1
|
Zhang H, Zhang B, Lasio G, Chen S, Nasehi Tehrani J. Assessing quality assurance of multi-leaf collimator using the structural similarity index. J Appl Clin Med Phys 2024; 25:e14288. [PMID: 38345201 PMCID: PMC11005984 DOI: 10.1002/acm2.14288] [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: 07/31/2023] [Revised: 12/11/2023] [Accepted: 01/22/2024] [Indexed: 04/11/2024] Open
Abstract
PURPOSE This study aims to evaluate the viability of utilizing the Structural Similarity Index (SSI*) as an innovative imaging metric for quality assurance (QA) of the multi-leaf collimator (MLC). Additionally, we compared the results obtained through SSI* with those derived from a conventional Gamma index test for three types of Varian machines (Trilogy, Truebeam, and Edge) over a 12-week period of MLC QA in our clinic. METHOD To assess sensitivity to MLC positioning errors, we designed a 1 cm slit on the reference MLC, subsequently shifted by 0.5-5 mm on the target MLC. For evaluating sensitivity to output error, we irradiated five 25 cm × 25 cm open fields on the portal image with varying Monitor Units (MUs) of 96-100. We compared SSI* and Gamma index tests using three linear accelerator (LINAC) machines: Varian Trilogy, Truebeam, and Edge, with MLC leaf widths of 1, 0.5, and 0.25 mm. Weekly QA included VMAT and static field modes, with Picket fence test images acquired. Mechanical uncertainties related to the LINAC head, electronic portal imaging device (EPID), and MLC during gantry rotation and leaf motion were monitored. RESULTS The Gamma index test started detecting the MLC shift at a threshold of 4 mm, whereas the SSI* metric showed sensitivity to shifts as small as 2 mm. Moreover, the Gamma index test identified dose changes at 95MUs, indicating a 5% dose difference based on the distance to agreement (DTA)/dose difference (DD) criteria of 1 mm/3%. In contrast, the SSI* metric alerted to dose differences starting from 97MUs, corresponding to a 3% dose difference. The Gamma index test passed all measurements conducted on each machine. However, the SSI* metric rejected all measurements from the Edge and Trilogy machines and two from the Truebeam. CONCLUSIONS Our findings demonstrate that the SSI* exhibits greater sensitivity than the Gamma index test in detecting MLC positioning errors and dose changes between static and VMAT modes. The SSI* metric outperformed the Gamma index test regarding sensitivity across these parameters.
Collapse
Affiliation(s)
- Hong Zhang
- Departments of Radiation OncologyVanderbilt University Medical CenterNashvilleTennesseeUSA
| | - Baoshe Zhang
- Departments of Radiation OncologyMedical SchoolUniversity of MarylandBaltimoreMarylandUSA
| | - Giovanni Lasio
- Departments of Radiation OncologyMedical SchoolUniversity of MarylandBaltimoreMarylandUSA
| | - Shifeng Chen
- Departments of Radiation OncologyMedical SchoolUniversity of MarylandBaltimoreMarylandUSA
| | - Joubin Nasehi Tehrani
- Departments of Radiation OncologyMedical SchoolUniversity of MarylandBaltimoreMarylandUSA
| |
Collapse
|
2
|
Kulkarni C, Sherkhane U, Jaiswar V, Mithun S, Mysore Siddu D, Rangarajan V, Dekker A, Traverso A, Jha A, Wee L. Comparing the performance of a deep learning-based lung gross tumour volume segmentation algorithm before and after transfer learning in a new hospital. BJR Open 2024; 6:tzad008. [PMID: 38352184 PMCID: PMC10860512 DOI: 10.1093/bjro/tzad008] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/06/2023] [Revised: 09/15/2023] [Accepted: 11/20/2023] [Indexed: 02/16/2024] Open
Abstract
Objectives Radiation therapy for lung cancer requires a gross tumour volume (GTV) to be carefully outlined by a skilled radiation oncologist (RO) to accurately pinpoint high radiation dose to a malignant mass while simultaneously minimizing radiation damage to adjacent normal tissues. This is manually intensive and tedious however, it is feasible to train a deep learning (DL) neural network that could assist ROs to delineate the GTV. However, DL trained on large openly accessible data sets might not perform well when applied to a superficially similar task but in a different clinical setting. In this work, we tested the performance of DL automatic lung GTV segmentation model trained on open-access Dutch data when used on Indian patients from a large public tertiary hospital, and hypothesized that generic DL performance could be improved for a specific local clinical context, by means of modest transfer-learning on a small representative local subset. Methods X-ray computed tomography (CT) series in a public data set called "NSCLC-Radiomics" from The Cancer Imaging Archive was first used to train a DL-based lung GTV segmentation model (Model 1). Its performance was assessed using a different open access data set (Interobserver1) of Dutch subjects plus a private Indian data set from a local tertiary hospital (Test Set 2). Another Indian data set (Retrain Set 1) was used to fine-tune the