1
|
Oh MY, Yoon KC, Hyeon S, Jang T, Choi Y, Kim J, Kong HJ, Chai YJ. Navigating the Future of 3D Laparoscopic Liver Surgeries: Visualization of Internal Anatomy on Laparoscopic Images With Augmented Reality. Surg Laparosc Endosc Percutan Tech 2024:00129689-990000000-00251. [PMID: 38965779 DOI: 10.1097/sle.0000000000001307] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/12/2024] [Accepted: 06/12/2024] [Indexed: 07/06/2024]
Abstract
INTRODUCTION Liver tumor resection requires precise localization of tumors and blood vessels. Despite advancements in 3-dimensional (3D) visualization for laparoscopic surgeries, challenges persist. We developed and evaluated an augmented reality (AR) system that overlays preoperative 3D models onto laparoscopic images, offering crucial support for 3D visualization during laparoscopic liver surgeries. METHODS Anatomic liver structures from preoperative computed tomography scans were segmented using open-source software including 3D Slicer and Maya 2022 for 3D model editing. A registration system was created with 3D visualization software utilizing a stereo registration input system to overlay the virtual liver onto laparoscopic images during surgical procedures. A controller was customized using a modified keyboard to facilitate manual alignment of the virtual liver with the laparoscopic image. The AR system was evaluated by 3 experienced surgeons who performed manual registration for a total of 27 images from 7 clinical cases. The evaluation criteria included registration time; measured in minutes, and accuracy; measured using the Dice similarity coefficient. RESULTS The overall mean registration time was 2.4±1.7 minutes (range: 0.3 to 9.5 min), and the overall mean registration accuracy was 93.8%±4.9% (range: 80.9% to 99.7%). CONCLUSION Our validated AR system has the potential to effectively enable the prediction of internal hepatic anatomic structures during 3D laparoscopic liver resection, and may enhance 3D visualization for select laparoscopic liver surgeries.
Collapse
Affiliation(s)
- Moon Young Oh
- Department of Surgery, Seoul National University College of Medicine, Seoul National University Boramae Medical Center
| | - Kyung Chul Yoon
- Department of Surgery, Seoul National University College of Medicine, Seoul National University Boramae Medical Center
| | - Seulgi Hyeon
- Department of Surgery, Seoul National University College of Medicine, Seoul National University Boramae Medical Center
| | - Taesoo Jang
- Department of Transdisciplinary Medicine, Seoul National University Hospital, Seoul, Korea
| | - Yeonjin Choi
- Department of Transdisciplinary Medicine, Seoul National University Hospital, Seoul, Korea
| | - Junki Kim
- Department of Transdisciplinary Medicine, Seoul National University Hospital, Seoul, Korea
| | - Hyoun-Joong Kong
- Department of Transdisciplinary Medicine, Seoul National University Hospital, Seoul, Korea
| | - Young Jun Chai
- Department of Surgery, Seoul National University College of Medicine, Seoul National University Boramae Medical Center
- Department of Transdisciplinary Medicine, Seoul National University Hospital, Seoul, Korea
| |
Collapse
|
2
|
El Hachimy I, Kabelma D, Echcharef C, Hassani M, Benamar N, Hajji N. A comprehensive survey on the use of deep learning techniques in glioblastoma. Artif Intell Med 2024; 154:102902. [PMID: 38852314 DOI: 10.1016/j.artmed.2024.102902] [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: 10/12/2023] [Revised: 04/28/2024] [Accepted: 06/02/2024] [Indexed: 06/11/2024]
Abstract
Glioblastoma, characterized as a grade 4 astrocytoma, stands out as the most aggressive brain tumor, often leading to dire outcomes. The challenge of treating glioblastoma is exacerbated by the convergence of genetic mutations and disruptions in gene expression, driven by alterations in epigenetic mechanisms. The integration of artificial intelligence, inclusive of machine learning algorithms, has emerged as an indispensable asset in medical analyses. AI is becoming a necessary tool in medicine and beyond. Current research on Glioblastoma predominantly revolves around non-omics data modalities, prominently including magnetic resonance imaging, computed tomography, and positron emission tomography. Nonetheless, the assimilation of omic data-encompassing gene expression through transcriptomics and epigenomics-offers pivotal insights into patients' conditions. These insights, reciprocally, hold significant value in refining diagnoses, guiding decision- making processes, and devising efficacious treatment strategies. This survey's core objective encompasses a comprehensive exploration of noteworthy applications of machine learning methodologies in the domain of glioblastoma, alongside closely associated research pursuits. The study accentuates the deployment of artificial intelligence techniques for both non-omics and omics data, encompassing a range of tasks. Furthermore, the survey underscores the intricate challenges posed by the inherent heterogeneity of Glioblastoma, delving into strategies aimed at addressing its multifaceted nature.
Collapse
Affiliation(s)
| | | | | | - Mohamed Hassani
- Cancer Division, Faculty of medicine, Department of Biomolecular Medicine, Imperial College, London, United Kingdom
| | - Nabil Benamar
- Moulay Ismail University of Meknes, Meknes, Morocco; Al Akhawayn University in Ifrane, Ifrane, Morocco.
| | - Nabil Hajji
- Cancer Division, Faculty of medicine, Department of Biomolecular Medicine, Imperial College, London, United Kingdom; Department of Medical Biochemistry, Molecular Biology and Immunology, School of Medicine, Virgen Macarena University Hospital, University of Seville, Seville, Spain
| |
Collapse
|
3
|
Saway BF, Courtney J, Barley J, Frankel B, Hofstetter C, Kalhorn S. Contrast enhanced ultrasound for traumatic spinal cord injury: an overview of current and future applications. Spinal Cord Ser Cases 2024; 10:31. [PMID: 38664470 PMCID: PMC11045808 DOI: 10.1038/s41394-024-00644-3] [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: 01/03/2024] [Revised: 04/08/2024] [Accepted: 04/17/2024] [Indexed: 04/28/2024] Open
Abstract
STUDY DESIGN Systematic review. OBJECTIVE Contrast-enhanced ultrasound (CEUS) is an imaging modality that has only recently seen neurosurgical application. CEUS uses inert microbubbles to intraoperatively visualize vasculature and perfusion of the brain and spinal cord in real time. Observation and augmentation of spinal cord perfusion is vital component of the management of traumatic spinal cord injury, yet there are limited imaging modalities to evaluate spinal cord perfusion. CEUS provides an intraoperative imaging tool to evaluate spinal cord perfusion in real time. The objective of this review is to evaluate the current literature on the various applications and benefits of CEUS in traumatic spinal cord injury. SETTING South Carolina, USA. METHODS This review was written according to the PRISMA 2020 guidelines. RESULTS 143 articles were found in our literature search, with 46 of them being unique. After excluding articles for relevance to CEUS and spinal cord injury, we were left with 10 papers. Studies in animal models have shown CEUS to be an effective non-invasive imaging modality that can detect perfusion changes of injured spinal cords in real time. CONCLUSION This imaging modality can provide object perfusion data of the nidus of injury, surrounding penumbra and healthy neural tissue in a traumatized spinal cord. Investigation in its use in humans is ongoing and remains promising to be an effective diagnostic and prognostic tool for those suffering from spinal cord injury.
