial focused ultrasound procedures. J Med Imaging (Bellingham) 2023; 10:055001. [PMID: 37744953 PMCID: PMC10514703 DOI: 10.1117/1.jmi.10.5.055001] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/13/2022] [Revised: 07/06/2023] [Accepted: 08/23/2023] [Indexed: 09/26/2023] Open
Abstract
Purpose Transcranial focused ultrasound (tFUS) is a therapeutic ultrasound method that focuses sound through the skull to a small region noninvasively and often under magnetic resonance imaging (MRI) guidance. CT imaging is used to estimate the acoustic properties that vary between individual skulls to enable effective focusing during tFUS procedures, exposing patients to potentially harmful radiation. A method to estimate acoustic parameters in the skull without the need for CT is desirable. Approach We synthesized CT images from routinely acquired T1-weighted MRI using a 3D patch-based conditional generative adversarial network and evaluated the performance of synthesized CT (sCT) images for treatment planning with tFUS. We compared the performance of sCT with real CT (rCT) images for tFUS planning using Kranion and simulations using the acoustic toolbox, k-Wave. Simulations were performed for 3 tFUS scenarios: (1) no aberration correction, (2) correction with phases calculated from Kranion, and (3) phase shifts calculated from time reversal. Results From Kranion, the skull density ratio, skull thickness, and number of active elements between rCT and sCT had Pearson's correlation coefficients of 0.94, 0.92, and 0.98, respectively. Among 20 targets, differences in simulated peak pressure between rCT and sCT were largest without phase correction (12.4 % ± 8.1 % ) and smallest with Kranion phases (7.3 % ± 6.0 % ). The distance between peak focal locations between rCT and sCT was < 1.3 mm for all simulation cases. Conclusions Real and synthetically generated skulls had comparable image similarity, skull measurements, and acoustic simulation metrics. Our work demonstrated similar results for 10 testing cases comparing MR-sCTs and rCTs for tFUS planning. Source code and a docker image with the trained model are available at https://github.com/han-liu/SynCT_TcMRgFUS.
Collapse
Affiliation(s)
- Han Liu
- Vanderbilt University, Department of Computer Science, Nashville, Tennessee, United States
| | - Michelle K. Sigona
- Vanderbilt University, Department of Biomedical Engineering, Nashville, Tennessee, United States
- Vanderbilt University, Institute of Imaging Science, Nashville, Tennessee, United States
| | - Thomas J. Manuel
- Vanderbilt University, Department of Biomedical Engineering, Nashville, Tennessee, United States
- Vanderbilt University, Institute of Imaging Science, Nashville, Tennessee, United States
| | - Li Min Chen
- Vanderbilt University, Institute of Imaging Science, Nashville, Tennessee, United States
- Vanderbilt University, Department of Radiology and Radiological Sciences, Nashville, Tennessee, United States
| | - Benoit M. Dawant
- Vanderbilt University, Department of Electrical and Computer Engineering, Nashville, Tennessee, United States
| | - Charles F. Caskey
- Vanderbilt University, Department of Biomedical Engineering, Nashville, Tennessee, United States
- Vanderbilt University, Institute of Imaging Science, Nashville, Tennessee, United States
- Vanderbilt University, Department of Radiology and Radiological Sciences, Nashville, Tennessee, United States
| |
Collapse
|
19
|
Marants R, Tattenberg S, Scholey J, Kaza E, Miao X, Benkert T, Magneson O, Fischer J, Vinas L, Niepel K, Bortfeld T, Landry G, Parodi K, Verburg J, Sudhyadhom A. Validation of an MR-based multimodal method for molecular composition and proton stopping power ratio determination using ex vivo animal tissues and tissue-mimicking phantoms. Phys Med Biol 2023; 68:10.1088/1361-6560/ace876. [PMID: 37463589 PMCID: PMC10645122 DOI: 10.1088/1361-6560/ace876] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/23/2023] [Accepted: 07/18/2023] [Indexed: 07/20/2023]
Abstract
Objective. Range uncertainty in proton therapy is an important factor limiting clinical effectiveness. Magnetic resonance imaging (MRI) can measure voxel-wise molecular composition and, when combined with kilovoltage CT (kVCT), accurately determine mean ionization potential (Im), electron density, and stopping power ratio (SPR). We aimed to develop a novel MR-based multimodal method to accurately determine SPR and molecular compositions. This method was evaluated in tissue-mimicking andex vivoporcine phantoms, and in a brain radiotherapy patient.Approach. Four tissue-mimicking phantoms with known compositions, two porcine tissue phantoms, and a brain cancer patient were imaged with kVCT and MRI. Three imaging-based values were determined: SPRCM(CT-based Multimodal), SPRMM(MR-based Multimodal), and SPRstoich(stoichiometric calibration). MRI was used to determine two tissue-specific quantities of the Bethe Bloch equation (Im, electron density) to compute SPRCMand SPRMM. Imaging-based SPRs were compared to measurements for phantoms in a proton beam using a multilayer ionization chamber (SPRMLIC).Main results. Root mean square errors relative to SPRMLICwere 0.0104(0.86%), 0.0046(0.45%), and 0.0142(1.31%) for SPRCM, SPRMM, and SPRstoich, respectively. The largest errors were in bony phantoms, while soft tissue and porcine tissue phantoms had <1% errors across all SPR values. Relative to known physical molecular compositions, imaging-determined compositions differed by approximately ≤10%. In the brain case, the largest differences between SPRstoichand SPRMMwere in bone and high lipids/fat tissue. The magnitudes and trends of these differences matched phantom results.Significance. Our MR-based multimodal method determined molecular compositions and SPR in various tissue-mimicking phantoms with high accuracy, as confirmed with proton beam measurements. This method also revealed significant SPR differences compared to stoichiometric kVCT-only calculation in a clinical case, with the largest differences in bone. These findings support that including MRI in proton therapy treatment planning can improve the accuracy of calculated SPR values and reduce range uncertainties.
Collapse
Affiliation(s)
- Raanan Marants
- Department of Radiation Oncology, Dana-Farber Cancer Institute, Brigham and Women’s Hospital, and Harvard Medical School, Boston, Massachusetts, United States of America
| | - Sebastian Tattenberg
- Department of Medical Physics, Faculty of Physics, Ludwig-Maximilians-Universität München, Garching, Germany
- Division of Radiation Biophysics, Department of Radiation Oncology, Massachusetts General Hospital and Harvard Medical School, Boston, Massachusetts, United States of America
| | - Jessica Scholey
- Department of Radiation Oncology, University of California, San Francisco, San Francisco, California, United States of America
| | - Evangelia Kaza
- Department of Radiation Oncology, Dana-Farber Cancer Institute, Brigham and Women’s Hospital, and Harvard Medical School, Boston, Massachusetts, United States of America
| | - Xin Miao
- Siemens Medical Solutions USA Inc., Boston, Massachusetts, United States of America
| | | | - Olivia Magneson
- Department of Radiation Oncology, Dana-Farber Cancer Institute, Brigham and Women’s Hospital, and Harvard Medical School, Boston, Massachusetts, United States of America
| | - Jade Fischer
- Department of Radiation Oncology, Dana-Farber Cancer Institute, Brigham and Women’s Hospital, and Harvard Medical School, Boston, Massachusetts, United States of America
- Department of Medical Physics, University of Calgary, Calgary, Alberta, Canada
| | - Luciano Vinas
- Department of Radiation Oncology, Dana-Farber Cancer Institute, Brigham and Women’s Hospital, and Harvard Medical School, Boston, Massachusetts, United States of America
- Department of Statistics, University of California, Los Angeles, Los Angeles, California, United States of America
| | - Katharina Niepel
- Department of Medical Physics, Faculty of Physics, Ludwig-Maximilians-Universität München, Garching, Germany
| | - Thomas Bortfeld
- Division of Radiation Biophysics, Department of Radiation Oncology, Massachusetts General Hospital and Harvard Medical School, Boston, Massachusetts, United States of America
| | - Guillaume Landry
- Department of Radiation Oncology, University Hospital, Ludwig-Maximilians-Universität München, Munich, Germany
- German Cancer Consortium (DKTK), Partner Site Munich, Munich, Germany
| | - Katia Parodi
- Department of Medical Physics, Faculty of Physics, Ludwig-Maximilians-Universität München, Garching, Germany
- German Cancer Consortium (DKTK), Partner Site Munich, Munich, Germany
| | - Joost Verburg
- Division of Radiation Biophysics, Department of Radiation Oncology, Massachusetts General Hospital and Harvard Medical School, Boston, Massachusetts, United States of America
| | - Atchar Sudhyadhom
- Department of Radiation Oncology, Dana-Farber Cancer Institute, Brigham and Women’s Hospital, and Harvard Medical School, Boston, Massachusetts, United States of America
| |
Collapse
|
20
|
Feng X, Tang B, Yao X, Liu M, Liao X, Yuan K, Peng Q, Orlandini LC. Effectiveness of bladder filling control during online MR-guided adaptive radiotherapy for rectal cancer. Radiat Oncol 2023; 18:136. [PMID: 37592338 PMCID: PMC10436664 DOI: 10.1186/s13014-023-02315-3] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/12/2023] [Accepted: 07/05/2023] [Indexed: 08/19/2023] Open
Abstract
BACKGROUND Magnetic resonance-guided adaptive radiotherapy (MRgART) treatment sessions at MR-Linac are time-consuming and changes in organs at risk volumes can impact the treatment dosimetry. This study aims to evaluate the feasibility to control bladder filling during the rectum MRgART online session and its effectiveness on plan dosimetry. METHODS A total of 109 online adaptive sessions of 24 rectum cancer patients treated at Unity 1.5 T MR-Linac with a short course radiotherapy (25 Gy, 5 Gy × 5) for whom the adaptive plan was optimized and recalculated online based on the daily magnetic resonance imaging (MRI) were analysed. Patients were fitted with a bladder catheter to control bladder filling; the bladder is emptied and then partially filled with a known amount of saline at the beginning and end of the online session. A first MRI ([Formula: see text]) acquired at the beginning of the session was used for plan adaptation and the second ([Formula: see text]) was acquired while approving the adapted plan and rigidly registered with the first to ensure the appropriateness of the isodoses on the ongoing delivery treatment. For each fraction, the time interval between the two MRIs and potential bladder changes were assessed with independent metrics, and the impact on the plan dosimetry was evaluated by comparing target and organs at risk dose volume histogram cut-off points of the plan adapted on [Formula: see text] and recalculated on [Formula: see text]. RESULTS Median bladder volume variations, DSC, and HD of 8.17%, 0.922, and 2.92 mm were registered within a median time of 38 min between [Formula: see text] and [Formula: see text]; dosimetric differences < 0.65% were registered for target coverage, and < 0.5% for bladder, small bowel and femoral heads constraints, with a p value > 0.05. CONCLUSION The use of a bladder filling control procedure can help ensure the dosimetric accuracy of the online adapted treatment delivered.
Collapse
Affiliation(s)
- Xi Feng
- Department of Radiation Oncology, Sichuan Cancer Hospital & Institute, Affiliated Cancer Hospital of University of Electronic Science and Technology of China, Chengdu, China
- Radiation Oncology Key Laboratory of Sichuan Province, Sichuan Clinical Research Center for Cancer, Sichuan Cancer Center, Chengdu, China
| | - Bin Tang
- Department of Radiation Oncology, Sichuan Cancer Hospital & Institute, Affiliated Cancer Hospital of University of Electronic Science and Technology of China, Chengdu, China
- Radiation Oncology Key Laboratory of Sichuan Province, Sichuan Clinical Research Center for Cancer, Sichuan Cancer Center, Chengdu, China
| | - Xinghong Yao
- Department of Radiation Oncology, Sichuan Cancer Hospital & Institute, Affiliated Cancer Hospital of University of Electronic Science and Technology of China, Chengdu, China
- Radiation Oncology Key Laboratory of Sichuan Province, Sichuan Clinical Research Center for Cancer, Sichuan Cancer Center, Chengdu, China
| | - Min Liu
- Department of Radiation Oncology, Sichuan Cancer Hospital & Institute, Affiliated Cancer Hospital of University of Electronic Science and Technology of China, Chengdu, China
- Radiation Oncology Key Laboratory of Sichuan Province, Sichuan Clinical Research Center for Cancer, Sichuan Cancer Center, Chengdu, China
- Institute of Nuclear Technology and Automation Engineering, Chengdu University of Technology, Chengdu, China
| | - Xiongfei Liao
- Department of Radiation Oncology, Sichuan Cancer Hospital & Institute, Affiliated Cancer Hospital of University of Electronic Science and Technology of China, Chengdu, China
- Radiation Oncology Key Laboratory of Sichuan Province, Sichuan Clinical Research Center for Cancer, Sichuan Cancer Center, Chengdu, China
| | - Ke Yuan
- Department of Radiation Oncology, Sichuan Cancer Hospital & Institute, Affiliated Cancer Hospital of University of Electronic Science and Technology of China, Chengdu, China
- Radiation Oncology Key Laboratory of Sichuan Province, Sichuan Clinical Research Center for Cancer, Sichuan Cancer Center, Chengdu, China
| | - Qian Peng
- Department of Radiation Oncology, Sichuan Cancer Hospital & Institute, Affiliated Cancer Hospital of University of Electronic Science and Technology of China, Chengdu, China
- Radiation Oncology Key Laboratory of Sichuan Province, Sichuan Clinical Research Center for Cancer, Sichuan Cancer Center, Chengdu, China
| | - Lucia Clara Orlandini
- Department of Radiation Oncology, Sichuan Cancer Hospital & Institute, Affiliated Cancer Hospital of University of Electronic Science and Technology of China, Chengdu, China
- Radiation Oncology Key Laboratory of Sichuan Province, Sichuan Clinical Research Center for Cancer, Sichuan Cancer Center, Chengdu, China
| |
Collapse
|
21
|
Ng CKC. Generative Adversarial Network (Generative Artificial Intelligence) in Pediatric Radiology: A Systematic Review. CHILDREN (BASEL, SWITZERLAND) 2023; 10:1372. [PMID: 37628371 PMCID: PMC10453402 DOI: 10.3390/children10081372] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 07/21/2023] [Revised: 08/07/2023] [Accepted: 08/09/2023] [Indexed: 08/27/2023]
Abstract
Generative artificial intelligence, especially with regard to the generative adversarial network (GAN), is an important research area in radiology as evidenced by a number of literature reviews on the role of GAN in radiology published in the last few years. However, no review article about GAN in pediatric radiology has been published yet. The purpose of this paper is to systematically review applications of GAN in pediatric radiology, their performances, and methods for their performance evaluation. Electronic databases were used for a literature search on 6 April 2023. Thirty-seven papers met the selection criteria and were included. This review reveals that the GAN can be applied to magnetic resonance imaging, X-ray, computed tomography, ultrasound and positron emission tomography for image translation, segmentation, reconstruction, quality assessment, synthesis and data augmentation, and disease diagnosis. About 80% of the included studies compared their GAN model performances with those of other approaches and indicated that their GAN models outperformed the others by 0.1-158.6%. However, these study findings should be used with caution because of a number of methodological weaknesses. For future GAN studies, more robust methods will be essential for addressing these issues. Otherwise, this would affect the clinical adoption of the GAN-based applications in pediatric radiology and the potential advantages of GAN could not be realized widely.