former DL model using a transfer learning method. The Indian data sets were taken from CT of a hybrid scanner based in nuclear medicine, but the GTV was drawn by skilled Indian ROs. The final (after fine-tuning) model (Model 2) was then re-evaluated in "Interobserver1" and "Test Set 2." Dice similarity coefficient (DSC), precision, and recall were used as geometric segmentation performance metrics. Results Model 1 trained exclusively on Dutch scans showed a significant fall in performance when tested on "Test Set 2." However, the DSC of Model 2 recovered by 14 percentage points when evaluated in the same test set. Precision and recall showed a similar rebound of performance after transfer learning, in spite of using a comparatively small sample size. The performance of both models, before and after the fine-tuning, did not significantly change the segmentation performance in "Interobserver1." Conclusions A large public open-access data set was used to train a generic DL model for lung GTV segmentation, but this did not perform well initially in the Indian clinical context. Using transfer learning methods, it was feasible to efficiently and easily fine-tune the generic model using only a small number of local examples from the Indian hospital. This led to a recovery of some of the geometric segmentation performance, but the tuning did not appear to affect the performance of the model in another open-access data set. Advances in knowledge Caution is needed when using models trained on large volumes of international data in a local clinical setting, even when that training data set is of good quality. Minor differences in scan acquisition and clinician delineation preferences may result in an apparent drop in performance. However, DL models have the advantage of being efficiently "adapted" from a generic to a locally specific context, with only a small amount of fine-tuning by means of transfer learning on a small local institutional data set.
Collapse
Affiliation(s)
- Chaitanya Kulkarni
- Philips Research, Philips Innovation Campus, Bengaluru, Karnataka 560045, India
- Department of Radiation Oncology (Maastro), GROW School for Oncology and Reproduction, Maastricht University Medical Centre+, Maastricht 6229 ET, The Netherlands
| | - Umesh Sherkhane
- Department of Radiation Oncology (Maastro), GROW School for Oncology and Reproduction, Maastricht University Medical Centre+, Maastricht 6229 ET, The Netherlands
- Department of Nuclear Medicine and Radiology, Tata Memorial Hospital Mumbai, Mumbai, Maharashtra 400012, India
| | - Vinay Jaiswar
- Department of Nuclear Medicine and Radiology, Tata Memorial Hospital Mumbai, Mumbai, Maharashtra 400012, India
| | - Sneha Mithun
- Department of Radiation Oncology (Maastro), GROW School for Oncology and Reproduction, Maastricht University Medical Centre+, Maastricht 6229 ET, The Netherlands
- Department of Nuclear Medicine and Radiology, Tata Memorial Hospital Mumbai, Mumbai, Maharashtra 400012, India
| | - Dinesh Mysore Siddu
- Philips Research, Philips Innovation Campus, Bengaluru, Karnataka 560045, India
| | - Venkatesh Rangarajan
- Department of Nuclear Medicine and Radiology, Tata Memorial Hospital Mumbai, Mumbai, Maharashtra 400012, India
| | - Andre Dekker
- Department of Radiation Oncology (Maastro), GROW School for Oncology and Reproduction, Maastricht University Medical Centre+, Maastricht 6229 ET, The Netherlands
| | - Alberto Traverso
- Department of Radiation Oncology (Maastro), GROW School for Oncology and Reproduction, Maastricht University Medical Centre+, Maastricht 6229 ET, The Netherlands
- Faculty of Medicine, University Vita Salute, San Raffaele Hospital, 20132 Milan, Italy
| | - Ashish Jha
- Department of Nuclear Medicine and Radiology, Tata Memorial Hospital Mumbai, Mumbai, Maharashtra 400012, India
| | - Leonard Wee
- Department of Radiation Oncology (Maastro), GROW School for Oncology and Reproduction, Maastricht University Medical Centre+, Maastricht 6229 ET, The Netherlands
| |
Collapse
|
3
|
Yimit Y, Yasin P, Tuersun A, Abulizi A, Jia W, Wang Y, Nijiati M. Differentiation between cerebral alveolar echinococcosis and brain metastases with radiomics combined machine learning approach. Eur J Med Res 2023; 28:577. [PMID: 38071384 PMCID: PMC10709961 DOI: 10.1186/s40001-023-01550-4] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/28/2023] [Accepted: 11/23/2023] [Indexed: 12/18/2023] Open
Abstract