Collapse
Affiliation(s)
- Brian Fabian Saway
- Medical University of South Carolina, Department of Neurosurgery, Charleston, SC, 29425, USA.
| | - James Courtney
- Florida State University College of Medicine, Tallahassee, FL, 32303, USA
| | - Jessica Barley
- Medical University of South Carolina, Department of Neurosurgery, Charleston, SC, 29425, USA
| | - Bruce Frankel
- Southern Illinois University School of Medicine, Department of Neurosurgery, Springfield, IL, 62702, USA
| | | | - Stephen Kalhorn
- Medical University of South Carolina, Department of Neurosurgery, Charleston, SC, 29425, USA
| |
Collapse
|
4
|
Tappero S, Fallara G, Chierigo F, Micalef A, Ambrosini F, Diaz R, Dorotei A, Pompeo E, Limena A, Bravi CA, Longoni M, Piccinelli ML, Barletta F, Albano L, Mazzone E, Dell'Oglio P. Intraoperative image-guidance during robotic surgery: is there clinical evidence of enhanced patient outcomes? Eur J Nucl Med Mol Imaging 2024:10.1007/s00259-024-06706-w. [PMID: 38607386 DOI: 10.1007/s00259-024-06706-w] [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: 12/19/2023] [Accepted: 03/25/2024] [Indexed: 04/13/2024]
Abstract
BACKGROUND To date, the benefit of image guidance during robot-assisted surgery (IGS) is an object of debate. The current study aims to address the quality of the contemporary body of literature concerning IGS in robotic surgery throughout different surgical specialties. METHODS A systematic review of all English-language articles on IGS, from January 2013 to March 2023, was conducted using PubMed, Cochrane library's Central, EMBASE, MEDLINE, and Scopus databases. Comparative studies that tested performance of IGS vs control were included for the quantitative synthesis, which addressed outcomes analyzed in at least three studies: operative time, length of stay, blood loss, surgical margins, complications, number of nodal retrievals, metastatic nodes, ischemia time, and renal function loss. Bias-corrected ratio of means (ROM) and bias-corrected odds ratio (OR) compared continuous and dichotomous variables, respectively. Subgroup analyses according to guidance type (i.e., 3D virtual reality vs ultrasound vs near-infrared fluoresce) were performed. RESULTS Twenty-nine studies, based on 11 surgical procedures of three specialties (general surgery, gynecology, urology), were included in the quantitative synthesis. IGS was associated with 12% reduction in length of stay (ROM 0.88; p = 0.03) and 13% reduction in blood loss (ROM 0.87; p = 0.03) but did not affect operative time (ROM 1.00; p = 0.9), or complications (OR 0.93; p = 0.4). IGS was associated with an estimated 44% increase in mean number of removed nodes (ROM 1.44; p < 0.001), and a significantly higher rate of metastatic nodal disease (OR 1.82; p < 0.001), as well as a significantly lower rate of positive surgical margins (OR 0.62; p < 0.001). In nephron sparing surgery, IGS significantly decreased renal function loss (ROM 0.37; p = 0.002). CONCLUSIONS Robot-assisted surgery benefits from image guidance, especially in terms of pathologic outcomes, namely higher detection of metastatic nodes and lower surgical margins. Moreover, IGS enhances renal function preservation and lowers surgical blood loss.
Collapse
Affiliation(s)
- Stefano Tappero
- Department of Urology, ASST Grande Ospedale Metropolitano Niguarda, Milan, Italy
| | - Giuseppe Fallara
- Department of Urology, European Institute of Oncology (IEO), University of Milan, Milan, Italy
| | - Francesco Chierigo
- Department of Urology, ASST Grande Ospedale Metropolitano Niguarda, Milan, Italy
- Department of Urology, Azienda Ospedaliera Nazionale SS. Antonio e Biagio e Cesare Arrigo, Alessandria, Italy
- Department of Urology, IRCCS Ospedale Policlinico San Martino, University of Genova, Genoa, Italy
- Department of Surgical and Diagnostic Integrated Sciences (DISC), University of Genova, Genoa, Italy
| | - Andrea Micalef
- Department of General Surgery, Luigi Sacco University Hospital, Milan, Italy
- Università Degli Studi Di Milano, Milan, Italy
| | - Francesca Ambrosini
- Department of Urology, IRCCS Ospedale Policlinico San Martino, University of Genova, Genoa, Italy
- Department of Surgical and Diagnostic Integrated Sciences (DISC), University of Genova, Genoa, Italy
| | - Raquel Diaz
- Department of Surgical and Diagnostic Integrated Sciences (DISC), University of Genova, Genoa, Italy
| | - Andrea Dorotei
- Department of Orthopaedics, Humanitas Clinical and Research Center, IRCCS, Rozzano, Milan, Italy
- Department of Biomedical Sciences, Humanitas University, Milan, Italy
| | - Edoardo Pompeo
- Neurosurgery and Gamma Knife Radiosurgery Unit, IRCCS Ospedale San Raffaele, Milan, Italy
| | - Alessia Limena
- Infertility Unit, Fondazione IRCCS Ca' Granda Ospedale Maggiore Policlinico, Milan, Italy
- Department of Clinical Sciences and Community Health, Università degli Studi di Milano, Milan, Italy
| | - Carlo Andrea Bravi
- Department of Urology, Northampton General Hospital, Northampton, UK
- Department of Urology, Royal Marsden Foundation Trust, London, UK
| | - Mattia Longoni
- Unit of Urology/Division of Oncology, Gianfranco Soldera Prostate Cancer Lab, IRCCS San Raffaele Scientific Institute, Milan, Italy
- Vita-Salute San Raffaele University, Milan, Italy
| | - Mattia Luca Piccinelli
- Department of Urology, European Institute of Oncology (IEO), University of Milan, Milan, Italy
| | - Francesco Barletta
- Unit of Urology/Division of Oncology, Gianfranco Soldera Prostate Cancer Lab, IRCCS San Raffaele Scientific Institute, Milan, Italy
- Vita-Salute San Raffaele University, Milan, Italy
| | - Luigi Albano
- Neurosurgery and Gamma Knife Radiosurgery Unit, IRCCS Ospedale San Raffaele, Milan, Italy
- Neuroimaging Research Unit, Division of Neuroscience, IRCCS Ospedale San Raffaele, Milan, Italy
| | - Elio Mazzone
- Unit of Urology/Division of Oncology, Gianfranco Soldera Prostate Cancer Lab, IRCCS San Raffaele Scientific Institute, Milan, Italy
- Vita-Salute San Raffaele University, Milan, Italy
| | - Paolo Dell'Oglio
- Department of Urology, ASST Grande Ospedale Metropolitano Niguarda, Milan, Italy.