Collapse
Affiliation(s)
- Curtise K. C. Ng
- Curtin Medical School, Curtin University, GPO Box U1987, Perth, WA 6845, Australia; or ; Tel.: +61-8-9266-7314; Fax: +61-8-9266-2377
- Curtin Health Innovation Research Institute (CHIRI), Faculty of Health Sciences, Curtin University, GPO Box U1987, Perth, WA 6845, Australia
| |
Collapse
|
22
|
Nijskens L, van den Berg CAT, Verhoeff JJC, Maspero M. Exploring contrast generalisation in deep learning-based brain MRI-to-CT synthesis. Phys Med 2023; 112:102642. [PMID: 37473612 DOI: 10.1016/j.ejmp.2023.102642] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 03/18/2023] [Revised: 05/24/2023] [Accepted: 07/05/2023] [Indexed: 07/22/2023] Open
Abstract
BACKGROUND Synthetic computed tomography (sCT) has been proposed and increasingly clinically adopted to enable magnetic resonance imaging (MRI)-based radiotherapy. Deep learning (DL) has recently demonstrated the ability to generate accurate sCT from fixed MRI acquisitions. However, MRI protocols may change over time or differ between centres resulting in low-quality sCT due to poor model generalisation. PURPOSE investigating domain randomisation (DR) to increase the generalisation of a DL model for brain sCT generation. METHODS CT and corresponding T1-weighted MRI with/without contrast, T2-weighted, and FLAIR MRI from 95 patients undergoing RT were collected, considering FLAIR the unseen sequence where to investigate generalisation. A "Baseline" generative adversarial network was trained with/without the FLAIR sequence to test how a model performs without DR. Image similarity and accuracy of sCT-based dose plans were assessed against CT to select the best-performing DR approach against the Baseline. RESULTS The Baseline model had the poorest performance on FLAIR, with mean absolute error (MAE) = 106 ± 20.7 HU (mean ±σ). Performance on FLAIR significantly improved for the DR model with MAE = 99.0 ± 14.9 HU, but still inferior to the performance of the Baseline+FLAIR model (MAE = 72.6 ± 10.1 HU). Similarly, an improvement in γ-pass rate was obtained for DR vs Baseline. CONCLUSION DR improved image similarity and dose accuracy on the unseen sequence compared to training only on acquired MRI. DR makes the model more robust, reducing the need for re-training when applying a model on sequences unseen and unavailable for retraining.
Collapse
Affiliation(s)
- Lotte Nijskens
- Computational Imaging Group for MR Diagnostics & Therapy, Center for Image Science, University Medical Center Utrecht, Heidelberglaan 100, Utrecht, 3584CX, The Netherlands; Department of Radiotherapy, University Medical Center Utrecht, Heidelberglaan 100, Utrecht, 3584CX, The Netherlands
| | - Cornelis A T van den Berg
- Computational Imaging Group for MR Diagnostics & Therapy, Center for Image Science, University Medical Center Utrecht, Heidelberglaan 100, Utrecht, 3584CX, The Netherlands; Department of Radiotherapy, University Medical Center Utrecht, Heidelberglaan 100, Utrecht, 3584CX, The Netherlands
| | - Joost J C Verhoeff
- Department of Radiotherapy, University Medical Center Utrecht, Heidelberglaan 100, Utrecht, 3584CX, The Netherlands
| | - Matteo Maspero
- Computational Imaging Group for MR Diagnostics & Therapy, Center for Image Science, University Medical Center Utrecht, Heidelberglaan 100, Utrecht, 3584CX, The Netherlands; Department of Radiotherapy, University Medical Center Utrecht, Heidelberglaan 100, Utrecht, 3584CX, The Netherlands.
| |
Collapse
|
23
|
Szmul A, Taylor S, Lim P, Cantwell J, Moreira I, Zhang Y, D’Souza D, Moinuddin S, Gaze MN, Gains J, Veiga C. Deep learning based synthetic CT from cone beam CT generation for abdominal paediatric radiotherapy. Phys Med Biol 2023; 68:105006. [PMID: 36996837 PMCID: PMC10160738 DOI: 10.1088/1361-6560/acc921] [Citation(s) in RCA: 5] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/13/2022] [Revised: 03/13/2023] [Accepted: 03/30/2023] [Indexed: 04/01/2023]
Abstract
Objective. Adaptive radiotherapy workflows require images with the quality of computed tomography (CT) for re-calculation and re-optimisation of radiation doses. In this work we aim to improve the quality of on-board cone beam CT (CBCT) images for dose calculation using deep learning.Approach. We propose a novel framework for CBCT-to-CT synthesis using cycle-consistent Generative Adversarial Networks (cycleGANs). The framework was tailored for paediatric abdominal patients, a challenging application due to the inter-fractional variability in bowel filling and small patient numbers. We introduced to the networks the concept of global residuals only learning and modified the cycleGAN loss function to explicitly promote structural consistency between source and synthetic images. Finally, to compensate for the anatomical variability and address the difficulties in collecting large datasets in the paediatric population, we applied a smart 2D slice selection based on the common field-of-view (abdomen) to our imaging dataset. This acted as a weakly paired data approach that allowed us to take advantage of scans from patients treated for a variety of malignancies (thoracic-abdominal-pelvic) for training purposes. We first optimised the proposed framework and benchmarked its performance on a development dataset. Later, a comprehensive quantitative evaluation was performed on an unseen dataset, which included calculating global image similarity metrics, segmentation-based measures and proton therapy-specific metrics.Main results. We found improved performance for our proposed method, compared to a baseline cycleGAN implementation, on image-similarity metrics such as Mean Absolute Error calculated for a matched virtual CT (55.0 ± 16.6 HU proposed versus 58.9 ± 16.8 HU baseline). There was also a higher level of structural agreement for gastrointestinal gas between source and synthetic images measured using the dice similarity coefficient (0.872 ± 0.053 proposed versus 0.846 ± 0.052 baseline). Differences found in water-equivalent thickness metrics were also smaller for our method (3.3 ± 2.4% proposed versus 3.7 ± 2.8% baseline).Significance. Our findings indicate that our innovations to the cycleGAN framework improved the quality and structure consistency of the synthetic CTs generated.
Collapse
Affiliation(s)
- Adam Szmul
- Centre for Medical Image Computing, Department of Medical Physics and Biomedical Engineering, University College London, London, United Kingdom
- Wellcome/EPSRC Centre for Interventional and Surgical Sciences, University College London, London, United Kingdom
| | - Sabrina Taylor
- Centre for Medical Image Computing, Department of Medical Physics and Biomedical Engineering, University College London, London, United Kingdom
| | - Pei Lim
- Department of Oncology, University College London Hospitals NHS Foundation Trust, London, United Kingdom
| | - Jessica Cantwell
- Radiotherapy, University College London Hospitals NHS Foundation Trust, London, United Kingdom
| | - Isabel Moreira
- Centre for Medical Image Computing, Department of Medical Physics and Biomedical Engineering, University College London, London, United Kingdom
| | - Ying Zhang
- Department of Medical Physics and Biomedical Engineering, University College London, London, United Kingdom
| | - Derek D’Souza
- Radiotherapy Physics Services, University College London Hospitals NHS Foundation Trust, London, United Kingdom
| | - Syed Moinuddin
- Radiotherapy, University College London Hospitals NHS Foundation Trust, London, United Kingdom
| | - Mark N. Gaze
- Department of Oncology, University College London Hospitals NHS Foundation Trust, London, United Kingdom
| | - Jennifer Gains
- Department of Oncology, University College London Hospitals NHS Foundation Trust, London, United Kingdom
| | - Catarina Veiga
- Centre for Medical Image Computing, Department of Medical Physics and Biomedical Engineering, University College London, London, United Kingdom
| |
Collapse
|
24
|
Olberg S, Choi BS, Park I, Liang X, Kim JS, Deng J, Yan Y, Jiang S, Park JC. Ensemble learning and personalized training for the improvement of unsupervised deep learning-based synthetic CT reconstruction. Med Phys 2023; 50:1436-1449. [PMID: 36336718 DOI: 10.1002/mp.16087] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/13/2022] [Revised: 08/22/2022] [Accepted: 10/19/2022] [Indexed: 11/09/2022] Open
Abstract
BACKGROUND The growing adoption of magnetic resonance imaging (MRI)-guided radiation therapy (RT) platforms and a focus on MRI-only RT workflows have brought the technical challenge of synthetic computed tomography (sCT) reconstruction to the forefront. Unpaired-data deep learning-based approaches to the problem offer the attractive characteristic of not requiring paired training data, but the gap between paired- and unpaired-data results can be limiting. PURPOSE We present two distinct approaches aimed at improving unpaired-data sCT reconstruction results: a cascade ensemble that combines multiple models and a personalized training strategy originally designed for the paired-data setting. METHODS Comparisons are made between the following models: (1) the paired-data fully convolutional DenseNet (FCDN), (2) the FCDN with the Intentional Deep Overfit Learning (IDOL) personalized training strategy, (3) the unpaired-data CycleGAN, (4) the CycleGAN with the IDOL training strategy, and (5) the CycleGAN as an intermediate model in a cascade ensemble approach. Evaluation of the various models over 25 total patients is carried out using a five-fold cross-validation scheme, with the patient-specific IDOL models being trained for the five patients of fold 3, chosen at random. RESULTS In both the paired- and unpaired-data settings, adopting the IDOL training strategy led to improvements in the mean absolute error (MAE) between true CT images and sCT outputs within the body contour (mean improvement, paired- and unpaired-data approaches, respectively: 38%, 9%) and in regions of bone (52%, 5%), the peak signal-to-noise ratio (PSNR; 15%, 7%), and the structural similarity index (SSIM; 6%, <1%). The ensemble approach offered additional benefits over the IDOL approach in all three metrics (mean improvement over unpaired-data approach in fold 3; MAE: 20%; bone MAE: 16%; PSNR: 10%; SSIM: 2%), and differences in body MAE between the ensemble approach and the paired-data approach are statistically insignificant. CONCLUSIONS We have demonstrated that both a cascade ensemble approach and a personalized training strategy designed initially for the paired-data setting offer significant improvements in image quality metrics for the unpaired-data sCT reconstruction task. Closing the gap between paired- and unpaired-data approaches is a step toward fully enabling these powerful and attractive unpaired-data frameworks.