BACKGROUND Cerebral alveolar echinococcosis (CAE) and brain metastases (BM) share similar in locations and imaging appearance. However, they require distinct treatment approaches, with CAE typically treated with chemotherapy and surgery, while BM is managed with radiotherapy and targeted therapy for the primary malignancy. Accurate diagnosis is crucial due to the divergent treatment strategies. PURPOSE This study aims to evaluate the effectiveness of radiomics and machine learning techniques based on magnetic resonance imaging (MRI) to differentiate between CAE and BM. METHODS We retrospectively analyzed MRI images of 130 patients (30 CAE and 100 BM) from Xinjiang Medical University First Affiliated Hospital and The First People's Hospital of Kashi Prefecture, between January 2014 and December 2022. The dataset was divided into training (91 cases) and testing (39 cases) sets. Three dimensional tumors were segmented by radiologists from contrast-enhanced T1WI images on open resources software 3D Slicer. Features were extracted on Pyradiomics, further feature reduction was carried out using univariate analysis, correlation analysis, and least absolute shrinkage and selection operator (LASSO). Finally, we built five machine learning models, support vector machine, logistic regression, linear discrimination analysis, k-nearest neighbors classifier, and Gaussian naïve bias and evaluated their performance via several metrics including sensitivity (recall), specificity, positive predictive value (precision), negative predictive value, accuracy and the area under the curve (AUC). RESULTS The area under curve (AUC) of support vector classifier (SVC), linear discrimination analysis (LDA), k-nearest neighbors (KNN), and gaussian naïve bias (NB) algorithms in training (testing) sets are 0.99 (0.94), 1.00 (0.87), 0.98 (0.92), 0.97 (0.97), and 0.98 (0.93), respectively. Nested cross-validation demonstrated the robustness and generalizability of the models. Additionally, the calibration plot and decision curve analysis demonstrated the practical usefulness of these models in clinical practice, with lower bias toward different subgroups during decision-making. CONCLUSION The combination of radiomics and machine learning approach based on contrast enhanced T1WI images could well distinguish CAE and BM. This approach holds promise in assisting doctors with accurate diagnosis and clinical decision-making.
Collapse
Affiliation(s)
- Yasen Yimit
- Medical Imaging Center, The First People's Hospital of Kashi (Kashgar) Prefecture, Kashi, 844000, People's Republic of China
| | - Parhat Yasin
- Department of Spine Surgery, The First Affiliated Hospital of Xinjiang Medical University, Urumqi, 830054, Xinjiang, China
| | - Abuduresuli Tuersun
- Medical Imaging Center, The First People's Hospital of Kashi (Kashgar) Prefecture, Kashi, 844000, People's Republic of China
| | - Abudoukeyoumujiang Abulizi
- Medical Imaging Center, The First People's Hospital of Kashi (Kashgar) Prefecture, Kashi, 844000, People's Republic of China
| | - Wenxiao Jia
- Medical Imaging Center, Xinjiang Medical University Affiliated First Hospital, Urumqi, 830054, People's Republic of China
| | - Yunling Wang
- Medical Imaging Center, Xinjiang Medical University Affiliated First Hospital, Urumqi, 830054, People's Republic of China
| | - Mayidili Nijiati
- Medical Imaging Center, The First People's Hospital of Kashi (Kashgar) Prefecture, Kashi, 844000, People's Republic of China.
| |
Collapse
|
4
|
Inau ET, Sack J, Waltemath D, Zeleke AA. Initiatives, Concepts, and Implementation Practices of the Findable, Accessible, Interoperable, and Reusable Data Principles in Health Data Stewardship: Scoping Review. J Med Internet Res 2023; 25:e45013. [PMID: 37639292 PMCID: PMC10495848 DOI: 10.2196/45013] [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: 12/13/2022] [Revised: 03/25/2023] [Accepted: 04/14/2023] [Indexed: 08/29/2023] Open
Abstract
BACKGROUND Thorough data stewardship is a key enabler of comprehensive health research. Processes such as data collection, storage, access, sharing, and analytics require researchers to follow elaborate data management strategies properly and consistently. Studies have shown that findable, accessible, interoperable, and reusable (FAIR) data leads to improved data sharing in different scientific domains. OBJECTIVE This scoping review identifies and discusses concepts, approaches, implementation experiences, and lessons learned in FAIR initiatives in health research data. METHODS The Arksey and O'Malley stage-based methodological framework for scoping reviews was applied. PubMed, Web of Science, and Google Scholar were searched to access relevant publications. Articles written in English, published between 2014 and 2020, and addressing FAIR concepts or practices in the health domain were included. The 3 data sources were deduplicated using a reference management software. In total, 2 independent authors reviewed the eligibility of each article based on defined inclusion and exclusion criteria. A charting tool was used to extract information from the full-text papers. The results were reported using the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) guidelines. RESULTS A total of 2.18% (34/1561) of the screened articles were included in the final review. The authors reported FAIRification approaches, which include interpolation, inclusion of comprehensive data dictionaries, repository design, semantic interoperability, ontologies, data