- Department of Urology, Netherlands Cancer Institute-Antoni Van Leeuwenhoek Hospital, Amsterdam, The Netherlands.
- Interventional Molecular Imaging Laboratory, Department of Radiology, Leiden University Medical Center, Leiden, The Netherlands.
| |
Collapse
|
5
|
Li Y, Dai C, Hua Z, Xia L, Ding Y, Wang Q, Gié MLM, Bouvet M, Cai H. A human serum albumin-indocyanine green complex offers improved tumor identification in fluorescence-guided surgery. Transl Cancer Res 2024; 13:437-452. [PMID: 38410209 PMCID: PMC10894326 DOI: 10.21037/tcr-23-2338] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/20/2023] [Accepted: 01/18/2024] [Indexed: 02/28/2024]
Abstract
Background Complete tumor removal is critical for achieving a good prognosis in patients but remains challenging for surgeons. Near-infrared fluorescence-guided surgery (NIRFGS) enables surgeons to accurately localize tumors in real time and facilitates accurate resection. Indocyanine green (ICG) has been approved by the U.S. Food and Drug Administration and the National Medical Products Administration for many years. Although the application of ICG has progressed for a variety of surgeries, there are inherent limitations to ICG, including poor water solubility and photostability, short blood half-life, and aggregation in blood, resulting in poor imaging performance. We found that mixing ICG with human serum albumin (HSA) preoperatively and then injecting it can improve the imaging performance. Methods We prepared fluorescent probes by combining ICG with HSA and identified their optimal ratio via in vitro absorption measurement and emission spectrum characterization of ICG-HSA complex with different mixing ratios and concentration gradients. Subsequently, under the optimal ratio and clinical simulated concentration, we conducted dynamic change analysis of the fluorescence spectral properties after mixing. We then compared the uptake of ICG-HSA in vitro for two different cell types and the imaging performance of different molar ratios of ICG and HSA in mouse models. Results Through in vitro absorption and emission spectrum characterization of ICG-HSA mixtures with different mixing ratios and concentration gradients, the optimal ratio of the mixture was obtained (ICG:HSA =4:5). Using this ratio, clinical simulated concentration, and mixing, we completed the dynamic change analysis of the fluorescence spectrum properties. The results verified that HSA can improve the dispersion and stability of ICG in aqueous solution, reduce the proportion of free-state ICG, and thus improve the biodistribution. Moreover, the fluorescence performance of ICG was improved. ICG-HSA and ICG uptake in MDA-MB-231 cells and imaging in vivo showed that HSA increased the enrichment of ICG in tumor compared to ICG alone (ICG-HSAfluorescence intensity =237.3±10.7 vs. ICGfluorescence intensity =127.1±10.7). Compared with ICG alone, ICG-HSA provided a clearer tumor boundary and higher tumor-to-background ratio (TBR) (ICG-HSATBRmax 3.49±0.56 vs. ICGTBRmax 1.94±0.23). Conclusions This study suggests that ICG-HSA can achieve higher tumor-to-background contrast with shorter time and can provide an overall superior imaging performance compared to ICG alone, thus exhibiting considerable potential for clinical application.
Collapse
Affiliation(s)
- Yunlong Li
- Department of Biomedical Engineering, College of Engineering and Applied Sciences, Nanjing University, Nanjing, China
| | - Chun Dai
- Department of General Surgery, The People’s Hospital of Yangzhong City, Yangzhong, China
| | - Zhaolai Hua
- Department of General Surgery, The People’s Hospital of Yangzhong City, Yangzhong, China
| | - Lin Xia
- Department of General Surgery, The People’s Hospital of Yangzhong City, Yangzhong, China
| | - Yongbin Ding
- Department of General Surgery, Pukou Branch of Jiangsu People’s Hospital, Nanjing, China
| | - Qiang Wang
- School of Life Sciences, Jiangsu University, Zhenjiang, China
| | - Marie-Laure Matthey Gié
- Department of Thoracic and Endocrine Surgery, University Hospital of Geneva (HUG), Geneva, Switzerland
- Department of Surgery, Clinica Moncucco, Lugano, Switzerland
| | - Michael Bouvet
- Department of Surgery, University of California, San Diego, CA, USA
| | - Huiming Cai
- Nanjing Nuoyuan Medical Devices Co., Ltd., Nanjing, China
| |
Collapse
|
6
|
Routkevitch D, Soulé Z, Kats N, Baca E, Hersh AM, Kempski-Leadingham KM, Menta AK, Bhimreddy M, Jiang K, Davidar AD, Smit C, Theodore N, Thakor NV, Manbachi A. Non-contrast ultrasound image analysis for spatial and temporal distribution of blood flow after spinal cord injury. Sci Rep 2024; 14:714. [PMID: 38184676 PMCID: PMC10771432 DOI: 10.1038/s41598-024-51281-7] [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: 09/17/2023] [Accepted: 01/03/2024] [Indexed: 01/08/2024] Open
Abstract
Ultrasound technology can provide high-resolution imaging of blood flow following spinal cord injury (SCI). Blood flow imaging may improve critical care management of SCI, yet its duration is limited clinically by the amount of contrast agent injection required for high-resolution, continuous monitoring. In this study, we aim to establish non-contrast ultrasound as a clinically translatable imaging technique for spinal cord blood flow via comparison to contrast-based methods and by measuring the spatial distribution of blood flow after SCI. A rodent model of contusion SCI at the T12 spinal level was carried out using three different impact forces. We compared images of spinal cord blood flow taken using both non-contrast and contrast-enhanced ultrasound. Subsequently, we processed the images as a function of distance from injury, yielding the distribution of blood flow through space after SCI, and found the following. (1) Both non-contrast and contrast-enhanced imaging methods resulted in similar blood flow distributions (Spearman's ρ = 0.55, p < 0.0001). (2) We found an area of decreased flow at the injury epicenter, or umbra (p < 0.0001). Unexpectedly, we found increased flow at the periphery, or penumbra (rostral, p < 0.05; caudal, p < 0.01), following SCI. However, distal flow remained unchanged, in what is presumably unaffected tissue. (3) Finally, tracking blood flow in the injury zones over time revealed interesting dynamic changes. After an initial decrease, blood flow in the penumbra increased during the first 10 min after injury, while blood flow in the umbra and distal tissue remained constant over time. These results demonstrate the viability of non-contrast ultrasound as a clinical monitoring tool. Furthermore, our surprising observations of increased flow in the injury periphery pose interesting new questions about how the spinal cord vasculature reacts to SCI, with potentially increased significance of the penumbra.
