1
|
Fu Q, Chen X, Liu Y, Zhang J, Xu Y, Yang X, Huang M, Men K, Dai J. Improvement of accumulated dose distribution in combined cervical cancer radiotherapy with deep learning-based dose prediction. Front Oncol 2024; 14:1407016. [PMID: 39040460 PMCID: PMC11260613 DOI: 10.3389/fonc.2024.1407016] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/26/2024] [Accepted: 06/17/2024] [Indexed: 07/24/2024] Open
Abstract
Purpose Difficulties remain in dose optimization and evaluation of cervical cancer radiotherapy that combines external beam radiotherapy (EBRT) and brachytherapy (BT). This study estimates and improves the accumulated dose distribution of EBRT and BT with deep learning-based dose prediction. Materials and methods A total of 30 patients treated with combined cervical cancer radiotherapy were enrolled in this study. The dose distributions of EBRT and BT plans were accumulated using commercial deformable image registration. A ResNet-101-based deep learning model was trained to predict pixel-wise dose distributions. To test the role of the predicted accumulated dose in clinic, each EBRT plan was designed using conventional method and then redesigned referencing the predicted accumulated dose distribution. Bladder and rectum dosimetric parameters and normal tissue complication probability (NTCP) values were calculated and compared between the conventional and redesigned accumulated doses. Results The redesigned accumulated doses showed a decrease in mean values of V50, V60, and D2cc for the bladder (-3.02%, -1.71%, and -1.19 Gy, respectively) and rectum (-4.82%, -1.97%, and -4.13 Gy, respectively). The mean NTCP values for the bladder and rectum were also decreased by 0.02‰ and 0.98%, respectively. All values had statistically significant differences (p < 0.01), except for the bladder D2cc (p = 0.112). Conclusion This study realized accumulated dose prediction for combined cervical cancer radiotherapy without knowing the BT dose. The predicted dose served as a reference for EBRT treatment planning, leading to a superior accumulated dose distribution and lower NTCP values.
Collapse
Affiliation(s)
- Qi Fu
- Department of Radiation Oncology, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medial Sciences and Peking Union Medical College, Beijing, China
| | - Xinyuan Chen
- Department of Radiation Oncology, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medial Sciences and Peking Union Medical College, Beijing, China
| | - Yuxiang Liu
- Department of Radiation Oncology, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medial Sciences and Peking Union Medical College, Beijing, China
- School of Physics and Technology, Wuhan University, Wuhan, China
| | - Jingbo Zhang
- Department of Radiotherapy Technology, The Cancer and Tuberculosis Hospital, Jiamusi, China
| | - Yingjie Xu
- Department of Radiation Oncology, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medial Sciences and Peking Union Medical College, Beijing, China
| | - Xi Yang
- Department of Radiation Oncology, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medial Sciences and Peking Union Medical College, Beijing, China
| | - Manni Huang
- Department of Radiation Oncology, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medial Sciences and Peking Union Medical College, Beijing, China
| | - Kuo Men
- Department of Radiation Oncology, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medial Sciences and Peking Union Medical College, Beijing, China
| | - Jianrong Dai
- Department of Radiation Oncology, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medial Sciences and Peking Union Medical College, Beijing, China
| |
Collapse
|
2
|
Moore LC, Ahern F, Li L, Kallis K, Kisling K, Cortes KG, Nwachukwu C, Rash D, Yashar CM, Mayadev J, Zou J, Vasconcelos N, Meyers SM. Neural network dose prediction for cervical brachytherapy: Overcoming data scarcity for applicator-specific models. Med Phys 2024; 51:4591-4606. [PMID: 38814165 PMCID: PMC11309769 DOI: 10.1002/mp.17230] [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: 11/16/2023] [Revised: 05/09/2024] [Accepted: 05/11/2024] [Indexed: 05/31/2024] Open
Abstract
BACKGROUND 3D neural network dose predictions are useful for automating brachytherapy (BT) treatment planning for cervical cancer. Cervical BT can be delivered with numerous applicators, which necessitates developing models that generalize to multiple applicator types. The variability and scarcity of data for any given applicator type poses challenges for deep learning. PURPOSE The goal of this work was to compare three methods of neural network training-a single model trained on all applicator data, fine-tuning the combined model to each applicator, and individual (IDV) applicator models-to determine the optimal method for dose prediction. METHODS Models were produced for four applicator types-tandem-and-ovoid (T&O), T&O with 1-7 needles (T&ON), tandem-and-ring (T&R) and T&R with 1-4 needles (T&RN). First, the combined model was trained on 859 treatment plans from 266 cervical