quality, linked data, and requirement gathering for FAIRification tools. Challenges and mitigation strategies associated with FAIRification, such as high setup costs, data politics, technical and administrative issues, privacy concerns, and difficulties encountered in sharing health data despite its sensitive nature were also reported. We found various workflows, tools, and infrastructures designed by different groups worldwide to facilitate the FAIRification of health research data. We also uncovered a wide range of problems and questions that researchers are trying to address by using the different workflows, tools, and infrastructures. Although the concept of FAIR data stewardship in the health research domain is relatively new, almost all continents have been reached by at least one network trying to achieve health data FAIRness. Documented outcomes of FAIRification efforts include peer-reviewed publications, improved data sharing, facilitated data reuse, return on investment, and new treatments. Successful FAIRification of data has informed the management and prognosis of various diseases such as cancer, cardiovascular diseases, and neurological diseases. Efforts to FAIRify data on a wider variety of diseases have been ongoing since the COVID-19 pandemic. CONCLUSIONS This work summarises projects, tools, and workflows for the FAIRification of health research data. The comprehensive review shows that implementing the FAIR concept in health data stewardship carries the promise of improved research data management and transparency in the era of big data and open research publishing. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID) RR2-10.2196/22505.
Collapse
Affiliation(s)
- Esther Thea Inau
- Department of Medical Informatics, Institute for Community Medicine, University Medicine Greifswald, Greifswald, Germany
| | - Jean Sack
- International Health Department, Johns Hopkins Bloomberg School of Public Health, Baltimore, MD, United States
| | - Dagmar Waltemath
- Department of Medical Informatics, Institute for Community Medicine, University Medicine Greifswald, Greifswald, Germany
| | - Atinkut Alamirrew Zeleke
- Department of Medical Informatics, Institute for Community Medicine, University Medicine Greifswald, Greifswald, Germany
| |
Collapse
|
5
|
Varghese AJ, Gouthamchand V, Sasidharan BK, Wee L, Sidhique SK, Rao JP, Dekker A, Hoebers F, Devakumar D, Irodi A, Balasingh TP, Godson HF, Joel T, Mathew M, Gunasingam Isiah R, Pavamani SP, Thomas HMT. Multi-centre radiomics for prediction of recurrence following radical radiotherapy for head and neck cancers: Consequences of feature selection, machine learning classifiers and batch-effect harmonization. Phys Imaging Radiat Oncol 2023; 26:100450. [PMID: 37260438 PMCID: PMC10227455 DOI: 10.1016/j.phro.2023.100450] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/28/2022] [Revised: 05/01/2023] [Accepted: 05/02/2023] [Indexed: 06/02/2023] Open
Abstract
Background and purpose Radiomics models trained with limited single institution data are often not reproducible and generalisable. We developed radiomics models that predict loco-regional recurrence within two years of radiotherapy with private and public datasets and their combinations, to simulate small and multi-institutional studies and study the responsiveness of the models to feature selection, machine learning algorithms, centre-effect harmonization and increased dataset sizes. Materials and methods 562 patients histologically confirmed and treated for locally advanced head-and-neck cancer (LA-HNC) from two public and two private datasets; one private dataset exclusively reserved for validation. Clinical contours of primary tumours were not recontoured and were used for Pyradiomics based feature extraction. ComBat harmonization was applied, and LASSO-Logistic Regression (LR) and Support Vector Machine (SVM) models were built. 95% confidence interval (CI) of 1000 bootstrapped area-under-the-Receiver-operating-curves (AUC) provided predictive performance. Responsiveness of the models' performance to the choice of feature selection methods, ComBat harmonization, machine learning classifier, single and pooled data was evaluated. Results LASSO and SelectKBest selected 14 and 16 features, respectively; three were overlapping. Without ComBat, the LR and SVM models for three institutional data showed AUCs (CI) of 0.513 (0.481-0.559) and 0.632 (0.586-0.665), respectively. Performances following ComBat revealed AUCs of 0.559 (0.536-0.590) and 0.662 (0.606-0.690), respectively. Compared to single cohort AUCs (0.562-0.629), SVM models from pooled data performed significantly better at AUC = 0.680. Conclusions Multi-institutional retrospective data accentuates the existing variabilities that affect radiomics. Carefully designed prospective, multi-institutional studies and data sharing are necessary for clinically relevant head-and-neck cancer prognostication models.