Collapse
Affiliation(s)
- Sven Olberg
- Medical Artificial Intelligence and Automation (MAIA) Laboratory, Department of Radiation Oncology, University of Texas Southwestern Medical Center, Dallas, Texas, USA
- Department of Biomedical Engineering, Washington University in St. Louis, St. Louis, Missouri, USA
| | - Byong Su Choi
- Medical Artificial Intelligence and Automation (MAIA) Laboratory, Department of Radiation Oncology, University of Texas Southwestern Medical Center, Dallas, Texas, USA
- Medical Physics and Biomedical Engineering Lab (MPBEL), Department of Radiation Oncology, Yonsei Cancer Center, Yonsei University College of Medicine, Seoul, South Korea
| | - Inkyung Park
- Medical Artificial Intelligence and Automation (MAIA) Laboratory, Department of Radiation Oncology, University of Texas Southwestern Medical Center, Dallas, Texas, USA
- Medical Physics and Biomedical Engineering Lab (MPBEL), Department of Radiation Oncology, Yonsei Cancer Center, Yonsei University College of Medicine, Seoul, South Korea
| | - Xiao Liang
- Medical Artificial Intelligence and Automation (MAIA) Laboratory, Department of Radiation Oncology, University of Texas Southwestern Medical Center, Dallas, Texas, USA
| | - Jin Sung Kim
- Medical Physics and Biomedical Engineering Lab (MPBEL), Department of Radiation Oncology, Yonsei Cancer Center, Yonsei University College of Medicine, Seoul, South Korea
- Oncosoft Inc., Seoul, South Korea
| | - Jie Deng
- Medical Artificial Intelligence and Automation (MAIA) Laboratory, Department of Radiation Oncology, University of Texas Southwestern Medical Center, Dallas, Texas, USA
| | - Yulong Yan
- Medical Artificial Intelligence and Automation (MAIA) Laboratory, Department of Radiation Oncology, University of Texas Southwestern Medical Center, Dallas, Texas, USA
| | - Steve Jiang
- Medical Artificial Intelligence and Automation (MAIA) Laboratory, Department of Radiation Oncology, University of Texas Southwestern Medical Center, Dallas, Texas, USA
| | - Justin C Park
- Medical Artificial Intelligence and Automation (MAIA) Laboratory, Department of Radiation Oncology, University of Texas Southwestern Medical Center, Dallas, Texas, USA
- Medical Physics and Biomedical Engineering Lab (MPBEL), Department of Radiation Oncology, Yonsei Cancer Center, Yonsei University College of Medicine, Seoul, South Korea
- Department of Radiation Oncology, Mayo Clinic, Jacksonville, Florida, USA
| |
Collapse
|
25
|
Zhao Y, Wang H, Yu C, Court LE, Wang X, Wang Q, Pan T, Ding Y, Phan J, Yang J. Compensation cycle consistent generative adversarial networks (Comp-GAN) for synthetic CT generation from MR scans with truncated anatomy. Med Phys 2023. [PMID: 36698291 DOI: 10.1002/mp.16246] [Citation(s) in RCA: 7] [Impact Index Per Article: 7.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/08/2022] [Revised: 12/26/2022] [Accepted: 12/27/2022] [Indexed: 01/27/2023] Open
Abstract
BACKGROUND MR scans used in radiotherapy can be partially truncated due to the limited field of view (FOV), affecting dose calculation accuracy in MR-based radiation treatment planning. PURPOSE We proposed a novel Compensation-cycleGAN (Comp-cycleGAN) by modifying the cycle-consistent generative adversarial network (cycleGAN), to simultaneously create synthetic CT (sCT) images and compensate the missing anatomy from the truncated MR images. METHODS Computed tomography (CT) and T1 MR images with complete anatomy of 79 head-and-neck patients were used for this study. The original MR images were manually cropped 10-25 mm off at the posterior head to simulate clinically truncated MR images. Fifteen patients were randomly chosen for testing and the rest of the patients were used for model training and validation. Both the truncated and original MR images were used in the Comp-cycleGAN training stage, which enables the model to compensate for the missing anatomy by learning the relationship between the truncation and known structures. After the model was trained, sCT images with complete anatomy can be generated by feeding only the truncated MR images into the model. In addition, the external body contours acquired from the CT images with full anatomy could be an optional input for the proposed method to leverage the additional information of the actual body shape for each test patient. The mean absolute error (MAE) of Hounsfield units (HU), peak signal-to-noise ratio (PSNR), and structural similarity index (SSIM) were calculated between sCT and real CT images to quantify the overall sCT performance. To further evaluate the shape accuracy, we generated the external body contours for sCT and original MR images with full anatomy. The Dice similarity coefficient (DSC) and mean surface distance (MSD) were calculated between the body contours of sCT and original MR images for the truncation region to assess the anatomy compensation accuracy. RESULTS The average MAE, PSNR, and SSIM calculated over test patients were 93.1 HU/91.3 HU, 26.5 dB/27.4 dB, and 0.94/0.94 for the proposed Comp-cycleGAN models trained without/with body-contour information, respectively. These results were comparable with those obtained from the cycleGAN model which is trained and tested on full-anatomy MR images, indicating the high quality of the sCT generated from truncated MR images by the proposed method. Within the truncated region, the mean DSC and MSD were 0.85/0.89 and 1.3/0.7 mm for the proposed Comp-cycleGAN models trained without/with body contour information, demonstrating good performance in compensating the truncated anatomy. CONCLUSIONS We developed a novel Comp-cycleGAN model that can effectively create sCT with complete anatomy compensation from truncated MR images, which could potentially benefit the MRI-based treatment planning.
Collapse
Affiliation(s)
- Yao Zhao
- Department of Radiation Physics, The University of Texas MD Anderson Cancer Center, Houston, Texas, USA.,The University of Texas MD Anderson Cancer Center UTHealth Houston Graduate School of Biomedical Sciences, Houston, Texas, USA
| | - He Wang
- Department of Radiation Physics, The University of Texas MD Anderson Cancer Center, Houston, Texas, USA.,The University of Texas MD Anderson Cancer Center UTHealth Houston Graduate School of Biomedical Sciences, Houston, Texas, USA
| | - Cenji Yu
- Department of Radiation Physics, The University of Texas MD Anderson Cancer Center, Houston, Texas, USA.,The University of Texas MD Anderson Cancer Center UTHealth Houston Graduate School of Biomedical Sciences, Houston, Texas, USA
| | - Laurence E Court
- Department of Radiation Physics, The University of Texas MD Anderson Cancer Center, Houston, Texas, USA
| | - Xin Wang
- Department of Radiation Physics, The University of Texas MD Anderson Cancer Center, Houston, Texas, USA.,The University of Texas MD Anderson Cancer Center UTHealth Houston Graduate School of Biomedical Sciences, Houston, Texas, USA
| | - Qianxia Wang
- Department of Radiation Physics, The University of Texas MD Anderson Cancer Center, Houston, Texas, USA.,Department of Radiation Oncology and Winship Cancer Institute, Emory University, Atlanta, Georgia, USA
| | - Tinsu Pan
- The University of Texas MD Anderson Cancer Center UTHealth Houston Graduate School of Biomedical Sciences, Houston, Texas, USA.,Department of Imaging Physics, The University of Texas MD Anderson Cancer Center, Houston, Texas, USA
| | - Yao Ding
- Department of Radiation Physics, The University of Texas MD Anderson Cancer Center, Houston, Texas, USA
| | - Jack Phan
- Department of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, Texas, USA
| | - Jinzhong Yang
- Department of Radiation Physics, The University of Texas MD Anderson Cancer Center, Houston, Texas, USA.,The University of Texas MD Anderson Cancer Center UTHealth Houston Graduate School of Biomedical Sciences, Houston, Texas, USA
| |
Collapse
|
26
|
Garcia Hernandez A, Fau P, Wojak J, Mailleux H, Benkreira M, Rapacchi S, Adel M. Synthetic computed tomography generation for abdominal adaptive radiotherapy using low-field magnetic resonance imaging. Phys Imaging Radiat Oncol 2023; 25:100425. [PMID: 36896334 PMCID: PMC9988674 DOI: 10.1016/j.phro.2023.100425] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/22/2022] [Revised: 02/12/2023] [Accepted: 02/17/2023] [Indexed: 02/24/2023] Open
Abstract
Background and Purpose Magnetic Resonance guided Radiotherapy (MRgRT) still needs the acquisition of Computed Tomography (CT) images and co-registration between CT and Magnetic Resonance Imaging (MRI). The generation of synthetic CT (sCT) images from the MR data can overcome this limitation. In this study we aim to propose a Deep Learning (DL) based approach for sCT image generation for abdominal Radiotherapy using low field MR images. Materials and methods CT and MR images were collected from 76 patients treated on abdominal sites. U-Net and conditional Generative Adversarial Network (cGAN) architectures were used to generate sCT images. Additionally, sCT images composed of only six bulk densities were generated with the aim of having a Simplified sCT.Radiotherapy plans calculated using the generated images were compared to the original plan in terms of gamma pass rate and Dose Volume Histogram (DVH) parameters. Results sCT images were generated in 2 s and 2.5 s with U-Net and cGAN architectures respectively.Gamma pass rates for 2%/2mm and 3%/3mm criteria were 91% and 95% respectively. Dose differences within 1% for DVH parameters on the target volume and organs at risk were obtained. Conclusion U-Net and cGAN architectures are able to generate abdominal sCT images fast and accurately from low field MRI.
Collapse
Affiliation(s)
- Armando Garcia Hernandez
- Aix Marseille Univ, CNRS, Centrale Marseille, Institut Fresnel, Marseille, France
- Corresponding author.
| | - Pierre Fau
- Institut Paoli-Calmettes, Bouches du Rhône, Marseille, France
| | - Julien Wojak
- Aix Marseille Univ, CNRS, Centrale Marseille, Institut Fresnel, Marseille, France
| | - Hugues Mailleux
- Institut Paoli-Calmettes, Bouches du Rhône, Marseille, France
| | | | | | - Mouloud Adel
- Aix Marseille Univ, CNRS, Centrale Marseille, Institut Fresnel, Marseille, France
| |
Collapse
|
27
|
Zhao S, Geng C, Guo C, Tian F, Tang X. SARU: A self-attention ResUNet to generate synthetic CT images for MR-only BNCT treatment planning. Med Phys 2023; 50:117-127. [PMID: 36129452 DOI: 10.1002/mp.15986] [Citation(s) in RCA: 6] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/29/2022] [Revised: 09/01/2022] [Accepted: 09/07/2022] [Indexed: 01/25/2023] Open
Abstract
PURPOSE Despite the significant physical differences between magnetic resonance imaging (MRI) and computed tomography (CT), the high entropy of MRI data indicates the existence of a surjective transformation from MRI to CT image. However, there is no specific optimization of the network itself in previous MRI/CT translation works, resulting in mistakes in details such as the skull margin and cavity edge. These errors might have moderate effect on conventional radiotherapy, but for boron neutron capture therapy (BNCT), the skin dose will be a critical part of the dose composition. Thus, the purpose of this work is to create a self-attention network that could directly transfer MRI to synthetical computerized tomography (sCT) images with lower inaccuracy at the skin edge and examine the viability of magnetic resonance (MR)-guided BNCT. METHODS A retrospective analysis was undertaken on 104 patients with brain malignancies who had both CT and MRI as part of their radiation treatment plan. The CT images were deformably registered to the MRI. In the U-shaped generation network, we introduced spatial and channel attention modules, as well as a versatile "Attentional ResBlock," which reduce the parameters while maintaining high performance. We employed five-fold cross-validation to test all patients, compared the proposed network to those used in earlier studies, and used Monte Carlo software to simulate the BNCT process for dosimetric evaluation in test set. RESULTS Compared with UNet, Pix2Pix, and ResNet, the mean absolute error (MAE) of self-attention ResUNet (SARU) is reduced by 12.91, 17.48, and 9.50 HU, respectively. The "two one-sided tests" show no significant difference in dose-volume histogram (DVH) results. And for all tested cases, the average 2%/2 mm gamma index of UNet, ResNet, Pix2Pix, and SARU were 0.96 ± 0.03, 0.96 ± 0.03, 0.95 ± 0.03, and 0.98 ± 0.01, respectively. The error of skin dose from SARU is much less than the results from other methods. CONCLUSIONS We have developed a residual U-shape network with an attention mechanism to generate sCT images from MRI for BNCT treatment planning with lower MAE in six organs. There is no significant difference between the dose distribution calculated by sCT and real CT. This solution may greatly simplify the BNCT treatment planning process, lower the BNCT treatment dose, and minimize image feature mismatch.