Collapse
Affiliation(s)
- Denis Routkevitch
- Department of Biomedical Engineering, Johns Hopkins University, Baltimore, MD, USA
- Department of Neurosurgery, School of Medicine, Johns Hopkins University, Baltimore, MD, USA
- HEPIUS Innovation Laboratory, School of Medicine, Johns Hopkins University, Baltimore, MD, USA
| | - Zoe Soulé
- Department of Biomedical Engineering, Johns Hopkins University, Baltimore, MD, USA
| | - Nicholas Kats
- Department of Biomedical Engineering, Johns Hopkins University, Baltimore, MD, USA
| | - Emily Baca
- Department of Biomedical Engineering, Johns Hopkins University, Baltimore, MD, USA
| | - Andrew M Hersh
- Department of Neurosurgery, School of Medicine, Johns Hopkins University, Baltimore, MD, USA
- HEPIUS Innovation Laboratory, School of Medicine, Johns Hopkins University, Baltimore, MD, USA
| | - Kelley M Kempski-Leadingham
- Department of Neurosurgery, School of Medicine, Johns Hopkins University, Baltimore, MD, USA
- HEPIUS Innovation Laboratory, School of Medicine, Johns Hopkins University, Baltimore, MD, USA
| | - Arjun K Menta
- Department of Neurosurgery, School of Medicine, Johns Hopkins University, Baltimore, MD, USA
- HEPIUS Innovation Laboratory, School of Medicine, Johns Hopkins University, Baltimore, MD, USA
| | - Meghana Bhimreddy
- Department of Neurosurgery, School of Medicine, Johns Hopkins University, Baltimore, MD, USA
- HEPIUS Innovation Laboratory, School of Medicine, Johns Hopkins University, Baltimore, MD, USA
| | - Kelly Jiang
- Department of Neurosurgery, School of Medicine, Johns Hopkins University, Baltimore, MD, USA
- HEPIUS Innovation Laboratory, School of Medicine, Johns Hopkins University, Baltimore, MD, USA
| | - A Daniel Davidar
- Department of Neurosurgery, School of Medicine, Johns Hopkins University, Baltimore, MD, USA
- HEPIUS Innovation Laboratory, School of Medicine, Johns Hopkins University, Baltimore, MD, USA
| | - Constantin Smit
- HEPIUS Innovation Laboratory, School of Medicine, Johns Hopkins University, Baltimore, MD, USA
| | - Nicholas Theodore
- Department of Neurosurgery, School of Medicine, Johns Hopkins University, Baltimore, MD, USA
- HEPIUS Innovation Laboratory, School of Medicine, Johns Hopkins University, Baltimore, MD, USA
| | - Nitish V Thakor
- Department of Biomedical Engineering, Johns Hopkins University, Baltimore, MD, USA
- HEPIUS Innovation Laboratory, School of Medicine, Johns Hopkins University, Baltimore, MD, USA
- Department of Electrical and Computer Engineering, Johns Hopkins University, Baltimore, MD, USA
| | - Amir Manbachi
- Department of Biomedical Engineering, Johns Hopkins University, Baltimore, MD, USA.
- Department of Neurosurgery, School of Medicine, Johns Hopkins University, Baltimore, MD, USA.
- HEPIUS Innovation Laboratory, School of Medicine, Johns Hopkins University, Baltimore, MD, USA.
- Department of Electrical and Computer Engineering, Johns Hopkins University, Baltimore, MD, USA.
- Department of Mechanical Engineering, Johns Hopkins University, Baltimore, MD, USA.
- Department of Anesthesiology and Critical Care Medicine, School of Medicine, Johns Hopkins University, Baltimore, MD, USA.
| |
Collapse
|
7
|
Wise PA, Studier-Fischer A, Nickel F, Hackert T. [Status Quo of Surgical Navigation]. Zentralbl Chir 2023. [PMID: 38056501 DOI: 10.1055/a-2211-4898] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/08/2023]
Abstract
Surgical navigation, also referred to as computer-assisted or image-guided surgery, is a technique that employs a variety of methods - such as 3D imaging, tracking systems, specialised software, and robotics to support surgeons during surgical interventions. These emerging technologies aim not only to enhance the accuracy and precision of surgical procedures, but also to enable less invasive approaches, with the objective of reducing complications and improving operative outcomes for patients. By harnessing the integration of emerging digital technologies, surgical navigation holds the promise of assisting complex procedures across various medical disciplines. In recent years, the field of surgical navigation has witnessed significant advances. Abdominal surgical navigation, particularly endoscopy, laparoscopic, and robot-assisted surgery, is currently undergoing a phase of rapid evolution. Emphases include image-guided navigation, instrument tracking, and the potential integration of augmented and mixed reality (AR, MR). This article will comprehensively delve into the latest developments in surgical navigation, spanning state-of-the-art intraoperative technologies like hyperspectral and fluorescent imaging, to the integration of preoperative radiological imaging within the intraoperative setting.