Collapse
Affiliation(s)
- Amal Joseph Varghese
- Department of Radiation Oncology, Christian Medical College, Vellore, Tamil Nadu, India
| | - Varsha Gouthamchand
- Department of Radiation Oncology (Maastro), GROW School for Oncology and Reproduction, Maastricht University Medical Centre+, Maastricht, The Netherlands
| | | | - Leonard Wee
- Department of Radiation Oncology (Maastro), GROW School for Oncology and Reproduction, Maastricht University Medical Centre+, Maastricht, The Netherlands
| | - Sharief K Sidhique
- Department of Radiation Oncology, Christian Medical College, Vellore, Tamil Nadu, India
| | | | - Andre Dekker
- Department of Radiation Oncology (Maastro), GROW School for Oncology and Reproduction, Maastricht University Medical Centre+, Maastricht, The Netherlands
| | - Frank Hoebers
- Department of Radiation Oncology (Maastro), GROW School for Oncology and Reproduction, Maastricht University Medical Centre+, Maastricht, The Netherlands
| | - Devadhas Devakumar
- Department of Nuclear Medicine, Christian Medical College, Vellore, Tamil Nadu, India
| | - Aparna Irodi
- Department of Radiology, Christian Medical College, Vellore, Tamil Nadu, India
| | | | - Henry Finlay Godson
- Department of Radiation Oncology, Christian Medical College, Vellore, Tamil Nadu, India
| | - T Joel
- Department of Radiation Oncology, Christian Medical College, Vellore, Tamil Nadu, India
| | - Manu Mathew
- Department of Radiation Oncology, Christian Medical College, Vellore, Tamil Nadu, India
| | | | | | - Hannah Mary T Thomas
- Department of Radiation Oncology, Christian Medical College, Vellore, Tamil Nadu, India
| |
Collapse
|
6
|
Lafata KJ, Wang Y, Konkel B, Yin FF, Bashir MR. Radiomics: a primer on high-throughput image phenotyping. Abdom Radiol (NY) 2022; 47:2986-3002. [PMID: 34435228 DOI: 10.1007/s00261-021-03254-x] [Citation(s) in RCA: 28] [Impact Index Per Article: 14.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/22/2021] [Revised: 08/15/2021] [Accepted: 08/16/2021] [Indexed: 01/18/2023]
Abstract
Radiomics is a high-throughput approach to image phenotyping. It uses computer algorithms to extract and analyze a large number of quantitative features from radiological images. These radiomic features collectively describe unique patterns that can serve as digital fingerprints of disease. They may also capture imaging characteristics that are difficult or impossible to characterize by the human eye. The rapid development of this field is motivated by systems biology, facilitated by data analytics, and powered by artificial intelligence. Here, as part of Abdominal Radiology's special issue on Quantitative Imaging, we provide an introduction to the field of radiomics. The technique is formally introduced as an advanced application of data analytics, with illustrating examples in abdominal radiology. Artificial intelligence is then presented as the main driving force of radiomics, and common techniques are defined and briefly compared. The complete step-by-step process of radiomic phenotyping is then broken down into five key phases. Potential pitfalls of each phase are highlighted, and recommendations are provided to reduce sources of variation, non-reproducibility, and error associated with radiomics.
Collapse
Affiliation(s)
- Kyle J Lafata
- Department of Radiology, Duke University School of Medicine, Durham, NC, USA. .,Department of Radiation Oncology, Duke University School of Medicine, Durham, NC, USA. .,Department of Electrical & Computer Engineering, Duke University Pratt School of Engineering, Durham, NC, USA.