Collapse
Affiliation(s)
- Sheng Zhao
- Department of Nuclear Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, People's Republic of China
| | - Changran Geng
- Department of Nuclear Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, People's Republic of China.,Key Laboratory of Nuclear Technology Application and Radiation Protection in Astronautics (Nanjing University of Aeronautics and Astronautics), Ministry of Industry and Information Technology, Nanjing, People's Republic of China
| | - Chang Guo
- Department of Radiation Oncology, Jiangsu Cancer Hospital, Nanjing, People's Republic of China
| | - Feng Tian
- Department of Nuclear Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, People's Republic of China
| | - Xiaobin Tang
- Department of Nuclear Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, People's Republic of China.,Key Laboratory of Nuclear Technology Application and Radiation Protection in Astronautics (Nanjing University of Aeronautics and Astronautics), Ministry of Industry and Information Technology, Nanjing, People's Republic of China
| |
Collapse
|
28
|
Thummerer A, Seller Oria C, Zaffino P, Visser S, Meijers A, Guterres Marmitt G, Wijsman R, Seco J, Langendijk JA, Knopf AC, Spadea MF, Both S. Deep learning-based 4D-synthetic CTs from sparse-view CBCTs for dose calculations in adaptive proton therapy. Med Phys 2022; 49:6824-6839. [PMID: 35982630 PMCID: PMC10087352 DOI: 10.1002/mp.15930] [Citation(s) in RCA: 10] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/02/2022] [Revised: 07/20/2022] [Accepted: 08/08/2022] [Indexed: 12/13/2022] Open
Abstract
BACKGROUND Time-resolved 4D cone beam-computed tomography (4D-CBCT) allows a daily assessment of patient anatomy and respiratory motion. However, 4D-CBCTs suffer from imaging artifacts that affect the CT number accuracy and prevent accurate proton dose calculations. Deep learning can be used to correct CT numbers and generate synthetic CTs (sCTs) that can enable CBCT-based proton dose calculations. PURPOSE In this work, sparse view 4D-CBCTs were converted into 4D-sCT utilizing a deep convolutional neural network (DCNN). 4D-sCTs were evaluated in terms of image quality and dosimetric accuracy to determine if accurate proton dose calculations for adaptive proton therapy workflows of lung cancer patients are feasible. METHODS A dataset of 45 thoracic cancer patients was utilized to train and evaluate a DCNN to generate 4D-sCTs, based on sparse view 4D-CBCTs reconstructed from projections acquired with a 3D acquisition protocol. Mean absolute error (MAE) and mean error were used as metrics to evaluate the image quality of single phases and average 4D-sCTs against 4D-CTs acquired on the same day. The dosimetric accuracy was checked globally (gamma analysis) and locally for target volumes and organs-at-risk (OARs) (lung, heart, and esophagus). Furthermore, 4D-sCTs were also compared to 3D-sCTs. To evaluate CT number accuracy, proton radiography simulations in 4D-sCT and 4D-CTs were compared in terms of range errors. The clinical suitability of 4D-sCTs was demonstrated by performing a 4D dose reconstruction using patient specific treatment delivery log files and breathing signals. RESULTS 4D-sCTs resulted in average MAEs of 48.1 ± 6.5 HU (single phase) and 37.7 ± 6.2 HU (average). The global dosimetric evaluation showed gamma pass ratios of 92.3% ± 3.2% (single phase) and 94.4% ± 2.1% (average). The clinical target volume showed high agreement in D98 between 4D-CT and 4D-sCT, with differences below 2.4% for all patients. Larger dose differences were observed in mean doses of OARs (up to 8.4%). The comparison with 3D-sCTs showed no substantial image quality and dosimetric differences for the 4D-sCT average. Individual 4D-sCT phases showed slightly lower dosimetric accuracy. The range error evaluation revealed that lung tissues cause range errors about three times higher than the other tissues. CONCLUSION In this study, we have investigated the accuracy of deep learning-based 4D-sCTs for daily dose calculations in adaptive proton therapy. Despite image quality differences between 4D-sCTs and 3D-sCTs, comparable dosimetric accuracy was observed globally and locally. Further improvement of 3D and 4D lung sCTs could be achieved by increasing CT number accuracy in lung tissues.
Collapse
Affiliation(s)
- Adrian Thummerer
- Department, of Radiation Oncology, University Medical Center Groningen, University of Groningen, Groningen, The Netherlands
| | - Carmen Seller Oria
- Department, of Radiation Oncology, University Medical Center Groningen, University of Groningen, Groningen, The Netherlands
| | - Paolo Zaffino
- Department of Experimental and Clinical Medicine, Magna Graecia University, Catanzaro, Italy
| | - Sabine Visser
- Department, of Radiation Oncology, University Medical Center Groningen, University of Groningen, Groningen, The Netherlands
| | - Arturs Meijers
- Department, of Radiation Oncology, University Medical Center Groningen, University of Groningen, Groningen, The Netherlands.,Center for Proton Therapy, Paul Scherrer Institute, Villigen, Switzerland
| | - Gabriel Guterres Marmitt
- Department, of Radiation Oncology, University Medical Center Groningen, University of Groningen, Groningen, The Netherlands
| | - Robin Wijsman
- Department, of Radiation Oncology, University Medical Center Groningen, University of Groningen, Groningen, The Netherlands
| | - Joao Seco
- Department of Biomedical Physics in Radiation Oncology, Deutsches Krebsforschungszentrum (DKFZ), Heidelberg, Germany.,Department of Physics and Astronomy, Heidelberg University, Heidelberg, Germany
| | - Johannes Albertus Langendijk
- Department, of Radiation Oncology, University Medical Center Groningen, University of Groningen, Groningen, The Netherlands
| | - Antje Christin Knopf
- Department, of Radiation Oncology, University Medical Center Groningen, University of Groningen, Groningen, The Netherlands.,Department I of Internal Medicine, Center for Integrated Oncology Cologne, University Hospital of Cologne, Cologne, Germany
| | - Maria Francesca Spadea
- Department of Experimental and Clinical Medicine, Magna Graecia University, Catanzaro, Italy
| | - Stefan Both
- Department, of Radiation Oncology, University Medical Center Groningen, University of Groningen, Groningen, The Netherlands
| |
Collapse
|
29
|
Tang B, Liu M, Wang B, Diao P, Li J, Feng X, Wu F, Yao X, Liao X, Hou Q, Orlandini LC. Improving the clinical workflow of a MR-Linac by dosimetric evaluation of synthetic CT. Front Oncol 2022; 12:920443. [PMID: 36106119 PMCID: PMC9464932 DOI: 10.3389/fonc.2022.920443] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/14/2022] [Accepted: 08/04/2022] [Indexed: 11/13/2022] Open
Abstract
Adaptive radiotherapy performed on the daily magnetic resonance imaging (MRI) is an option to improve the treatment quality. In the adapt-to-shape workflow of 1.5-T MR-Linac, the contours of structures are adjusted on the basis of patient daily MRI, and the adapted plan is recalculated on the MRI-based synthetic computed tomography (syCT) generated by bulk density assignment. Because dosimetric accuracy of this strategy is a priority and requires evaluation, this study aims to explore the usefulness of adding an assessment of dosimetric errors associated with recalculation on syCT to the clinical workflow. Sixty-one patients, with various tumor sites, treated using a 1.5-T MR-Linac were included in this study. In Monaco V5.4, the target and organs at risk (OARs) were contoured, and a reference CT plan that contains information about the outlined contours, their average electron density (ED), and the priority of ED assignment was generated. To evaluate the dosimetric error of syCT caused by the inherent approximation within bulk density assignment, the reference CT plan was recalculated on the syCT obtained from the reference CT by forcing all contoured structures to their mean ED defined on the reference plan. The dose–volume histogram (DVH) and dose distribution of the CT and syCT plan were compared. The causes of dosimetric discrepancies were investigated, and the reference plan was reworked to minimize errors if needed. For 54 patients, gamma analysis of the dose distribution on syCT and CT show a median pass rate of 99.7% and 98.5% with the criteria of 3%/3 mm and 2%/2 mm, respectively. DVH difference of targets and OARs remained less than 1.5% or 1 Gy. For the remaining patients, factors (i.e., inappropriate ED assignments) influenced the dosimetric agreement of the syCT vs. CT reference DVH by up to 21%. The causes of the errors were promptly identified, and the DVH dosimetry was realigned except for two lung treatments for which a significant discrepancy remained. The recalculation on the syCT obtained from the planning CT is a powerful tool to assess and decrease the minimal error committed during the adaptive plan on the MRI-based syCT.
Collapse
Affiliation(s)
- Bin Tang
- Department of Radiation Oncology, Sichuan Cancer Hospital and Research Institute, affiliated to University of Electronic Science and Technology of China (UESTC), Chengdu, China
- Key Laboratory of Radiation Physics and Technology of the Ministry of Education, Institute of Nuclear Science and Technology, Sichuan University, Chengdu, China
| | - Min Liu
- Department of Radiation Oncology, Sichuan Cancer Hospital and Research Institute, affiliated to University of Electronic Science and Technology of China (UESTC), Chengdu, China
| | - Bingjie Wang
- Faculty of Arts and Science, University of Toronto, Toronto, ON, Canada
| | - Peng Diao
- Department of Radiation Oncology, Sichuan Cancer Hospital and Research Institute, affiliated to University of Electronic Science and Technology of China (UESTC), Chengdu, China
- *Correspondence: Peng Diao,
| | - Jie Li
- Department of Radiation Oncology, Sichuan Cancer Hospital and Research Institute, affiliated to University of Electronic Science and Technology of China (UESTC), Chengdu, China
| | - Xi Feng
- Department of Radiation Oncology, Sichuan Cancer Hospital and Research Institute, affiliated to University of Electronic Science and Technology of China (UESTC), Chengdu, China
| | - Fan Wu
- Department of Radiation Oncology, Sichuan Cancer Hospital and Research Institute, affiliated to University of Electronic Science and Technology of China (UESTC), Chengdu, China
| | - Xinghong Yao
- Department of Radiation Oncology, Sichuan Cancer Hospital and Research Institute, affiliated to University of Electronic Science and Technology of China (UESTC), Chengdu, China
| | - Xiongfei Liao
- Department of Radiation Oncology, Sichuan Cancer Hospital and Research Institute, affiliated to University of Electronic Science and Technology of China (UESTC), Chengdu, China
| | - Qing Hou
- Key Laboratory of Radiation Physics and Technology of the Ministry of Education, Institute of Nuclear Science and Technology, Sichuan University, Chengdu, China
| | - Lucia Clara Orlandini
- Department of Radiation Oncology, Sichuan Cancer Hospital and Research Institute, affiliated to University of Electronic Science and Technology of China (UESTC), Chengdu, China
| |
Collapse
|
30
|
Possibilities and challenges when using synthetic computed tomography in an adaptive carbon-ion treatment workflow. Z Med Phys 2022:S0939-3889(22)00064-2. [PMID: 35764469 DOI: 10.1016/j.zemedi.2022.05.003] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/16/2022] [Revised: 05/29/2022] [Accepted: 05/29/2022] [Indexed: 11/23/2022]
Abstract
BACKGROUND AND PURPOSE Anatomical surveillance during ion-beam therapy is the basis for an effective tumor treatment and optimal organ at risk (OAR) sparing. Synthetic computed tomography (sCT) based on magnetic resonance imaging (MRI) can replace the X-ray based planning CT (X-rayCT) in photon radiotherapy and improve the workflow efficiency without additional imaging dose. The extension to carbon-ion radiotherapy is highly challenging; complex patient positioning, unique anatomical situations, distinct horizontal and vertical beam incidence directions, and limited training data are only few problems. This study gives insight into the possibilities and challenges of using sCTs in carbon-ion therapy. MATERIALS AND METHODS For head and neck patients immobilised with thermoplastic masks 30 clinically applied actively scanned carbon-ion treatment plans on 15 CTs comprising 60 beams were analyzed. Those treatment plans were re-calculated on MRI based sCTs which were created employing a 3D U-Net. Dose differences and carbon-ion spot displacements between sCT and X-rayCT were evaluated on a patient specific basis. RESULTS Spot displacement analysis showed a peak displacement by 0.2 cm caused by the immobilisation mask not measurable with the MRI. 95.7% of all spot displacements were located within 1 cm. For the clinical target volume (CTV) the median D50% agreed within -0.2% (-1.3 to 1.4%), while the median D0.01cc differed up to 4.2% (-1.3 to 25.3%) comparing the dose distribution on the X-rayCT and the sCT. OAR deviations depended strongly on the position and the dose gradient. For three patients no deterioration of the OAR parameters was observed. Other patients showed large deteriorations, e.g. for one patient D2% of the chiasm differed by 28.1%. CONCLUSION The usage of sCTs opens several new questions, concluding that we are not ready yet for an MR-only workflow in carbon-ion therapy, as envisaged in photon therapy. Although omitting the X-rayCT seems unfavourable in the case of carbon-ion therapy, an sCT could be advantageous for monitoring, re-planning, and adaptation.
Collapse
|
31
|
A Survey on Deep Learning for Precision Oncology. Diagnostics (Basel) 2022; 12:diagnostics12061489. [PMID: 35741298 PMCID: PMC9222056 DOI: 10.3390/diagnostics12061489] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/25/2022] [Revised: 06/14/2022] [Accepted: 06/14/2022] [Indexed: 12/27/2022] Open
Abstract
Precision oncology, which ensures optimized cancer treatment tailored to the unique biology of a patient’s disease, has rapidly developed and is of great clinical importance. Deep learning has become the main method for precision oncology. This paper summarizes the recent deep-learning approaches relevant to precision oncology and reviews over 150 articles within the last six years. First, we survey the deep-learning approaches categorized by various precision oncology tasks, including the estimation of dose distribution for treatment planning, survival analysis and risk estimation after treatment, prediction of treatment response, and patient selection for treatment planning. Secondly, we provide an overview of the studies per anatomical area, including the brain, bladder, breast, bone, cervix, esophagus, gastric, head and neck, kidneys, liver, lung, pancreas, pelvis, prostate, and rectum. Finally, we highlight the challenges and discuss potential solutions for future research directions.
Collapse
|
32
|
Ranjan A, Lalwani D, Misra R. GAN for synthesizing CT from T2-weighted MRI data towards MR-guided radiation treatment. MAGMA (NEW YORK, N.Y.) 2022; 35:449-457. [PMID: 34741702 DOI: 10.1007/s10334-021-00974-5] [Citation(s) in RCA: 7] [Impact Index Per Article: 3.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 05/27/2021] [Revised: 10/12/2021] [Accepted: 10/25/2021] [Indexed: 06/13/2023]
Abstract
OBJECTIVE In medical domain, cross-modality image synthesis suffers from multiple issues , such as context-misalignment, image distortion, image blurriness, and loss of details. The fundamental objective behind this study is to address these issues in estimating synthetic Computed tomography (sCT) scans from T2-weighted Magnetic Resonance Imaging (MRI) scans to achieve MRI-guided Radiation Treatment (RT). MATERIALS AND METHODS We proposed a conditional generative adversarial network (cGAN) with multiple residual blocks to estimate sCT from T2-weighted MRI scans using 367 paired brain MR-CT images dataset. Few state-of-the-art deep learning models were implemented to generate sCT including Pix2Pix model, U-Net model, autoencoder model and their results were compared, respectively. RESULTS Results with paired MR-CT image dataset demonstrate that the proposed model with nine residual blocks in generator architecture results in the smallest mean absolute error (MAE) value of [Formula: see text], and mean squared error (MSE) value of [Formula: see text], and produces the largest Pearson correlation coefficient (PCC) value of [Formula: see text], SSIM value of [Formula: see text] and peak signal-to-noise ratio (PSNR) value of [Formula: see text], respectively. We qualitatively evaluated our result by visual comparisons of generated sCT to original CT of respective MRI input. DISCUSSION The quantitative and qualitative comparison of this work demonstrates that deep learning-based cGAN model can be used to estimate sCT scan from a reference T2 weighted MRI scan. The overall accuracy of our proposed model outperforms different state-of-the-art deep learning-based models.