Collapse
Affiliation(s)
- Philipp Anthony Wise
- Klinik für Allgemein-, Viszeral- und Transplantationschirurgie, Universitätsklinikum Heidelberg, Heidelberg, Deutschland
| | - Alexander Studier-Fischer
- Klinik für Allgemein-, Viszeral- und Transplantationschirurgie, Universitätsklinikum Heidelberg, Heidelberg, Deutschland
| | - Felix Nickel
- Klinik für Allgemein-, Viszeral- und Thoraxchirurgie, Universitätsklinikum Hamburg-Eppendorf, Hamburg, Deutschland
- Klinik für Allgemein-, Viszeral- und Transplantationschirurgie, Universitätsklinikum Heidelberg, Heidelberg, Deutschland
| | - Thilo Hackert
- Klinik für Allgemein-, Viszeral- und Thoraxchirurgie, Universitätsklinikum Hamburg-Eppendorf, Hamburg, Deutschland
| |
Collapse
|
8
|
Chen L, Liao H, Kong W, Zhang D, Chen F. Anatomy preserving GAN for realistic simulation of intraoperative liver ultrasound images. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2023; 240:107642. [PMID: 37480644 DOI: 10.1016/j.cmpb.2023.107642] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 02/26/2023] [Revised: 05/31/2023] [Accepted: 06/02/2023] [Indexed: 07/24/2023]
Abstract
In ultrasound-guided liver surgery, the lack of large-scale intraoperative ultrasound images with important anatomical structures remains an obstacle hindering the successful application of AI to ultrasound guidance. In this case, intraoperative ultrasound (iUS) simulation should be conducted from preoperative magnetic resonance (pMR), which not only helps doctors understand the characteristics of iUS in advance, but also expands the iUS dataset from various imaging positions, thereby promoting the automatic iUS analysis in ultrasound guidance. Herein, a novel anatomy preserving generative adversarial network (ApGAN) framework was proposed to generate simulated intraoperative ultrasound (Sim-iUS) of liver with precise structure information from pMR. Specifically, the low-rank factors based bimodal fusion was first established focusing on the effective information of hepatic parenchyma. Then, a deformation field based correction module was introduced to learn and correct the slight structural distortion from surgical operations. Meanwhile, the multiple loss functions were designed to constrain the simulation of the content, structures, and style. Empirical results of clinical data showed that the proposed ApGAN obtained higher Structural Similarity (SSIM) of 0.74 and Fr´echet Inception Distance (FID) of 35.54 compared to existing methods. Furthermore, the average Hausdorff Distance (HD) error of the liver capsule structure was less than 0.25 mm, and the average relative (Euclidean Distance) ED error for polyps was 0.12 mm, indicating the high-level precision of this ApGAN in simulating the anatomical structures and focal areas.
Collapse
Affiliation(s)
- Lingyu Chen
- Key Laboratory of Brain-Machine Intelligence Technology, Ministry of Education, Nanjing University of Aeronautics and Astronautics, Nanjing, China; College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, China
| | - Hongen Liao
- Department of Biomedical Engineering, School of Medicine, Tsinghua University, Beijing, China
| | - Wentao Kong
- Department of Ultrasound, Affiliated DrumTower Hospital, Medical School of Nanjing University, Nanjing 210008, China.
| | - Daoqiang Zhang
- Key Laboratory of Brain-Machine Intelligence Technology, Ministry of Education, Nanjing University of Aeronautics and Astronautics, Nanjing, China; College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, China
| | - Fang Chen
- Key Laboratory of Brain-Machine Intelligence Technology, Ministry of Education, Nanjing University of Aeronautics and Astronautics, Nanjing, China; College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, China.
| |
Collapse
|
9
|
Li C, Mi J, Wang Y, Zhang Z, Guo X, Zhou J, Hu Z, Tian J. New and effective EGFR-targeted fluorescence imaging technology for intraoperative rapid determination of lung cancer in freshly isolated tissue. Eur J Nucl Med Mol Imaging 2023; 50:494-507. [PMID: 36207638 DOI: 10.1007/s00259-022-05975-7] [Citation(s) in RCA: 6] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/10/2022] [Accepted: 09/15/2022] [Indexed: 01/11/2023]
Abstract
PURPOSE During lung cancer surgery, it is very important to define tumor boundaries and determine the surgical margin distance. In previous research, systemically application of fluorescent probes can help medical professionals determine the boundaries of tumors and find small tumors and metastases, thereby improving the accuracy of surgical resection. However, there are very few safe and effective probes that can be applied to clinical trials up to now, which limits the clinical application of fluorescence imaging. Here we developed a new technology that can quickly identify the tumor area in the resected lung tissue during the operation and distinguish the tumor boundary and metastatic lymph nodes. EXPERIMENTAL DESIGN For animal studies, a PDX model of lung cancer was established. The tumors, lungs, and peritumoral muscle tissues of tumor-bearing mice were surgically removed and incubated with a probe targeting epidermal growth factor receptor (EGFR) for 20 min, and then imaged by a closed-field near-infrared two-zone (NIR-II) fluorescence imaging system. For clinical samples, ten surgically removed lung tissues and 60 lymph nodes from 10 lung cancer patients undergoing radical resection were incubated with the targeting probe immediately after intraoperative resection and imaged to identify the tumor area and distinguish the tumor boundary and metastatic lymph nodes. The accuracy of fluorescence imaging was confirmed by HE staining and immunohistochemistry. RESULTS The ex vivo animal imaging experiments showed a fluorescence enhancement of tumor tissue. For clinical samples, our results showed that this new technology yielded more than 85.7% sensitivity and 100% specificity in identifying the tumor area in the resected lung tissue. The average fluorescence tumor-to-background ratio was 2.5 ± 1.3. Furthermore, we also used this technique to image metastatic lymph nodes intraoperatively and showed that metastatic lymph nodes have brighter fluorescence than normal lymph nodes, as the average fluorescence tumor-to-background signal ratio was 2.7 ± 1.1. Calculations on the results of the fluorescence signal in relation to the number of metastatic lymph nodes yielded values of 77.8% for sensitivity and 92.1% for specificity. We expect this new technology to be a useful diagnostic tool for rapid intraoperative pathological detection and margin determination. CONCLUSIONS By using fluorescently labeled anti-human EGFR recombinant antibody scFv fragment to incubate freshly isolated tissues during surgery, the probes can quickly accumulate in lung cancer tissues, which can be used to quickly identify tumor areas in the resected lung tissues and distinguish tumor boundaries and find metastases in lymph nodes. This technology is expected to be used for rapid intraoperative pathological detection and margin determination.