| | - Yuqi Wang
- Department of Electrical & Computer Engineering, Duke University Pratt School of Engineering, Durham, NC, USA
| | - Brandon Konkel
- Department of Radiology, Duke University School of Medicine, Durham, NC, USA
| | - Fang-Fang Yin
- Department of Radiation Oncology, Duke University School of Medicine, Durham, NC, USA
| | - Mustafa R Bashir
- Department of Radiology, Duke University School of Medicine, Durham, NC, USA.,Department of Medicine, Gastroenterology, Duke University School of Medicine, Durham, NC, USA
| |
Collapse
|
7
|
Jiang J, Rimner A, Deasy JO, Veeraraghavan H. Unpaired Cross-Modality Educed Distillation (CMEDL) for Medical Image Segmentation. IEEE TRANSACTIONS ON MEDICAL IMAGING 2022; 41:1057-1068. [PMID: 34855590 PMCID: PMC9128665 DOI: 10.1109/tmi.2021.3132291] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/15/2023]
Abstract
Accurate and robust segmentation of lung cancers from CT, even those located close to mediastinum, is needed to more accurately plan and deliver radiotherapy and to measure treatment response. Therefore, we developed a new cross-modality educed distillation (CMEDL) approach, using unpaired CT and MRI scans, whereby an informative teacher MRI network guides a student CT network to extract features that signal the difference between foreground and background. Our contribution eliminates two requirements of distillation methods: (i) paired image sets by using an image to image (I2I) translation and (ii) pre-training of the teacher network with a large training set by using concurrent training of all networks. Our framework uses an end-to-end trained unpaired I2I translation, teacher, and student segmentation networks. Architectural flexibility of our framework is demonstrated using 3 segmentation and 2 I2I networks. Networks were trained with 377 CT and 82 T2w MRI from different sets of patients, with independent validation (N = 209 tumors) and testing (N = 609 tumors) datasets. Network design, methods to combine MRI with CT information, distillation learning under informative (MRI to CT), weak (CT to MRI) and equal teacher (MRI to MRI), and ablation tests were performed. Accuracy was measured using Dice similarity (DSC), surface Dice (sDSC), and Hausdorff distance at the 95th percentile (HD95). The CMEDL approach was significantly (p < 0.001) more accurate (DSC of 0.77 vs. 0.73) than non-CMEDL methods with an informative teacher for CT lung tumor, with a weak teacher (DSC of 0.84 vs. 0.81) for MRI lung tumor, and with equal teacher (DSC of 0.90 vs. 0.88) for MRI multi-organ segmentation. CMEDL also reduced inter-rater lung tumor segmentation variabilities.
Collapse
|
8
|
Jha AK, Mithun S, Sherkhane UB, Jaiswar V, Shi Z, Kalendralis P, Kulkarni C, M.S. D, Rajamenakshi R, Sunder G, Purandare N, Wee L, Rangarajan V, van Soest J, Dekker A. Implementation of Big Imaging Data Pipeline Adhering to FAIR Principles for Federated Machine Learning in Oncology. IEEE TRANSACTIONS ON RADIATION AND PLASMA MEDICAL SCIENCES 2022. [DOI: 10.1109/trpms.2021.3113860] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/10/2022]
|
9
|
Radiomics for Predicting Lung Cancer Outcomes Following Radiotherapy: A Systematic Review. Clin Oncol (R Coll Radiol) 2021; 34:e107-e122. [PMID: 34763965 DOI: 10.1016/j.clon.2021.10.006] [Citation(s) in RCA: 15] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/19/2021] [Revised: 08/24/2021] [Accepted: 10/14/2021] [Indexed: 12/13/2022]
Abstract
Lung cancer's radiomic phenotype may potentially inform clinical decision-making with respect to radical radiotherapy. At present there are no validated biomarkers available for the individualisation of radical radiotherapy in lung cancer and the mortality rate of this disease remains the highest of all other solid tumours. MEDLINE was searched using the terms 'radiomics' and 'lung cancer' according to the Preferred Reporting Items for Systematic Reviews and Met-Analyses (PRISMA) guidance. Radiomics studies were defined as those manuscripts describing the extraction and analysis of at least 10 quantifiable imaging features. Only those studies assessing disease control, survival or toxicity outcomes for patients with lung cancer following radical radiotherapy ± chemotherapy were included. Study titles and abstracts were reviewed by two independent reviewers. The Radiomics Quality Score was applied to the full text of included papers. Of 244 returned results, 44 studies met the eligibility criteria for inclusion. End points frequently reported were local (17%), regional (17%) and distant control (31%), overall survival (79%) and pulmonary toxicity (4%). Imaging features strongly associated with clinical outcomes include texture features belonging to the subclasses Gray level run length matrix, Gray level co-occurrence matrix and kurtosis. The median cohort size for model development was 100 (15-645); in the 11 studies with external validation in a separate independent population, the median cohort size was 84 (21-295). The median number of imaging features extracted was 184 (10-6538). The median Radiomics Quality Score was 11% (0-47). Patient-reported outcomes were not incorporated within any studies identified. No studies externally validated a radiomics signature in a registered prospective study. Imaging-derived indices attained through radiomic analyses could equip thoracic oncologists with biomarkers for treatment response, patterns of failure, normal tissue toxicity and survival in lung cancer. Based on routine scans, their non-invasive nature and cost-effectiveness are major advantages over conventional pathological assessment. Improved tools are required for the appraisal of radiomics studies, as significant barriers to clinical implementation remain, such as standardisation of input scan data, quality of reporting and external validation of signatures in randomised, interventional clinical trials.