Collapse
Affiliation(s)
- Amit Ranjan
- Department of Computer Science and Engineering, Indian Institute of Technology Patna, Bihta, 801103, India.
| | - Debanshu Lalwani
- Department of Computer Science and Engineering, Indian Institute of Technology Patna, Bihta, 801103, India
| | - Rajiv Misra
- Department of Computer Science and Engineering, Indian Institute of Technology Patna, Bihta, 801103, India
| |
Collapse
|
33
|
Sheikh K, Liu D, Li H, Acharya S, Ladra MM, Hrinivich WT. Dosimetric evaluation of cone-beam CT-based synthetic CTs in pediatric patients undergoing intensity-modulated proton therapy. J Appl Clin Med Phys 2022; 23:e13604. [PMID: 35413144 PMCID: PMC9194971 DOI: 10.1002/acm2.13604] [Citation(s) in RCA: 7] [Impact Index Per Article: 3.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/29/2021] [Revised: 03/10/2022] [Accepted: 03/21/2022] [Indexed: 11/07/2022] Open
Abstract
PURPOSE To evaluate dosimetric changes detected using synthetic computed tomography (sCT) derived from online cone-beam CTs (CBCT) in pediatric patients treated using intensity-modulated proton therapy (IMPT). METHODS Ten pediatric patients undergoing IMPT and aligned daily using proton gantry-mounted CBCT were identified for retrospective analysis with treated anatomical sites fully encompassed in the CBCT field of view. Dates were identified when the patient received both a CBCT and a quality assurance CT (qCT) for routine dosimetric evaluation. sCTs were generated based on a deformable registration between the initial plan CT (pCT) and CBCT. The clinical IMPT plans were re-computed on the same day qCT and sCT, and dosimetric changes due to tissue change or response from the initial plan were computed using each image. Linear regression analysis was performed to determine the correlation between dosimetric changes detected using the qCT and the sCT. Gamma analysis was also used to compare the dose distributions computed on the qCT and sCT. RESULTS The correlation coefficients (p-values) between qCTs and sCTs for changes detected in target coverage, overall maximum dose, and organ at risk dose were 0.97 (< .001), 0.84 (.002) and 0.91 (< .001), respectively. Mean ± SD gamma pass rates of the sCT-based dose compared to the qCT-based dose at 3%/3 mm, 3%/2 mm, and 2%/2 mm criteria were 96.5%±4.5%, 93.2%±6.3%, and 91.3%±7.8%, respectively. Pass rates tended to be lower for targets near lung. CONCLUSION While insufficient for re-planning, sCTs provide approximate dosimetry without administering additional imaging dose in pediatric patients undergoing IMPT. Dosimetric changes detected using sCTs are correlated with changes detected using clinically-standard qCTs; however, residual differences in dosimetry remain a limitation. Further improvements in sCT image quality may both improve online dosimetric evaluation and reduce imaging dose for pediatric patients by reducing the need for routine qCTs.
Collapse
Affiliation(s)
- Khadija Sheikh
- Department of Radiation Oncology and Molecular Sciences, Johns Hopkins University School of Medicine, Baltimore, Maryland, USA
| | - Dezhi Liu
- Department of Radiation Oncology and Molecular Sciences, Johns Hopkins University School of Medicine, Baltimore, Maryland, USA
| | - Heng Li
- Department of Radiation Oncology and Molecular Sciences, Johns Hopkins University School of Medicine, Baltimore, Maryland, USA
| | - Sahaja Acharya
- Department of Radiation Oncology and Molecular Sciences, Johns Hopkins University School of Medicine, Baltimore, Maryland, USA
| | - Matthew M Ladra
- Department of Radiation Oncology and Molecular Sciences, Johns Hopkins University School of Medicine, Baltimore, Maryland, USA
| | - William T Hrinivich
- Department of Radiation Oncology and Molecular Sciences, Johns Hopkins University School of Medicine, Baltimore, Maryland, USA
| |
Collapse
|
34
|
Farina E, Nabhen JJ, Dacoregio MI, Batalini F, Moraes FY. An overview of artificial intelligence in oncology. Future Sci OA 2022; 8:FSO787. [PMID: 35369274 PMCID: PMC8965797 DOI: 10.2144/fsoa-2021-0074] [Citation(s) in RCA: 17] [Impact Index Per Article: 8.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/11/2021] [Accepted: 01/19/2022] [Indexed: 11/23/2022] Open
Abstract
Cancer is associated with significant morbimortality globally. Advances in screening, diagnosis, management and survivorship were substantial in the last decades, however, challenges in providing personalized and data-oriented care remain. Artificial intelligence (AI), a branch of computer science used for predictions and automation, has emerged as potential solution to improve the healthcare journey and to promote precision in healthcare. AI applications in oncology include, but are not limited to, optimization of cancer research, improvement of clinical practice (eg., prediction of the association of multiple parameters and outcomes - prognosis and response) and better understanding of tumor molecular biology. In this review, we examine the current state of AI in oncology, including fundamentals, current applications, limitations and future perspectives.
Collapse
Affiliation(s)
- Eduardo Farina
- Department of Radiology, Federal University of São Paulo, SP, 04021-001, Brazil; Diagnósticos da America SA (Dasa), 05425-020, Brazil
| | - Jacqueline J Nabhen
- School of Medicine, Federal University of Paraná, Curitiba, PR, 80060-000, Brazil
| | - Maria Inez Dacoregio
- School of Medicine, State University of Centro-Oeste, Guarapuava, PR, 85040-167, Brazil
| | - Felipe Batalini
- Department of Medicine, Division of Medical Oncology, Beth Israel Deaconess Medical Center, Harvard Medical School, Boston, MA 02215, USA
| | - Fabio Y Moraes
- Department of Oncology, Division of Radiation Oncology, Queen's University, Kingston, ON, K7L 3N6, Canada
| |
Collapse
|
35
|
Generative Adversarial Networks in Brain Imaging: A Narrative Review. J Imaging 2022; 8:jimaging8040083. [PMID: 35448210 PMCID: PMC9028488 DOI: 10.3390/jimaging8040083] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/21/2021] [Revised: 03/08/2022] [Accepted: 03/15/2022] [Indexed: 02/04/2023] Open
Abstract
Artificial intelligence (AI) is expected to have a major effect on radiology as it demonstrated remarkable progress in many clinical tasks, mostly regarding the detection, segmentation, classification, monitoring, and prediction of diseases. Generative Adversarial Networks have been proposed as one of the most exciting applications of deep learning in radiology. GANs are a new approach to deep learning that leverages adversarial learning to tackle a wide array of computer vision challenges. Brain radiology was one of the first fields where GANs found their application. In neuroradiology, indeed, GANs open unexplored scenarios, allowing new processes such as image-to-image and cross-modality synthesis, image reconstruction, image segmentation, image synthesis, data augmentation, disease progression models, and brain decoding. In this narrative review, we will provide an introduction to GANs in brain imaging, discussing the clinical potential of GANs, future clinical applications, as well as pitfalls that radiologists should be aware of.
Collapse
|
36
|
Recent Applications of Artificial Intelligence in Radiotherapy: Where We Are and Beyond. APPLIED SCIENCES-BASEL 2022. [DOI: 10.3390/app12073223] [Citation(s) in RCA: 10] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 12/12/2022]
Abstract
In recent decades, artificial intelligence (AI) tools have been applied in many medical fields, opening the possibility of finding novel solutions for managing very complex and multifactorial problems, such as those commonly encountered in radiotherapy (RT). We conducted a PubMed and Scopus search to identify the AI application field in RT limited to the last four years. In total, 1824 original papers were identified, and 921 were analyzed by considering the phase of the RT workflow according to the applied AI approaches. AI permits the processing of large quantities of information, data, and images stored in RT oncology information systems, a process that is not manageable for individuals or groups. AI allows the iterative application of complex tasks in large datasets (e.g., delineating normal tissues or finding optimal planning solutions) and might support the entire community working in the various sectors of RT, as summarized in this overview. AI-based tools are now on the roadmap for RT and have been applied to the entire workflow, mainly for segmentation, the generation of synthetic images, and outcome prediction. Several concerns were raised, including the need for harmonization while overcoming ethical, legal, and skill barriers.
Collapse
|
37
|
O'Connor LM, Choi JH, Dowling JA, Warren-Forward H, Martin J, Greer PB. Comparison of Synthetic Computed Tomography Generation Methods, Incorporating Male and Female Anatomical Differences, for Magnetic Resonance Imaging-Only Definitive Pelvic Radiotherapy. Front Oncol 2022; 12:822687. [PMID: 35211413 PMCID: PMC8861348 DOI: 10.3389/fonc.2022.822687] [Citation(s) in RCA: 6] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/26/2021] [Accepted: 01/11/2022] [Indexed: 11/13/2022] Open
Abstract
Purpose There are several means of synthetic computed tomography (sCT) generation for magnetic resonance imaging (MRI)-only planning; however, much of the research omits large pelvic treatment regions and female anatomical specific methods. This research aimed to apply four of the most popular methods of sCT creation to facilitate MRI-only radiotherapy treatment planning for male and female anorectal and gynecological neoplasms. sCT methods were validated against conventional computed tomography (CT), with regard to Hounsfield unit (HU) estimation and plan dosimetry. Methods and Materials Paired MRI and CT scans of 40 patients were used for sCT generation and validation. Bulk density assignment, tissue class density assignment, hybrid atlas, and deep learning sCT generation methods were applied to all 40 patients. Dosimetric accuracy was assessed by dose difference at reference point, dose volume histogram (DVH) parameters, and 3D gamma dose comparison. HU estimation was assessed by mean error and mean absolute error in HU value between each sCT and CT. Results The median percentage dose difference between the CT and sCT was <1.0% for all sCT methods. The deep learning method resulted in the lowest median percentage dose difference to CT at −0.03% (IQR 0.13, −0.31) and bulk density assignment resulted in the greatest difference at −0.73% (IQR −0.10, −1.01). The mean 3D gamma dose agreement at 3%/2 mm among all sCT methods was 99.8%. The highest agreement at 1%/1 mm was 97.3% for the deep learning method and the lowest was 93.6% for the bulk density method. Deep learning and hybrid atlas techniques gave the lowest difference to CT in mean error and mean absolute error in HU estimation. Conclusions All methods of sCT generation used in this study resulted in similarly high dosimetric agreement for MRI-only planning of male and female cancer pelvic regions. The choice of the sCT generation technique can be guided by department resources available and image guidance considerations, with minimal impact on dosimetric accuracy.
Collapse
Affiliation(s)
- Laura M O'Connor
- Department of Radiation Oncology, Calvary Mater Hospital, Newcastle, NSW, Australia.,School of Health Sciences, University of Newcastle, Callaghan, NSW, Australia
| | - Jae H Choi
- Department of Radiation Oncology, Calvary Mater Hospital, Newcastle, NSW, Australia.,School of Mathematical and Physical Sciences, University of Newcastle, Callaghan, NSW, Australia
| | - Jason A Dowling
- Commonwealth Scientific and Industrial Research Organisation (CSIRO), Australian E-Health Research Centre, Herston, QLD, Australia
| | | | - Jarad Martin
- Department of Radiation Oncology, Calvary Mater Hospital, Newcastle, NSW, Australia.,School of Medicine and Public Health, University of Newcastle, Callaghan, NSW, Australia
| | - Peter B Greer
- Department of Radiation Oncology, Calvary Mater Hospital, Newcastle, NSW, Australia.,School of Mathematical and Physical Sciences, University of Newcastle, Callaghan, NSW, Australia
| |
Collapse
|
38
|
Wang C, Uh J, Patni T, Merchant T, Li Y, Hua CH, Acharya S. Toward MR-only proton therapy planning for pediatric brain tumors: synthesis of relative proton stopping power images with multiple sequence MRI and development of an online quality assurance tool. Med Phys 2022; 49:1559-1570. [PMID: 35075670 DOI: 10.1002/mp.15479] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/22/2021] [Revised: 12/23/2021] [Accepted: 01/11/2022] [Indexed: 11/11/2022] Open
Abstract
PURPOSE To generate synthetic relative proton-stopping-power (sRPSP) images from MRI sequence(s) and develop an online quality assurance (QA) tool for sRPSP to facilitate safe integration of MR-only proton planning into clinical practice. MATERIALS AND METHODS Planning CT and MR images of 195 pediatric brain tumor patients were utilized (training: 150, testing: 45). Seventeen consistent-cycle Generative Adversarial Network (ccGAN) models were trained separately using paired CT-converted RPSP and MRI datasets to transform a subject's MRI into sRPSP. T1-weighted (T1W), T2-weighted (T2W), and FLAIR MRI were permutated to form 17 combinations, with or without preprocessing, for determining the optimal training sequence(s). For evaluation, sRPSP images were converted to synthetic CT (sCT) and compared to the real CT in terms of mean absolute error (MAE) in HU. For QA, sCT was deformed and compared to a reference template built from training dataset to produce a flag map, highlighting pixels that deviate by >100 HU and fall outside the mean ± standard deviation reference intensity. The gamma intensity analysis (10%/3mm) of the deformed sCT against the QA template on the intensity difference was investigated as a surrogate of sCT accuracy. RESULTS The sRPSP images generated from a single T1W or T2W sequence outperformed that generated from multi-MRI sequences in terms of MAE (all P<0.05). Preprocessing with N4 bias and histogram matching reduced MAE of T2W MRI-based sCT (54±21 HU vs. 42±13 HU, P = .002). The gamma intensity analysis of sCT against the QA template was highly correlated with the MAE of sCT against the real CT in the testing cohort (r = -0.89 for T1W sCT; r = -0.93 for T2W sCT). CONCLUSION Accurate sRPSP images can be generated from T1W/T2W MRI for proton planning. A QA tool highlights regions of inaccuracy, flagging problematic cases unsuitable for clinical use. This article is protected by copyright. All rights reserved.