cancer patients treated from 2010 onwards. The train/validation/test split was 70%/16%/14%, with approximately 49%/10%/19%/22% T&O/T&ON/T&R/T&RN in each dataset. Inputs included four channels for anatomical masks (high-risk clinical target volume [HRCTV], bladder, rectum, and sigmoid), a mask indicating dwell position locations, and applicator channels for each applicator component. Applicator channels were created by mapping the 3D dose for a single dwell position to each dwell position and summing over each applicator component with uniform dwell time weighting. A 3D Cascade U-Net, which consists of two U-Nets in sequence, and mean squared error loss function were used. The combined model was then fine-tuned to produce four applicator-specific models by freezing the first U-Net and encoding layers of the second and resuming training on applicator-specific data. Finally, four IDV models were trained using only data from each applicator type. Performance of these three model types was compared using the following metrics for the test set: mean error (ME, representing model bias) and mean absolute error (MAE) over all dose voxels and ME of clinical metrics (HRCTV D90% and D2cc of bladder, rectum, and sigmoid), averaged over all patients. A positive ME indicates the clinical dose was higher than predicted. 3D global gamma analysis with the prescription dose as reference value was performed. Dice similarity coefficients (DSC) were computed for each isodose volume. RESULTS Fine-tuned and combined models showed better performance than IDV applicator training. Fine-tuning resulted in modest improvements in about half the metrics, compared to the combined model, while the remainder were mostly unchanged. Fine-tuned MAE = 3.98%/2.69%/5.36%/3.80% for T&O/T&R/T&ON/T&RN, and ME over all voxels = -0.08%/-0.89%/-0.59%/1.42%. ME D2cc were bladder = -0.77%/1.00%/-0.66%/-1.53%, rectum = 1.11%/-0.22%/-0.29%/-3.37%, sigmoid = -0.47%/-0.06%/-2.37%/-1.40%, and ME D90 = 2.6%/-4.4%/4.8%/0.0%. Gamma pass rates (3%/3 mm) were 86%/91%/83%/89%. Mean DSCs were 0.92%/0.92%/0.88%/0.91% for isodoses ≤ 150% of prescription. CONCLUSIONS 3D BT dose was accurately predicted for all applicator types, as indicated by the low MAE and MEs, high gamma scores and high DSCs. Training on all treatment data overcomes challenges with data scarcity in each applicator type, resulting in superior performance than can be achieved by training on IDV applicators alone. This could presumably be explained by the fact that the larger, more diverse dataset allows the neural network to learn underlying trends and characteristics in dose that are common to all treatment applicators. Accurate, applicator-specific dose predictions could enable automated, knowledge-based planning for any cervical brachytherapy treatment.
Collapse
Affiliation(s)
- Lance C Moore
- Radiation Medicine and Applied Sciences, University of California San Diego, La Jolla, California, USA
| | - Fritz Ahern
- Radiation Medicine and Applied Sciences, University of California San Diego, La Jolla, California, USA
| | - Lingyi Li
- Radiation Medicine and Applied Sciences, University of California San Diego, La Jolla, California, USA
| | - Karoline Kallis
- Radiation Medicine and Applied Sciences, University of California San Diego, La Jolla, California, USA
| | - Kelly Kisling
- Radiation Medicine and Applied Sciences, University of California San Diego, La Jolla, California, USA
| | - Katherina G Cortes
- Radiation Medicine and Applied Sciences, University of California San Diego, La Jolla, California, USA
| | - Chika Nwachukwu
- Radiation Medicine and Applied Sciences, University of California San Diego, La Jolla, California, USA
| | - Dominique Rash
- Radiation Medicine and Applied Sciences, University of California San Diego, La Jolla, California, USA
| | - Catheryn M Yashar
- Radiation Medicine and Applied Sciences, University of California San Diego, La Jolla, California, USA
| | - Jyoti Mayadev
- Radiation Medicine and Applied Sciences, University of California San Diego, La Jolla, California, USA
| | - Jingjing Zou
- Herbert Wertheim School of Public Health and Human Longevity Science, University of California, San Diego and Moores Cancer Center, La Jolla, California, USA
| | - Nuno Vasconcelos
- Electrical and Computer Engineering, University of California San Diego, La Jolla, California, USA
| | - Sandra M Meyers
- Radiation Medicine and Applied Sciences, University of California San Diego, La Jolla, California, USA
| |
Collapse
|
3
|
Xiong T, Cai J, Zhou F, Liu B, Zhang J, Wu Q. An end-to-end deep convolutional neural network-based dose engine for parotid gland cancer seed implant brachytherapy. Med Phys 2024. [PMID: 38753975 DOI: 10.1002/mp.17123] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/30/2023] [Revised: 04/12/2024] [Accepted: 04/29/2024] [Indexed: 05/18/2024] Open
Abstract