Collapse
|
10
|
Zhovannik I, Pai S, da Silva Santos TA, van Driel LLG, Dekker A, Fijten R, Traverso A, Bussink J, Monshouwer R. Radiomics integration into a picture archiving and communication system. Phys Imaging Radiat Oncol 2021; 20:30-33. [PMID: 34667885 PMCID: PMC8507196 DOI: 10.1016/j.phro.2021.09.007] [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: 06/04/2021] [Revised: 09/30/2021] [Accepted: 09/30/2021] [Indexed: 12/22/2022] Open
Abstract
Radiomics is referred to as quantitative imaging of biomarkers used for clinical outcome prognosis or tumor characterization. In order to bridge radiomics and its clinical application, we aimed to build an integrated solution of radiomics extraction with an open-source Picture Archiving and Communication System (PACS). The integrated SQLite4Radiomics software was tested in three different imaging modalities and its performance was benchmarked in lung cancer open datasets RIDER and MMD with median extraction time of 10.7 (percentiles 25-75: 8.9-18.7) seconds per ROI in three different configurations.
Collapse
Affiliation(s)
- Ivan Zhovannik
- Department of Radiation Oncology, Radboud Institute for Health Sciences, Radboud University Medical Center, The Netherlands.,Department of Radiation Oncology (Maastro), School for Oncology and Developmental Biology (GROW), Maastricht University Medical Center, The Netherlands
| | - Suraj Pai
- Department of Radiation Oncology (Maastro), School for Oncology and Developmental Biology (GROW), Maastricht University Medical Center, The Netherlands
| | - Talia A da Silva Santos
- Department of Radiation Oncology, Radboud Institute for Health Sciences, Radboud University Medical Center, The Netherlands.,Fontys University of Applied Sciences, The Netherlands
| | | | - Andre Dekker
- Department of Radiation Oncology (Maastro), School for Oncology and Developmental Biology (GROW), Maastricht University Medical Center, The Netherlands
| | - Rianne Fijten
- Department of Radiation Oncology (Maastro), School for Oncology and Developmental Biology (GROW), Maastricht University Medical Center, The Netherlands
| | - Alberto Traverso
- Department of Radiation Oncology (Maastro), School for Oncology and Developmental Biology (GROW), Maastricht University Medical Center, The Netherlands
| | - Johan Bussink
- Department of Radiation Oncology, Radboud Institute for Health Sciences, Radboud University Medical Center, The Netherlands
| | - René Monshouwer
- Department of Radiation Oncology, Radboud Institute for Health Sciences, Radboud University Medical Center, The Netherlands
| |
Collapse
|
11
|
Guiot J, Vaidyanathan A, Deprez L, Zerka F, Danthine D, Frix AN, Lambin P, Bottari F, Tsoutzidis N, Miraglio B, Walsh S, Vos W, Hustinx R, Ferreira M, Lovinfosse P, Leijenaar RTH. A review in radiomics: Making personalized medicine a reality via routine imaging. Med Res Rev 2021; 42:426-440. [PMID: 34309893 DOI: 10.1002/med.21846] [Citation(s) in RCA: 92] [Impact Index Per Article: 30.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/18/2021] [Revised: 07/05/2021] [Accepted: 07/07/2021] [Indexed: 12/14/2022]
Abstract
Radiomics is the quantitative analysis of standard-of-care medical imaging; the information obtained can be applied within clinical decision support systems to create diagnostic, prognostic, and/or predictive models. Radiomics analysis can be performed by extracting hand-crafted radiomics features or via deep learning algorithms. Radiomics has evolved tremendously in the last decade, becoming a bridge between imaging and precision medicine. Radiomics exploits sophisticated image analysis tools coupled with statistical elaboration to extract the wealth of information hidden inside medical images, such as computed tomography (CT), magnetic resonance (MR), and/or Positron emission tomography (PET) scans, routinely performed in the everyday clinical practice. Many efforts have been devoted in recent years to the standardization and validation of radiomics approaches, to demonstrate their usefulness and robustness beyond any reasonable doubts. However, the booming of publications and commercial applications of radiomics approaches warrant caution and proper understanding of all the factors involved to avoid "scientific pollution" and overly enthusiastic claims by researchers and clinicians alike. For these reasons the present review aims to be a guidebook of sorts, describing the process of radiomics, its pitfalls, challenges, and opportunities, along with its ability to improve clinical decision-making, from oncology and respiratory medicine to pharmacological and genotyping studies.