Collapse
Affiliation(s)
- Chuang Wang
- Department of Radiation Oncology, St. Jude Children's Research Hospital, Memphis, TN, United States Of America
| | - Jinsoo Uh
- Department of Radiation Oncology, St. Jude Children's Research Hospital, Memphis, TN, United States Of America
| | - Tushar Patni
- Department of Biostatistics, St. Jude Children's Research Hospital, Memphis, TN, United States Of America
| | - Thomas Merchant
- Department of Radiation Oncology, St. Jude Children's Research Hospital, Memphis, TN, United States Of America
| | - Yimei Li
- Department of Biostatistics, St. Jude Children's Research Hospital, Memphis, TN, United States Of America
| | - Chia-Ho Hua
- Department of Radiation Oncology, St. Jude Children's Research Hospital, Memphis, TN, United States Of America
| | - Sahaja Acharya
- Department of Radiation Oncology, St. Jude Children's Research Hospital, Memphis, TN, United States Of America.,Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins Medicine, Baltimore, MD, United States Of America
| |
Collapse
|
39
|
Florkow MC, Willemsen K, Mascarenhas VV, Oei EHG, van Stralen M, Seevinck PR. Magnetic Resonance Imaging Versus Computed Tomography for Three-Dimensional Bone Imaging of Musculoskeletal Pathologies: A Review. J Magn Reson Imaging 2022; 56:11-34. [PMID: 35044717 PMCID: PMC9305220 DOI: 10.1002/jmri.28067] [Citation(s) in RCA: 23] [Impact Index Per Article: 11.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/13/2021] [Revised: 12/31/2021] [Accepted: 01/05/2022] [Indexed: 12/18/2022] Open
Abstract
Magnetic resonance imaging (MRI) is increasingly utilized as a radiation‐free alternative to computed tomography (CT) for the diagnosis and treatment planning of musculoskeletal pathologies. MR imaging of hard tissues such as cortical bone remains challenging due to their low proton density and short transverse relaxation times, rendering bone tissues as nonspecific low signal structures on MR images obtained from most sequences. Developments in MR image acquisition and post‐processing have opened the path for enhanced MR‐based bone visualization aiming to provide a CT‐like contrast and, as such, ease clinical interpretation. The purpose of this review is to provide an overview of studies comparing MR and CT imaging for diagnostic and treatment planning purposes in orthopedic care, with a special focus on selective bone visualization, bone segmentation, and three‐dimensional (3D) modeling. This review discusses conventional gradient‐echo derived techniques as well as dedicated short echo time acquisition techniques and post‐processing techniques, including the generation of synthetic CT, in the context of 3D and specific bone visualization. Based on the reviewed literature, it may be concluded that the recent developments in MRI‐based bone visualization are promising. MRI alone provides valuable information on both bone and soft tissues for a broad range of applications including diagnostics, 3D modeling, and treatment planning in multiple anatomical regions, including the skull, spine, shoulder, pelvis, and long bones.
Collapse
Affiliation(s)
- Mateusz C Florkow
- Image Sciences Institute, University Medical Center Utrecht, Utrecht, The Netherlands
| | - Koen Willemsen
- Department of Orthopedics, University Medical Center Utrecht, Utrecht, The Netherlands
| | - Vasco V Mascarenhas
- Musculoskeletal Imaging Unit, Imaging Center, Hospital da Luz, Lisbon, Portugal
| | - Edwin H G Oei
- Department of Radiology and Nuclear Medicine, Erasmus MC, University Medical Center Rotterdam, Rotterdam, The Netherlands
| | - Marijn van Stralen
- Image Sciences Institute, University Medical Center Utrecht, Utrecht, The Netherlands.,MRIguidance BV, Utrecht, The Netherlands
| | - Peter R Seevinck
- Image Sciences Institute, University Medical Center Utrecht, Utrecht, The Netherlands.,MRIguidance BV, Utrecht, The Netherlands
| |
Collapse
|
40
|
Lerner M, Medin J, Jamtheim Gustafsson C, Alkner S, Olsson LE. Prospective Clinical Feasibility Study for MRI-Only Brain Radiotherapy. Front Oncol 2022; 11:812643. [PMID: 35083159 PMCID: PMC8784680 DOI: 10.3389/fonc.2021.812643] [Citation(s) in RCA: 7] [Impact Index Per Article: 3.5] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/10/2021] [Accepted: 12/20/2021] [Indexed: 11/14/2022] Open
Abstract
OBJECTIVES MRI-only radiotherapy (RT) provides a workflow to decrease the geometric uncertainty introduced by the image registration process between MRI and CT data and to streamline the RT planning. Despite the recent availability of validated synthetic CT (sCT) methods for the head region, there are no clinical implementations reported for brain tumors. Based on a preceding validation study of sCT, this study aims to investigate MRI-only brain RT through a prospective clinical feasibility study with endpoints for dosimetry and patient setup. MATERIAL AND METHODS Twenty-one glioma patients were included. MRI Dixon images were used to generate sCT images using a CE-marked deep learning-based software. RT treatment plans were generated based on MRI delineated anatomical structures and sCT for absorbed dose calculations. CT scans were acquired but strictly used for sCT quality assurance (QA). Prospective QA was performed prior to MRI-only treatment approval, comparing sCT and CT image characteristics and calculated dose distributions. Additional retrospective analysis of patient positioning and dose distribution gamma evaluation was performed. RESULTS Twenty out of 21 patients were treated using the MRI-only workflow. A single patient was excluded due to an MRI artifact caused by a hemostatic substance injected near the target during surgery preceding radiotherapy. All other patients fulfilled the acceptance criteria. Dose deviations in target were within ±1% for all patients in the prospective analysis. Retrospective analysis yielded gamma pass rates (2%, 2 mm) above 99%. Patient positioning using CBCT images was within ± 1 mm for registrations with sCT compared to CT. CONCLUSION We report a successful clinical study of MRI-only brain radiotherapy, conducted using both prospective and retrospective analysis. Synthetic CT images generated using the CE-marked deep learning-based software were clinically robust based on endpoints for dosimetry and patient positioning.
Collapse
Affiliation(s)
- Minna Lerner
- Department of Hematology, Oncology, and Radiation Physics, Skåne University Hospital, Lund, Sweden
- Department of Translational Medicine, Medical Radiation Physics, Lund University, Malmö, Sweden
| | - Joakim Medin
- Department of Hematology, Oncology, and Radiation Physics, Skåne University Hospital, Lund, Sweden
- Department of Medical Radiation Physics, Clinical Sciences, Lund, Lund University, Lund, Sweden
| | - Christian Jamtheim Gustafsson
- Department of Hematology, Oncology, and Radiation Physics, Skåne University Hospital, Lund, Sweden
- Department of Translational Medicine, Medical Radiation Physics, Lund University, Malmö, Sweden
| | - Sara Alkner
- Department of Hematology, Oncology, and Radiation Physics, Skåne University Hospital, Lund, Sweden
- Department of Clinical Sciences Lund, Oncology and Pathology, Lund University, Lund, Sweden
| | - Lars E. Olsson
- Department of Hematology, Oncology, and Radiation Physics, Skåne University Hospital, Lund, Sweden
- Department of Translational Medicine, Medical Radiation Physics, Lund University, Malmö, Sweden
| |
Collapse
|
41
|
Feasibility of Synthetic Computed Tomography Images Generated from Magnetic Resonance Imaging Scans Using Various Deep Learning Methods in the Planning of Radiation Therapy for Prostate Cancer. Cancers (Basel) 2021; 14:cancers14010040. [PMID: 35008204 PMCID: PMC8750723 DOI: 10.3390/cancers14010040] [Citation(s) in RCA: 9] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/23/2021] [Revised: 12/17/2021] [Accepted: 12/20/2021] [Indexed: 11/17/2022] Open
Abstract
Simple Summary MRI-only simulation in radiation therapy (RT) planning has received attention because the CT scan can be omitted. For MRI-only simulation, synthetic CT (sCT) is necessary for the dose calculation. Various methodologies have been suggested for the generation of sCT and, recently, methods using the deep learning approaches are actively investigated. GAN and cycle-consistent GAN (CycGAN) have been mainly tested, however, very limited studies compared the qualities of sCTs generated from these methods or suggested other models for sCT generation. We have compared GAN, CycGAN, and, reference-guided GAN (RgGAN), a new model of deep learning method. We found that the performance in the HU conservation for soft tissue was poorest for GAN. All methods could generate sCTs feasible for VMAT planning with the trend that sCT generated from the RgGAN showed best performance in dosimetric conservation D98% and D95% than sCTs from other methodologies. Abstract We aimed to evaluate and compare the qualities of synthetic computed tomography (sCT) generated by various deep-learning methods in volumetric modulated arc therapy (VMAT) planning for prostate cancer. Simulation computed tomography (CT) and T2-weighted simulation magnetic resonance image from 113 patients were used in the sCT generation by three deep-learning approaches: generative adversarial network (GAN), cycle-consistent GAN (CycGAN), and reference-guided CycGAN (RgGAN), a new model which performed further adjustment of sCTs generated by CycGAN with available paired images. VMAT plans on the original simulation CT images were recalculated on the sCTs and the dosimetric differences were evaluated. For soft tissue, a significant difference in the mean Hounsfield unites (HUs) was observed between the original CT images and only sCTs from GAN (p = 0.03). The mean relative dose differences for planning target volumes or organs at risk were within 2% among the sCTs from the three deep-learning approaches. The differences in dosimetric parameters for D98% and D95% from original CT were lowest in sCT from RgGAN. In conclusion, HU conservation for soft tissue was poorest for GAN. There was the trend that sCT generated from the RgGAN showed best performance in dosimetric conservation D98% and D95% than sCTs from other methodologies.
Collapse
|
42
|
Huang J, Shlobin NA, Lam SK, DeCuypere M. Artificial Intelligence Applications in Pediatric Brain Tumor Imaging: A Systematic Review. World Neurosurg 2021; 157:99-105. [PMID: 34648981 DOI: 10.1016/j.wneu.2021.10.068] [Citation(s) in RCA: 13] [Impact Index Per Article: 4.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/13/2021] [Accepted: 10/04/2021] [Indexed: 01/23/2023]
Abstract
OBJECTIVE Artificial intelligence (AI) has facilitated the analysis of medical imaging given increased computational capacity and medical data availability in recent years. Although many applications for AI in the imaging of brain tumors have been proposed, their potential clinical impact remains to be explored. A systematic review was performed to examine the role of AI in the analysis of pediatric brain tumor imaging. METHODS PubMed, Embase, and Scopus were searched for relevant articles up to January 27, 2021. RESULTS Literature search identified 298 records, of which 22 studies were included. The most commonly studied tumors were posterior fossa tumors including brainstem glioma, ependymoma, medulloblastoma, and pilocytic astrocytoma (15, 68%). Tumor diagnosis was the most frequently performed task (14, 64%), followed by tumor segmentation (3, 14%) and tumor detection (3, 14%). Of the 6 studies comparing AI to clinical experts, 5 demonstrated superiority of AI for tumor diagnosis. Other tasks including tumor segmentation, attenuation correction of positron emission tomography scans, image registration for patient positioning, and dose calculation for radiotherapy were performed with high accuracy comparable with clinical experts. No studies described use of the AI tool in routine clinical practice. CONCLUSIONS AI methods for analysis of pediatric brain tumor imaging have increased exponentially in recent years. However, adoption of these methods in clinical practice requires further characterization of validity and utility. Implementation of these methods may streamline clinical workflows by improving diagnostic accuracy and automating basic imaging analysis tasks.