Collapse
Affiliation(s)
- Changjian Li
- School of Engineering Medicine, Beihang University, Beijing, 100191, People's Republic of China
- Key Laboratory of Big Data-Based Precision Medicine (Beihang University), Ministry of Industry and Information Technology, Beijing, 100191, People's Republic of China
| | - Jiahui Mi
- Department of Thoracic Surgery, Peking University People's Hospital, No.11, Xi Zhi Men South Avenue, Beijing, 100190, People's Republic of China
| | - Yueqi Wang
- CAS Key Laboratory of Molecular Imaging, Beijing Key Laboratory of Molecular Imaging, The State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, People's Republic of China
| | - Zeyu Zhang
- School of Engineering Medicine, Beihang University, Beijing, 100191, People's Republic of China
- Key Laboratory of Big Data-Based Precision Medicine (Beihang University), Ministry of Industry and Information Technology, Beijing, 100191, People's Republic of China
| | - Xiaoyong Guo
- CAS Key Laboratory of Molecular Imaging, Beijing Key Laboratory of Molecular Imaging, The State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, People's Republic of China
- Department of Gastroenterology, The Third Medical Centre, Chinese PLA General Hospital, Beijing, 100190, People's Republic of China
| | - Jian Zhou
- Department of Thoracic Surgery, Peking University People's Hospital, No.11, Xi Zhi Men South Avenue, Beijing, 100190, People's Republic of China.
| | - Zhenhua Hu
- CAS Key Laboratory of Molecular Imaging, Beijing Key Laboratory of Molecular Imaging, The State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, People's Republic of China.
| | - Jie Tian
- School of Engineering Medicine, Beihang University, Beijing, 100191, People's Republic of China.
- Key Laboratory of Big Data-Based Precision Medicine (Beihang University), Ministry of Industry and Information Technology, Beijing, 100191, People's Republic of China.
- CAS Key Laboratory of Molecular Imaging, Beijing Key Laboratory of Molecular Imaging, The State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, People's Republic of China.
- Zhuhai Precision Medical Center, Zhuhai People's Hospital, Affiliated With Jinan University, Zhuhai, 519000, People's Republic of China.
| |
Collapse
|
10
|
Giammalva GR, Viola A, Maugeri R, Giardina K, Di Bonaventura R, Musso S, Brunasso L, Cepeda S, Della Pepa GM, Scerrati A, Mantovani G, Ferini G, Gerardi RM, Pino MA, Umana GE, Denaro L, Albanese A, Iacopino DG. Intraoperative Evaluation of Brain-Tumor Microvascularization through MicroV IOUS: A Protocol for Image Acquisition and Analysis of Radiomic Features. Cancers (Basel) 2022; 14:5335. [PMID: 36358754 PMCID: PMC9656308 DOI: 10.3390/cancers14215335] [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: 08/25/2022] [Revised: 10/25/2022] [Accepted: 10/27/2022] [Indexed: 08/09/2023] Open
Abstract
Microvascular Doppler (MicroV) is a new-generation Doppler technique developed by Esaote (Esaote s.p.a., Genova, Italy), which is able to visualize small and low-flow vessels through a suppression of interfering signals. MicroV uses advanced filters that are able to differentiate tissue artifacts from low-speed blood flows; by exploiting the space-time coherence information, these filters can selectively suppress tissue components, preserving the signal coming from the microvascular flow. This technique is clinically applied to the study of the vascularization of parenchymatous lesions, often with better diagnostic accuracy than color/power Doppler techniques. The aim of this paper is to develop a reproducible protocol for the recording and collection of MicroV intraoperative ultrasound images by the use of a capable intraoperative ultrasound machine and post-processing aimed at evaluation of brain-tumor microvascularization through the analysis of radiomic features. The proposed protocol has been internally validated on eight patients and will be firstly applied to patients affected by WHO grade IV astrocytoma (glioblastoma-GBM) candidates for craniotomy and lesion removal. In a further stage, it will be generally applied to patients with primary or metastatic brain tumors. IOUS is performed before durotomy. Tumor microvascularization is evaluated using the MicroV Doppler technique and IOUS images are recorded, stored, and post-processed. IOUS images are remotely stored on the BraTIoUS database, which will promote international cooperation and multicentric analysis. Processed images and texture radiomic features are analyzed post-operatively using ImageJ, a free scientific image-analysis software based on the Sun-Java platform. Post-processing protocol is further described in-depth. The study of tumor microvascularization through advanced IOUS techniques such as MicroV could represent, in the future, a non-invasive and real-time method for intraoperative predictive evaluation of the tumor features. This evaluation could finally result in a deeper knowledge of brain-tumor behavior and in the on-going adaptation of the surgery with the improvement of surgical outcomes.
Collapse
Affiliation(s)
- Giuseppe Roberto Giammalva
- Neurosurgical Clinic, Post Graduate Residency Program in Neurologic Surgery, Department of Biomedicine Neurosciences and Advanced Diagnostics, School of Medicine, University of Palermo, 90127 Palermo, Italy
| | - Anna Viola
- Department of Radiation Oncology, REM Radioterapia srl, 95029 Viagrande, Italy
| | - Rosario Maugeri
- Neurosurgical Clinic, Post Graduate Residency Program in Neurologic Surgery, Department of Biomedicine Neurosciences and Advanced Diagnostics, School of Medicine, University of Palermo, 90127 Palermo, Italy
| | - Kevin Giardina
- Neurosurgical Clinic, Post Graduate Residency Program in Neurologic Surgery, Department of Biomedicine Neurosciences and Advanced Diagnostics, School of Medicine, University of Palermo, 90127 Palermo, Italy
| | - Rina Di Bonaventura
- Department of Neurosurgery, Fondazione Policlinico Universitario A. Gemelli IRCCS, Università Cattolica del Sacro Cuore, 00100 Rome, Italy