Collapse
Affiliation(s)
- Julien Guiot
- Department of Pneumology, University Hospital of Liège, Liège, Belgium
| | - Akshayaa Vaidyanathan
- Radiomics (Oncoradiomics SA), Liège, Belgium.,The D-Lab, Department of Precision Medicine, Department of Nuclear Medicine, GROW-School for Oncology, Maastricht University, Maastricht, The Netherlands
| | - Louis Deprez
- Department of Radiology, University Hospital of Liège, Liège, Belgium
| | - Fadila Zerka
- Radiomics (Oncoradiomics SA), Liège, Belgium.,The D-Lab, Department of Precision Medicine, Department of Nuclear Medicine, GROW-School for Oncology, Maastricht University, Maastricht, The Netherlands
| | - Denis Danthine
- Department of Radiology, University Hospital of Liège, Liège, Belgium
| | - Anne-Noelle Frix
- Department of Pneumology, University Hospital of Liège, Liège, Belgium
| | - Philippe Lambin
- The D-Lab, Department of Precision Medicine, Department of Nuclear Medicine, GROW-School for Oncology, Maastricht University, Maastricht, The Netherlands
| | | | | | | | - Sean Walsh
- Radiomics (Oncoradiomics SA), Liège, Belgium
| | - Wim Vos
- Radiomics (Oncoradiomics SA), Liège, Belgium
| | - Roland Hustinx
- Department of Nuclear Medicine and Oncological Imaging, University Hospital of Liege, Liege, Belgium.,GIGA-CRC in vivo imaging, University of Liège, Liège, Belgium
| | - Marta Ferreira
- GIGA-CRC in vivo imaging, University of Liège, Liège, Belgium
| | - Pierre Lovinfosse
- Department of Nuclear Medicine and Oncological Imaging, University Hospital of Liege, Liege, Belgium
| | | |
Collapse
|
12
|
Kirby J, Prior F, Petrick N, Hadjiski L, Farahani K, Drukker K, Kalpathy-Cramer J, Glide-Hurst C, El Naqa I. Introduction to special issue on datasets hosted in The Cancer Imaging Archive (TCIA). Med Phys 2021; 47:6026-6028. [PMID: 33202038 DOI: 10.1002/mp.14595] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/03/2020] [Revised: 11/03/2020] [Accepted: 11/09/2020] [Indexed: 01/19/2023] Open
Affiliation(s)
- Justin Kirby
- Frederick National Laboratory for Cancer Research, Cancer Imaging Informatics Lab, National Institute of Health, Frederick, MD, USA
| | - Fred Prior
- Department of Biomedical Informatics, University of Arkansas for Medical Sciences, Little Rock, AR, USA
| | - Nicholas Petrick
- Center for Devices and Radiological Health, U.S. Food and Drug Administration, Silver Spring, MD, USA
| | - Lubomir Hadjiski
- Department of Radiology, University of Michigan, Ann Arbor, MI, USA
| | - Keyvan Farahani
- Center for Biomedical Informatics and Information Technology, National Cancer Institute, Bethesda, MD, USA
| | | | | | - Carri Glide-Hurst
- Department of Radiation Oncology, University of Wisconsin, Madison, WI, USA
| | - Issam El Naqa
- Department of Machine Learning, Moffitt Cancer Center, Tampa, FL, USA
| |
Collapse
|
13
|
Kalendralis P, Sloep M, van Soest J, Dekker A, Fijten R. Making radiotherapy more efficient with FAIR data. Phys Med 2021; 82:158-162. [PMID: 33639520 DOI: 10.1016/j.ejmp.2021.01.083] [Citation(s) in RCA: 6] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 12/03/2020] [Revised: 01/26/2021] [Accepted: 01/29/2021] [Indexed: 12/13/2022] Open
Abstract
Given the rapid growth of artificial intelligence (AI) applications in radiotherapy and the related transformations toward the data-driven healthcare domain, this article summarizes the need and usage of the FAIR (Findable, Accessible, Interoperable, Reusable) data principles in radiotherapy. This work introduces the FAIR data concept, presents practical and relevant use cases and the future role of the different parties involved. The goal of this article is to provide guidance and potential applications of FAIR to various radiotherapy stakeholders, focusing on the central role of medical physicists.
Collapse
Affiliation(s)
- Petros Kalendralis
- Department of Radiation Oncology (Maastro), GROW School for Oncology, Maastricht University Medical Centre+, 6229 ET Maastricht, The Netherlands.
| | - Matthijs Sloep
- Department of Radiation Oncology (Maastro), GROW School for Oncology, Maastricht University Medical Centre+, 6229 ET Maastricht, The Netherlands
| | - Johan van Soest
- Department of Radiation Oncology (Maastro), GROW School for Oncology, Maastricht University Medical Centre+, 6229 ET Maastricht, The Netherlands
| | - Andre Dekker
- Department of Radiation Oncology (Maastro), GROW School for Oncology, Maastricht University Medical Centre+, 6229 ET Maastricht, The Netherlands
| | - Rianne Fijten
- Department of Radiation Oncology (Maastro), GROW School for Oncology, Maastricht University Medical Centre+, 6229 ET Maastricht, The Netherlands
| |
Collapse
|