Collapse
Affiliation(s)
- Jonathan Huang
- Department of Neurological Surgery, Northwestern University Feinberg School of Medicine, Division of Pediatric Neurosurgery, Ann and Robert H. Lurie Children's Hospital, Chicago, Illinois, USA
| | - Nathan A Shlobin
- Department of Neurological Surgery, Northwestern University Feinberg School of Medicine, Division of Pediatric Neurosurgery, Ann and Robert H. Lurie Children's Hospital, Chicago, Illinois, USA
| | - Sandi K Lam
- Department of Neurological Surgery, Northwestern University Feinberg School of Medicine, Division of Pediatric Neurosurgery, Ann and Robert H. Lurie Children's Hospital, Chicago, Illinois, USA
| | - Michael DeCuypere
- Department of Neurological Surgery, Northwestern University Feinberg School of Medicine, Division of Pediatric Neurosurgery, Ann and Robert H. Lurie Children's Hospital, Chicago, Illinois, USA.
| |
Collapse
|
43
|
Hoeben BA, Seravalli E, Wood AM, Bosman M, Matysiak WP, Maduro JH, van Lier AL, Maspero M, Bol GH, Janssens GO. Influence of eye movement on lens dose and optic nerve target coverage during craniospinal irradiation. Clin Transl Radiat Oncol 2021; 31:28-33. [PMID: 34522796 PMCID: PMC8427085 DOI: 10.1016/j.ctro.2021.08.009] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/03/2021] [Revised: 08/11/2021] [Accepted: 08/25/2021] [Indexed: 12/18/2022] Open
Abstract
Purpose Optic nerves are part of the craniospinal irradiation (CSI) target volume. Modern radiotherapy techniques achieve highly conformal target doses while avoiding organs-at-risk such as the lens. The magnitude of eye movement and its influence on CSI target- and avoidance volumes are unclear. We aimed to evaluate the movement-range of lenses and optic nerves and its influence on dose distribution of several planning techniques. Methods Ten volunteers underwent MRI scans in various gaze directions (neutral, left, right, cranial, caudal). Lenses, orbital optic nerves, optic discs and CSI target volumes were delineated. 36-Gy cranial irradiation plans were constructed on synthetic CT images in neutral gaze, with Volumetric Modulated Arc Therapy, pencil-beam scanning proton therapy, and 3D-conventional photons. Movement-amplitudes of lenses and optic discs were analyzed, and influence of gaze direction on lens and orbital optic nerve dose distribution. Results Mean eye structures' shift from neutral position was greatest in caudal gaze; -5.8±1.2 mm (±SD) for lenses and 7.0±2.0 mm for optic discs. In 3D-conventional plans, caudal gaze decreased Mean Lens Dose (MLD). In VMAT and proton plans, eye movements mainly increased MLD and diminished D98 orbital optic nerve (D98OON) coverage; mean MLD increased up to 5.5 Gy [total ΔMLD range -8.1 to 10.0 Gy], and mean D98OON decreased up to 3.3 Gy [total ΔD98OON range -13.6 to 1.2 Gy]. VMAT plans optimized for optic disc Internal Target Volume and lens Planning organ-at-Risk Volume resulted in higher MLD over gaze directions. D98OON became ≥95% of prescribed dose over 95/100 evaluated gaze directions, while all-gaze bilateral D98OON significantly changed in 1 of 10 volunteers. Conclusion With modern CSI techniques, eye movements result in higher lens doses and a mean detriment for orbital optic nerve dose coverage of <10% of prescribed dose.
Collapse
Key Words
- 3D-conventional
- COM, center of mass
- CSI, craniospinal irradiation
- CTVvoxelwise min, voxelwise minimum CTV
- Craniospinal irradiation
- D98OON, D98 orbital optic nerve
- ITVoptic disc, internal target volume around optic discs
- Lens
- MLD, mean lens dose
- OON, orbital optic nerve
- Optic nerve
- PBS, pencil-beam scanning
- PRVlens, planning organ-at-risk volume around lenses
- Proton
- SIOPE, European International Society for Paediatric Oncology
- VMAT
- sCT, synthetic CT
Collapse
Affiliation(s)
- Bianca A.W. Hoeben
- Department of Radiation Oncology, University Medical Center Utrecht, Utrecht, the Netherlands
- Princess Máxima Center for Pediatric Oncology, Utrecht, the Netherlands
- Corresponding author at: Department of Radiation Oncology, University Medical Center Utrecht and Princess Máxima Center for Pediatric Oncology, PO Box 85500, Q.00.311, 3508 GA Utrecht, the Netherlands.
| | - Enrica Seravalli
- Department of Radiation Oncology, University Medical Center Utrecht, Utrecht, the Netherlands
| | - Amber M.L. Wood
- Princess Máxima Center for Pediatric Oncology, Utrecht, the Netherlands
- Radboud University, Nijmegen, the Netherlands
| | - Mirjam Bosman
- Department of Radiation Oncology, University Medical Center Utrecht, Utrecht, the Netherlands
| | - Witold P. Matysiak
- Department of Radiation Oncology, University of Groningen, University Medical Center Groningen, Groningen, the Netherlands
| | - John H. Maduro
- Princess Máxima Center for Pediatric Oncology, Utrecht, the Netherlands
- Department of Radiation Oncology, University of Groningen, University Medical Center Groningen, Groningen, the Netherlands
| | | | - Matteo Maspero
- Department of Radiation Oncology, University Medical Center Utrecht, Utrecht, the Netherlands
| | - Gijsbert H. Bol
- Department of Radiation Oncology, University Medical Center Utrecht, Utrecht, the Netherlands
| | - Geert O. Janssens
- Department of Radiation Oncology, University Medical Center Utrecht, Utrecht, the Netherlands
- Princess Máxima Center for Pediatric Oncology, Utrecht, the Netherlands
| |
Collapse
|
44
|
Boulanger M, Nunes JC, Chourak H, Largent A, Tahri S, Acosta O, De Crevoisier R, Lafond C, Barateau A. Deep learning methods to generate synthetic CT from MRI in radiotherapy: A literature review. Phys Med 2021; 89:265-281. [PMID: 34474325 DOI: 10.1016/j.ejmp.2021.07.027] [Citation(s) in RCA: 74] [Impact Index Per Article: 24.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 02/11/2021] [Revised: 07/15/2021] [Accepted: 07/19/2021] [Indexed: 01/04/2023] Open
Abstract
PURPOSE In radiotherapy, MRI is used for target volume and organs-at-risk delineation for its superior soft-tissue contrast as compared to CT imaging. However, MRI does not provide the electron density of tissue necessary for dose calculation. Several methods of synthetic-CT (sCT) generation from MRI data have been developed for radiotherapy dose calculation. This work reviewed deep learning (DL) sCT generation methods and their associated image and dose evaluation, in the context of MRI-based dose calculation. METHODS We searched the PubMed and ScienceDirect electronic databases from January 2010 to March 2021. For each paper, several items were screened and compiled in figures and tables. RESULTS This review included 57 studies. The DL methods were either generator-only based (45% of the reviewed studies), or generative adversarial network (GAN) architecture and its variants (55% of the reviewed studies). The brain and pelvis were the most commonly investigated anatomical localizations (39% and 28% of the reviewed studies, respectively), and more rarely, the head-and-neck (H&N) (15%), abdomen (10%), liver (5%) or breast (3%). All the studies performed an image evaluation of sCTs with a diversity of metrics, with only 36 studies performing dosimetric evaluations of sCT. CONCLUSIONS The median mean absolute errors were around 76 HU for the brain and H&N sCTs and 40 HU for the pelvis sCTs. For the brain, the mean dose difference between the sCT and the reference CT was <2%. For the H&N and pelvis, the mean dose difference was below 1% in most of the studies. Recent GAN architectures have advantages compared to generator-only, but no superiority was found in term of image or dose sCT uncertainties. Key challenges of DL-based sCT generation methods from MRI in radiotherapy is the management of movement for abdominal and thoracic localizations, the standardization of sCT evaluation, and the investigation of multicenter impacts.
Collapse
Affiliation(s)
- M Boulanger
- Univ. Rennes 1, CLCC Eugène Marquis, INSERM, LTSI - UMR 1099, F-35000 Rennes, France
| | - Jean-Claude Nunes
- Univ. Rennes 1, CLCC Eugène Marquis, INSERM, LTSI - UMR 1099, F-35000 Rennes, France.
| | - H Chourak
- Univ. Rennes 1, CLCC Eugène Marquis, INSERM, LTSI - UMR 1099, F-35000 Rennes, France; CSIRO Australian e-Health Research Centre, Herston, Queensland, Australia
| | - A Largent
- Developing Brain Institute, Department of Diagnostic Imaging and Radiology, Children's National Hospital, Washington, DC, USA
| | - S Tahri
- Univ. Rennes 1, CLCC Eugène Marquis, INSERM, LTSI - UMR 1099, F-35000 Rennes, France
| | - O Acosta
- Univ. Rennes 1, CLCC Eugène Marquis, INSERM, LTSI - UMR 1099, F-35000 Rennes, France
| | - R De Crevoisier
- Univ. Rennes 1, CLCC Eugène Marquis, INSERM, LTSI - UMR 1099, F-35000 Rennes, France
| | - C Lafond
- Univ. Rennes 1, CLCC Eugène Marquis, INSERM, LTSI - UMR 1099, F-35000 Rennes, France
| | - A Barateau
- Univ. Rennes 1, CLCC Eugène Marquis, INSERM, LTSI - UMR 1099, F-35000 Rennes, France
| |
Collapse
|
45
|
Spadea MF, Maspero M, Zaffino P, Seco J. Deep learning based synthetic-CT generation in radiotherapy and PET: A review. Med Phys 2021; 48:6537-6566. [PMID: 34407209 DOI: 10.1002/mp.15150] [Citation(s) in RCA: 80] [Impact Index Per Article: 26.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/09/2021] [Revised: 06/06/2021] [Accepted: 07/13/2021] [Indexed: 01/22/2023] Open
Abstract
Recently,deep learning (DL)-based methods for the generation of synthetic computed tomography (sCT) have received significant research attention as an alternative to classical ones. We present here a systematic review of these methods by grouping them into three categories, according to their clinical applications: (i) to replace computed tomography in magnetic resonance (MR) based treatment planning, (ii) facilitate cone-beam computed tomography based image-guided adaptive radiotherapy, and (iii) derive attenuation maps for the correction of positron emission tomography. Appropriate database searching was performed on journal articles published between January 2014 and December 2020. The DL methods' key characteristics were extracted from each eligible study, and a comprehensive comparison among network architectures and metrics was reported. A detailed review of each category was given, highlighting essential contributions, identifying specific challenges, and summarizing the achievements. Lastly, the statistics of all the cited works from various aspects were analyzed, revealing the popularity and future trends and the potential of DL-based sCT generation. The current status of DL-based sCT generation was evaluated, assessing the clinical readiness of the presented methods.
Collapse
Affiliation(s)
- Maria Francesca Spadea
- Department Experimental and Clinical Medicine, University "Magna Graecia" of Catanzaro, Catanzaro, 88100, Italy
| | - Matteo Maspero
- Division of Imaging & Oncology, Department of Radiotherapy, University Medical Center Utrecht, Heidelberglaan, Utrecht, The Netherlands.,Computational Imaging Group for MR Diagnostics & Therapy, Center for Image Sciences, University Medical Center Utrecht, Heidelberglaan, Utrecht, The Netherlands
| | - Paolo Zaffino
- Department Experimental and Clinical Medicine, University "Magna Graecia" of Catanzaro, Catanzaro, 88100, Italy
| | - Joao Seco
- Division of Biomedical Physics in Radiation Oncology, DKFZ German Cancer Research Center, Heidelberg, Germany.,Department of Physics and Astronomy, Heidelberg University, Heidelberg, Germany
| |
Collapse
|
46
|
Farjam R, Nagar H, Kathy Zhou X, Ouellette D, Chiara Formenti S, DeWyngaert JK. Deep learning-based synthetic CT generation for MR-only radiotherapy of prostate cancer patients with 0.35T MRI linear accelerator. J Appl Clin Med Phys 2021; 22:93-104. [PMID: 34184390 PMCID: PMC8364266 DOI: 10.1002/acm2.13327] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/01/2021] [Revised: 05/25/2021] [Accepted: 05/27/2021] [Indexed: 12/19/2022] Open
Abstract
PURPOSE To develop a deep learning model to generate synthetic CT for MR-only radiotherapy of prostate cancer patients treated with 0.35 T MRI linear accelerator. MATERIALS AND METHODS A U-NET convolutional neural network was developed to translate 0.35 T TRUFI MRI into electron density map using a novel cost function equalizing the contribution of various tissue types including fat, muscle, bone, and background air in training. The impact of training time, dataset size, image standardization, and data augmentation approaches was also quantified. Mean absolute error (MAE) between synthetic and planning CTs was calculated to measure the goodness of the model. RESULTS With 20 patients in training, our U-NET model has the potential to generate synthetic CT with a MAE of about 29.68 ± 4.41, 16.34 ± 2.67, 23.36 ± 2.85, and 105.90 ± 22.80 HU over the entire body, fat, muscle, and bone tissues, respectively. As expected, we found that the number of patients used for training and MAE are nonlinearly correlated. Data augmentation and our proposed loss function were effective to improve MAE by ~9% and ~18% in bony voxels, respectively. Increasing the training time and image standardization did not improve the accuracy of the model. CONCLUSION A U-NET model has been developed and tested numerically to generate synthetic CT from 0.35T TRUFI MRI for MR-only radiotherapy of prostate cancer patients. Dosimetric evaluation using a large and independent dataset warrants the validity of the proposed model and the actual number of patients needed for the safe usage of the model in routine clinical workflow.