| | - Sofia Musso
- Neurosurgical Clinic, Post Graduate Residency Program in Neurologic Surgery, Department of Biomedicine Neurosciences and Advanced Diagnostics, School of Medicine, University of Palermo, 90127 Palermo, Italy
| | - Lara Brunasso
- Neurosurgical Clinic, Post Graduate Residency Program in Neurologic Surgery, Department of Biomedicine Neurosciences and Advanced Diagnostics, School of Medicine, University of Palermo, 90127 Palermo, Italy
| | - Santiago Cepeda
- Departamento de Neurocirugía, Hospital Universitario Río Hortega, 47012 Valladolid, Spain
| | - Giuseppe Maria Della Pepa
- Department of Neurosurgery, Fondazione Policlinico Universitario A. Gemelli IRCCS, Università Cattolica del Sacro Cuore, 00100 Rome, Italy
| | - Alba Scerrati
- Department of Translational Medicine, University of Ferrara, 44121 Ferrara, Italy
- Department of Neurosurgery, Sant’Anna University Hospital of Ferrara, 44124 Ferrara, Italy
| | - Giorgio Mantovani
- Department of Translational Medicine, University of Ferrara, 44121 Ferrara, Italy
- Department of Neurosurgery, Sant’Anna University Hospital of Ferrara, 44124 Ferrara, Italy
| | - Gianluca Ferini
- Department of Radiation Oncology, REM Radioterapia srl, 95029 Viagrande, Italy
| | - Rosa Maria Gerardi
- Neurosurgical Clinic, Post Graduate Residency Program in Neurologic Surgery, Department of Biomedicine Neurosciences and Advanced Diagnostics, School of Medicine, University of Palermo, 90127 Palermo, Italy
| | - Maria Angela Pino
- Neurosurgical Clinic, Post Graduate Residency Program in Neurologic Surgery, Department of Biomedicine Neurosciences and Advanced Diagnostics, School of Medicine, University of Palermo, 90127 Palermo, Italy
| | - Giuseppe Emmanuele Umana
- Trauma Center, Gamma Knife Center, Department of Neurosurgery, Cannizzaro Hospital, 95126 Catania, Italy
| | - Luca Denaro
- Academic Neurosurgery, Department of Neurosciences DNS, University of Padua, 35128 Padua, Italy
| | - Alessio Albanese
- Department of Neurosurgery, Fondazione Policlinico Universitario A. Gemelli IRCCS, Università Cattolica del Sacro Cuore, 00100 Rome, Italy
| | - Domenico Gerardo Iacopino
- Neurosurgical Clinic, Post Graduate Residency Program in Neurologic Surgery, Department of Biomedicine Neurosciences and Advanced Diagnostics, School of Medicine, University of Palermo, 90127 Palermo, Italy
| |
Collapse
|
11
|
Barash Y, Klang E, Lux A, Konen E, Horesh N, Pery R, Zilka N, Eshkenazy R, Nachmany I, Pencovich N. Artificial intelligence for identification of focal lesions in intraoperative liver ultrasonography. Langenbecks Arch Surg 2022; 407:3553-3560. [PMID: 36068378 DOI: 10.1007/s00423-022-02674-7] [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: 05/15/2022] [Accepted: 09/02/2022] [Indexed: 11/28/2022]
Abstract
PURPOSE Intraoperative ultrasonography (IOUS) of the liver is a crucial adjunct in every liver resection and may significantly impact intraoperative surgical decisions. However, IOUS is highly operator dependent and has a steep learning curve. We describe the design and assessment of an artificial intelligence (AI) system to identify focal liver lesions in IOUS. METHODS IOUS images were collected during liver resections performed between November 2020 and November 2021. The images were labeled by radiologists and surgeons as normal liver tissue versus images that contain liver lesions. A convolutional neural network (CNN) was trained and tested to classify images based on the labeling. Algorithm performance was tested in terms of area under the curves (AUCs), accuracy, sensitivity, specificity, F1 score, positive predictive value, and negative predictive value. RESULTS Overall, the dataset included 5043 IOUS images from 16 patients. Of these, 2576 were labeled as normal liver tissue and 2467 as containing focal liver lesions. Training and testing image sets were taken from different patients. Network performance area under the curve (AUC) was 80.2 ± 2.9%, and the overall classification accuracy was 74.6% ± 3.1%. For maximal sensitivity of 99%, the classification specificity is 36.4 ± 9.4%. CONCLUSIONS This study provides for the first time a proof of concept for the use of AI in IOUS and show that high accuracy can be achieved. Further studies using high volume data are warranted to increase accuracy and differentiate between lesion types.
Collapse
Affiliation(s)
- Yiftach Barash
- Department of Radiology, Sheba Medical Center, Tel-Hashomer, Faculty of Medicine, Tel-Aviv University, Tel-Aviv, Israel
| | - Eyal Klang
- Department of Radiology, Sheba Medical Center, Tel-Hashomer, Faculty of Medicine, Tel-Aviv University, Tel-Aviv, Israel
| | - Adar Lux
- Department of Radiology, Sheba Medical Center, Tel-Hashomer, Faculty of Medicine, Tel-Aviv University, Tel-Aviv, Israel
| | - Eli Konen
- Department of Radiology, Sheba Medical Center, Tel-Hashomer, Faculty of Medicine, Tel-Aviv University, Tel-Aviv, Israel
| | - Nir Horesh
- Department of General Surgery and Transplantation, Sheba Medical Center, Tel-Hashomer, Faculty of Medicine, Tel-Aviv University, Tel-Aviv, Israel
| | - Ron Pery
- Department of General Surgery and Transplantation, Sheba Medical Center, Tel-Hashomer, Faculty of Medicine, Tel-Aviv University, Tel-Aviv, Israel
| | - Nadav Zilka
- Department of General Surgery and Transplantation, Sheba Medical Center, Tel-Hashomer, Faculty of Medicine, Tel-Aviv University, Tel-Aviv, Israel
| | - Rony Eshkenazy
- Department of General Surgery and Transplantation, Sheba Medical Center, Tel-Hashomer, Faculty of Medicine, Tel-Aviv University, Tel-Aviv, Israel
| | - Ido Nachmany
- Department of General Surgery and Transplantation, Sheba Medical Center, Tel-Hashomer, Faculty of Medicine, Tel-Aviv University, Tel-Aviv, Israel
| | - Niv Pencovich
- Department of General Surgery and Transplantation, Sheba Medical Center, Tel-Hashomer, Faculty of Medicine, Tel-Aviv University, Tel-Aviv, Israel.