Collapse
Affiliation(s)
- Reza Farjam
- Department of Radiation OncologyWeill Cornell Medical CollegeNew YorkNew YorkUSA
| | - Himanshu Nagar
- Department of Radiation OncologyWeill Cornell Medical CollegeNew YorkNew YorkUSA
| | - Xi Kathy Zhou
- Public Health ScienceWeill Cornell Medical CollegeNew YorkNew YorkUSA
| | - David Ouellette
- Department of Radiation OncologyWeill Cornell Medical CollegeNew YorkNew YorkUSA
| | | | - J. Keith DeWyngaert
- Department of Radiation OncologyWeill Cornell Medical CollegeNew YorkNew YorkUSA
| |
Collapse
|
47
|
Guerreiro F, Svensson S, Seravalli E, Traneus E, Raaymakers BW. Intra-fractional per-beam adaptive workflow to mitigate the need for a rotating gantry during MRI-guided proton therapy. Phys Med Biol 2021; 66. [PMID: 34298523 DOI: 10.1088/1361-6560/ac176f] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/16/2021] [Accepted: 07/23/2021] [Indexed: 11/12/2022]
Abstract
The integration of real-time magnetic resonance imaging (MRI)-guidance and proton therapy would potentially improve the proton dose steering capability by reducing daily uncertainties due to anatomical variations. The use of a fixed beamline coupled with an axial patient couch rotation would greatly simplify the proton delivery with MRI-guidance. Nonetheless, it is mandatory to assure that the plan quality is not deteriorated by the anatomical deformations due to patient rotation. In this work, an in-house tool allowing for intra-fractional per-beam adaptation of intensity-modulated proton plans (BeamAdapt) was implemented through features available in RayStation. A set of three MRIs was acquired for two healthy volunteers (V1, V2): (1) no rotation/static, (2) rotation to the right and (3) left. V1 was rotated by 15º, to simulate a clinical pediatric abdominal case and V2 by 45º, to simulate an extreme patient rotation case. For each volunteer, a total of four intensity-modulated pencil beam scanning plans were optimized on the static MRI using virtual abdominal targets and 2-3 posterior-oblique beams. Beam angles were defined according to the angulations on the rotated MRIs. With BeamAdapt, each original plan was first converted into separate plans with one beam per plan. In an iterative order, individual beam doses were non-rigidly deformed to the rotated anatomies and re-optimized accounting for the consequent deformations and the beam doses delivered so far. For evaluation, the final adapted dose distribution was propagated back to the static MRI. Planned and adapted dose distributions were compared by computing relative differences between dose-volume histogram (DVH) metrics. Absolute target dose differences were on average below 1% and mean dose organs-at-risk differences were below 3%. With BeamAdapt, not only intra-fractional per-beam proton plan adaptation coupled with axial patient rotation is possible but also the need for a rotating gantry during MRI-guidance might be mitigated.
Collapse
Affiliation(s)
- Filipa Guerreiro
- Department of Radiotherapy, University Medical Center Utrecht Imaging Division, Utrecht, NETHERLANDS
| | | | - Enrica Seravalli
- Department of Radiotherapy, University Medical Center Utrecht Imaging Division, Utrecht, NETHERLANDS
| | - Erik Traneus
- RaySearch Laboratories AB, Stockholm, Stockholm, SWEDEN
| | - Bas W Raaymakers
- Department of Radiotherapy, University Medical Center Utrecht Imaging Division, Utrecht, NETHERLANDS
| |
Collapse
|
48
|
Wang C, Uh J, Merchant TE, Hua CH, Acharya S. Facilitating MR-Guided Adaptive Proton Therapy in Children Using Deep Learning-Based Synthetic CT. Int J Part Ther 2021; 8:11-20. [PMID: 35127971 PMCID: PMC8768893 DOI: 10.14338/ijpt-20-00099.1] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/21/2020] [Accepted: 05/10/2021] [Indexed: 11/21/2022] Open
Abstract
Abstract
Purpose
To determine whether self-attention cycle-generative adversarial networks (cycle-GANs), a novel deep-learning method, can generate accurate synthetic computed tomography (sCT) to facilitate adaptive proton therapy in children with brain tumors.
Materials and Methods
Both CT and T1-weighted magnetic resonance imaging (MRI) of 125 children (ages 1-20 years) with brain tumors were included in the training dataset. A model introducing a self-attention mechanism into the conventional cycle-GAN was created to enhance tissue interfaces and reduce noise. The test dataset consisted of 7 patients (ages 2-14 years) who underwent adaptive planning because of changes in anatomy discovered on MRI during proton therapy. The MRI during proton therapy-based sCT was compared with replanning CT (ground truth).
Results
The Hounsfield unit-mean absolute error was significantly reduced with self-attention cycle-GAN, as compared with conventional cycle-GAN (65.3 ± 13.9 versus 88.9 ± 19.3, P < .01). The average 3-dimensional gamma passing rates (2%/2 mm criteria) for the original plan on the anatomy of the day and for the adapted plan were high (97.6% ± 1.2% and 98.9 ± 0.9%, respectively) when using sCT generated by self-attention cycle-GAN. The mean absolute differences in clinical target volume (CTV) receiving 95% of the prescription dose and 80% distal falloff along the beam axis were 1.1% ± 0.8% and 1.1 ± 0.9 mm, respectively. Areas of greatest dose difference were distal to the CTV and corresponded to shifts in distal falloff. Plan adaptation was appropriately triggered in all test patients when using sCT.
Conclusion
The novel cycle-GAN model with self-attention outperforms conventional cycle-GAN for children with brain tumors. Encouraging dosimetric results suggest that sCT generation can be used to identify patients who would benefit from adaptive replanning.
Collapse
Affiliation(s)
- Chuang Wang
- Department of Radiation Oncology, St Jude Children's Research Hospital, Memphis, TN, USA
| | - Jinsoo Uh
- Department of Radiation Oncology, St Jude Children's Research Hospital, Memphis, TN, USA
| | - Thomas E. Merchant
- Department of Radiation Oncology, St Jude Children's Research Hospital, Memphis, TN, USA
| | - Chia-ho Hua
- Department of Radiation Oncology, St Jude Children's Research Hospital, Memphis, TN, USA
| | - Sahaja Acharya
- Department of Radiation Oncology, St Jude Children's Research Hospital, Memphis, TN, USA
| |
Collapse
|
49
|
Cusumano D, Boldrini L, Dhont J, Fiorino C, Green O, Güngör G, Jornet N, Klüter S, Landry G, Mattiucci GC, Placidi L, Reynaert N, Ruggieri R, Tanadini-Lang S, Thorwarth D, Yadav P, Yang Y, Valentini V, Verellen D, Indovina L. Artificial Intelligence in magnetic Resonance guided Radiotherapy: Medical and physical considerations on state of art and future perspectives. Phys Med 2021; 85:175-191. [PMID: 34022660 DOI: 10.1016/j.ejmp.2021.05.010] [Citation(s) in RCA: 49] [Impact Index Per Article: 16.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 01/30/2021] [Revised: 04/15/2021] [Accepted: 05/04/2021] [Indexed: 12/14/2022] Open
Abstract
Over the last years, technological innovation in Radiotherapy (RT) led to the introduction of Magnetic Resonance-guided RT (MRgRT) systems. Due to the higher soft tissue contrast compared to on-board CT-based systems, MRgRT is expected to significantly improve the treatment in many situations. MRgRT systems may extend the management of inter- and intra-fraction anatomical changes, offering the possibility of online adaptation of the dose distribution according to daily patient anatomy and to directly monitor tumor motion during treatment delivery by means of a continuous cine MR acquisition. Online adaptive treatments require a multidisciplinary and well-trained team, able to perform a series of operations in a safe, precise and fast manner while the patient is waiting on the treatment couch. Artificial Intelligence (AI) is expected to rapidly contribute to MRgRT, primarily by safely and efficiently automatising the various manual operations characterizing online adaptive treatments. Furthermore, AI is finding relevant applications in MRgRT in the fields of image segmentation, synthetic CT reconstruction, automatic (on-line) planning and the development of predictive models based on daily MRI. This review provides a comprehensive overview of the current AI integration in MRgRT from a medical physicist's perspective. Medical physicists are expected to be major actors in solving new tasks and in taking new responsibilities: their traditional role of guardians of the new technology implementation will change with increasing emphasis on the managing of AI tools, processes and advanced systems for imaging and data analysis, gradually replacing many repetitive manual tasks.
Collapse
Affiliation(s)
- Davide Cusumano
- Fondazione Policlinico Universitario Agostino Gemelli, IRCCS, Rome, Italy
| | - Luca Boldrini
- Fondazione Policlinico Universitario Agostino Gemelli, IRCCS, Rome, Italy
| | | | - Claudio Fiorino
- Medical Physics, San Raffaele Scientific Institute, Milan, Italy
| | - Olga Green
- Department of Radiation Oncology, Washington University School of Medicine, St. Louis, MO, USA
| | - Görkem Güngör
- Acıbadem MAA University, School of Medicine, Department of Radiation Oncology, Maslak Istanbul, Turkey
| | - Núria Jornet
- Servei de Radiofísica i Radioprotecció, Hospital de la Santa Creu i Sant Pau, Spain
| | - Sebastian Klüter
- Department of Radiation Oncology, Heidelberg University Hospital, Heidelberg, Germany
| | - Guillaume Landry
- Department of Radiation Oncology, LMU Munich, Munich, Germany; German Cancer Consortium (DKTK), Munich, Germany
| | | | - Lorenzo Placidi
- Fondazione Policlinico Universitario Agostino Gemelli, IRCCS, Rome, Italy.
| | - Nick Reynaert
- Department of Medical Physics, Institut Jules Bordet, Belgium
| | - Ruggero Ruggieri
- Dipartimento di Radioterapia Oncologica Avanzata, IRCCS "Sacro cuore - don Calabria", Negrar di Valpolicella (VR), Italy
| | - Stephanie Tanadini-Lang
- Department of Radiation Oncology, University Hospital Zurich and University of Zurich, Zurich, Switzerland
| | - Daniela Thorwarth
- Section for Biomedical Physics, Department of Radiation Oncology, University Hospital Tüebingen, Tübingen, Germany
| | - Poonam Yadav
- Department of Human Oncology School of Medicine and Public Heath University of Wisconsin - Madison, USA
| | - Yingli Yang
- Department of Radiation Oncology, David Geffen School of Medicine, University of California Los Angeles, USA
| | - Vincenzo Valentini
- Fondazione Policlinico Universitario Agostino Gemelli, IRCCS, Rome, Italy
| | - Dirk Verellen
- Department of Medical Physics, Iridium Cancer Network, Belgium; Faculty of Medicine and Health Sciences, Antwerp University, Antwerp, Belgium
| | - Luca Indovina
- Fondazione Policlinico Universitario Agostino Gemelli, IRCCS, Rome, Italy
| |
Collapse
|
50
|
Edmund JM, Andreasen D, Van Leemput K. Cone beam computed tomography based image guidance and quality assessment of prostate cancer for magnetic resonance imaging-only radiotherapy in the pelvis. PHYSICS & IMAGING IN RADIATION ONCOLOGY 2021; 18:55-60. [PMID: 34258409 PMCID: PMC8254192 DOI: 10.1016/j.phro.2021.05.001] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 02/16/2021] [Revised: 04/23/2021] [Accepted: 05/04/2021] [Indexed: 12/22/2022]
Abstract
MRI-only IGRT accuracy is ≤2 mm as compared to CT but significant differences were observed. MRI-only CBCT-based IGRT seems feasible but caution is advised. The median absolute error (MeAE) for independent verification on the sCT quality is proposed. A MeAE around 0.1 in mass density could call for sCT quality inspection.
Background and purpose Radiotherapy (RT) based on magentic resonance imaging (MRI) only is currently used clinically in the pelvis. A synthetic computed tomography (sCT) is needed for dose planning. Here, we investigate the accuracy of cone beam CT (CBCT) based MRI-only image guided RT (IGRT) and sCT image quality. Materials and methods CT, MRI and CBCT scans of ten prostate cancer patients were included. The MRI was converted to a sCT using a multi-atlas approach. The sCT, CT and MR images were auto-matched with the CBCT on the bony anatomy. Paired sCT-CT and sCT-CBCT data were created. CT numbers were converted to relative electron (RED) and mass densities (DES) using a standard calibration curve for the CT and sCT. For the CBCT RED/DES conversion, a phantom and paired CT-CBCT population based calibration curve was used. For the latter, the CBCT numbers were averaged in 100 HU bins and the known RED/DES of the CT were assigned. The paired sCT-CT and sCT-CBCT data were averaged in bins of 10 HU or 0.01 RED/DES. The median absolute error (MeAE) between the sCT-CT and sCT-CBCT bins was calculated. Wilcoxon rank-sum tests were carried out for the IGRT and MeAE study. Results The mean sCT or MR IGRT difference from CT was ≤ 2 mm but significant differences were observed. A CBCT HU or phantom-based RED/DES MeAE did not estimate the sCT quality similar to a CT based MeAE but the CBCT population-based RED/DES MeAE did. Conclusions MRI-only CBCT-based IGRT seems feasible but caution is advised. A MeAE around 0.1 DES could call for sCT quality inspection.
Collapse
Affiliation(s)
- Jens M Edmund
- Radiotherapy Research Unit, Department of Oncology, Gentofte and Herlev Hospital, University of Copenhagen, 2730 Herlev, Denmark.,Niels Bohr Institute, University of Copenhagen, 2100 Copenhagen, Denmark
| | - Daniel Andreasen
- Department of Health Technology, Technical University of Denmark, 2800 Lyngby, Denmark
| | - Koen Van Leemput
- Department of Health Technology, Technical University of Denmark, 2800 Lyngby, Denmark.,Martinos Center for Biomedical Imaging, Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, MA 02114, USA
| |
Collapse
|