| |
Collapse
|
12
|
Kasaven LS, Jones BP, Ghaem-Maghami S, Verbakel JYJ, El-Bahrawy M, Saso S, Yazbek J. Study protocol for a randomised controlled trial on the use of intraoperative ultrasound-guided laparoscopic ovarian cystectomy (UGLOC) as a method of fertility preservation in the management of benign ovarian cysts. BMJ Open 2022; 12:e060409. [PMID: 35835531 PMCID: PMC9289018 DOI: 10.1136/bmjopen-2021-060409] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 11/08/2022] Open
Abstract
INTRODUCTION The lifetime risk of women undergoing surgery for the presence of benign ovarian pathology in the UK is 5%-10%. Despite minimally invasive surgical techniques, evidence suggests a number of healthy ovarian follicles and tissues are resected intraoperatively, resulting in subsequent decline of ovarian reserve. As such, there is an increasing demand for the implementation of fertility preservation surgery (FPS). This study will evaluate the effect on ovarian reserve following two different surgical interventions for the management of benign ovarian cysts. METHODS AND ANALYSIS We will conduct a two-armed randomised controlled trial comparing laparoscopic ovarian cystectomy, considered gold standard treatment as per the Royal College of Obstetricians and Gynaecologists (RCOG) Green Top guidelines for the management of benign ovarian cysts, with ultrasound-guided laparoscopic ovarian cystectomy (UGLOC), a novel method of FPS. The study commencement date was October 2021, with a completion date aimed for October 2024. The primary outcome will be the difference in anti-Müllerian hormone (AMH) (pmol/L) and antral follicle count (AFC) measured 3 and 6 months postoperatively from the preoperative baseline. Secondary outcomes include assessment of various surgical and histopathological findings, including duration of hospital stay (days), duration of surgery (minutes), presence of intraoperative cyst rupture (yes/no), presence of ovarian tissue within the resected specimen (yes/no) and the grade of follicles excised within the specimen (grade 0-4). We aim to randomise 94 patients over 3 years to achieve power of 80% at an alpha level of 0.05. ETHICS AND DISSEMINATION Findings will be published in peer-reviewed journals and presented at national and international conferences and scientific meetings. The Chelsea NHS Research and Ethics Committee have awarded ethical approval of the study (21/LO/036). TRIAL REGISTRATION NUMBER NCT05032846.
Collapse
Affiliation(s)
- Lorraine S Kasaven
- Department of Cancer and Surgery, Imperial College London, London, UK
- Cutrale Perioperative and Ageing Group, Imperial College London, London, UK
- West London Gynaecological Cancer Centre, Imperial College NHS Trust, London, UK
| | - Benjamin P Jones
- Department of Cancer and Surgery, Imperial College London, London, UK
- West London Gynaecological Cancer Centre, Imperial College NHS Trust, London, UK
| | - Sadaf Ghaem-Maghami
- Department of Cancer and Surgery, Imperial College London, London, UK
- West London Gynaecological Cancer Centre, Imperial College NHS Trust, London, UK
| | | | - Mona El-Bahrawy
- Department of Metabolism, Digestion and Reproduction, Imperial College Healthcare NHS Trust, London, UK
| | - Srdjan Saso
- Department of Cancer and Surgery, Imperial College London, London, UK
- West London Gynaecological Cancer Centre, Imperial College NHS Trust, London, UK
| | - Joseph Yazbek
- Department of Cancer and Surgery, Imperial College London, London, UK
- West London Gynaecological Cancer Centre, Imperial College NHS Trust, London, UK
| |
Collapse
|
13
|
Dai X, Lei Y, Wang T, Axente M, Xu D, Patel P, Jani AB, Curran WJ, Liu T, Yang X. Self-supervised learning for accelerated 3D high-resolution ultrasound imaging. Med Phys 2021; 48:3916-3926. [PMID: 33993508 DOI: 10.1002/mp.14946] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/27/2020] [Revised: 05/03/2021] [Accepted: 05/10/2021] [Indexed: 12/23/2022] Open
Abstract
PURPOSE Ultrasound (US) imaging has been widely used in diagnosis, image-guided intervention, and therapy, where high-quality three-dimensional (3D) images are highly desired from sparsely acquired two-dimensional (2D) images. This study aims to develop a deep learning-based algorithm to reconstruct high-resolution (HR) 3D US images only reliant on the acquired sparsely distributed 2D images. METHODS We propose a self-supervised learning framework using cycle-consistent generative adversarial network (cycleGAN), where two independent cycleGAN models are trained with paired original US images and two sets of low-resolution (LR) US images, respectively. The two sets of LR US images are obtained through down-sampling the original US images along the two axes, respectively. In US imaging, in-plane spatial resolution is generally much higher than through-plane resolution. By learning the mapping from down-sampled in-plane LR images to original HR US images, cycleGAN can generate through-plane HR images from original sparely distributed 2D images. Finally, HR 3D US images are reconstructed by combining the generated 2D images from the two cycleGAN models. RESULTS The proposed method was assessed on two different datasets. One is automatic breast ultrasound (ABUS) images from 70 breast cancer patients, the other is collected from 45 prostate cancer patients. By applying a spatial resolution enhancement factor of 3 to the breast cases, our proposed method achieved the mean absolute error (MAE) value of 0.90 ± 0.15, the peak signal-to-noise ratio (PSNR) value of 37.88 ± 0.88 dB, and the visual information fidelity (VIF) value of 0.69 ± 0.01, which significantly outperforms bicubic interpolation. Similar performances have been achieved using the enhancement factor of 5 in these breast cases and using the enhancement factors of 5 and 10 in the prostate cases. CONCLUSIONS We have proposed and investigated a new deep learning-based algorithm for reconstructing HR 3D US images from sparely acquired 2D images. Significant improvement on through-plane resolution has been achieved by only using the acquired 2D images without any external atlas images. Its self-supervision capability could accelerate HR US imaging.
Collapse
Affiliation(s)
- Xianjin Dai
- Department of Radiation Oncology and Winship Cancer Institute, Emory University, Atlanta, GA, 30322, USA
| | - Yang Lei
- Department of Radiation Oncology and Winship Cancer Institute, Emory University, Atlanta, GA, 30322, USA
| | - Tonghe Wang
- Department of Radiation Oncology and Winship Cancer Institute, Emory University, Atlanta, GA, 30322, USA
| | - Marian Axente
- Department of Radiation Oncology and Winship Cancer Institute, Emory University, Atlanta, GA, 30322, USA
| | - Dong Xu
- Department of Radiation Oncology and Winship Cancer Institute, Emory University, Atlanta, GA, 30322, USA
| | - Pretesh Patel
- Department of Radiation Oncology and Winship Cancer Institute, Emory University, Atlanta, GA, 30322, USA
| | - Ashesh B Jani
- Department of Radiation Oncology and Winship Cancer Institute, Emory University, Atlanta, GA, 30322, USA
| | - Walter J Curran
- Department of Radiation Oncology and Winship Cancer Institute, Emory University, Atlanta, GA, 30322, USA
| | - Tian Liu
- Department of Radiation Oncology and Winship Cancer Institute, Emory University, Atlanta, GA, 30322, USA
| | - Xiaofeng Yang
- Department of Radiation Oncology and Winship Cancer Institute, Emory University, Atlanta, GA, 30322, USA
| |
Collapse
|