BACKGROUND Seed implant brachytherapy (SIBT) is a promising treatment modality for parotid gland cancers (PGCs). However, the current clinical standard dose calculation method based on the American Association of Physicists in Medicine (AAPM) Task Group 43 (TG-43) Report oversimplifies patient anatomy as a homogeneous water phantom medium, leading to significant dose calculation errors due to heterogeneity surrounding the parotid gland. Monte Carlo Simulation (MCS) can yield accurate dose distributions but the long computation time hinders its wide application in clinical practice. PURPOSE This paper aims to develop an end-to-end deep convolutional neural network-based dose engine (DCNN-DE) to achieve fast and accurate dose calculation for PGC SIBT. METHODS A DCNN model was trained using the patient's CT images and TG-43-based dose maps as inputs, with the corresponding MCS-based dose maps as the ground truth. The DCNN model was enhanced based on our previously proposed model by incorporating attention gates (AGs) and large kernel convolutions. Training and evaluation of the model were performed using a dataset comprising 188 PGC I-125 SIBT patient cases, and its transferability was tested on an additional 16 non-PGC head and neck cancers (HNCs) I-125 SIBT patient cases. Comparison studies were conducted to validate the superiority of the enhanced model over the original one and compare their overall performance. RESULTS On the PGC testing dataset, the DCNN-DE demonstrated the ability to generate accurate dose maps, with percentage absolute errors (PAEs) of 0.67% ± 0.47% for clinical target volume (CTV) D90 and 1.04% ± 1.33% for skin D0.1cc. The comparison studies revealed that incorporating AGs and large kernel convolutions resulted in 8.2% (p < 0.001) and 3.1% (p < 0.001) accuracy improvement, respectively, as measured by dose mean absolute error. On the non-PGC HNC dataset, the DCNN-DE exhibited good transferability, achieving a CTV D90 PAE of 1.88% ± 1.73%. The DCNN-DE can generate a dose map in less than 10 ms. CONCLUSIONS We have developed and validated an end-to-end DCNN-DE for PGC SIBT. The proposed DCNN-DE enables fast and accurate dose calculation, making it suitable for application in the plan optimization and evaluation process of PGC SIBT.
Collapse
Affiliation(s)
- Tianyu Xiong
- Image Processing Center, Beihang University, Beijing, People's Republic of China
- Department of Health Technology and Informatics, The Hong Kong Polytechnic University, Hong Kong SAR, People's Republic of China
| | - Jing Cai
- Department of Health Technology and Informatics, The Hong Kong Polytechnic University, Hong Kong SAR, People's Republic of China
| | - Fugen Zhou
- Image Processing Center, Beihang University, Beijing, People's Republic of China
| | - Bo Liu
- Image Processing Center, Beihang University, Beijing, People's Republic of China
| | - Jie Zhang
- Department of Oral and Maxillofacial Surgery, Peking University School of Stomatology, Beijing, People's Republic of China
| | - Qiuwen Wu
- Department of Radiation Oncology, Duke University Medical Center, Durham, North Carolina, USA
| |
Collapse
|
4
|
Wang Y, Liu Y, Bai Y, Zhou Q, Xu S, Pang X. A generalization performance study on the boosting radiotherapy dose calculation engine based on super-resolution. Z Med Phys 2024; 34:208-217. [PMID: 36631314 DOI: 10.1016/j.zemedi.2022.10.006] [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: 12/24/2021] [Revised: 10/10/2022] [Accepted: 10/10/2022] [Indexed: 01/11/2023]
Abstract
PURPOSE During the radiation treatment planning process, one of the time-consuming procedures is the final high-resolution dose calculation, which obstacles the wide application of the emerging online adaptive radiotherapy techniques (OLART). There is an urgent desire for highly accurate and efficient dose calculation methods. This study aims to develop a dose super resolution-based deep learning model for fast and accurate dose prediction in clinical practice. METHOD A Multi-stage Dose Super-Resolution Network (MDSR Net) architecture with sparse masks module and multi-stage progressive dose distribution restoration method were developed to predict high-resolution dose distribution using low-resolution data. A total of 340 VMAT plans from different disease sites were used, among which 240 randomly selected nasopharyngeal, lung, and cervix cases were used for model training, and the remaining 60 cases from the same sites for model benchmark testing, and additional 40 cases from the unseen site (breast and rectum) was used for model generalizability evaluation. The clinical calculated dose with a grid size of 2 mm was used as baseline dose distribution. The input included the dose distribution with 4 mm grid size and CT images. The model performance was compared with HD U-Net and cubic interpolation methods using Dose-volume histograms (DVH) metrics and global gamma analysis with 1%/1 mm and 10% low dose threshold. The correlation between the prediction error and the dose, dose gradient, and CT values was also evaluated. RESULTS The prediction errors of MDSR were 0.06-0.84% of Dmean indices, and the gamma passing rate was 83.1-91.0% on the benchmark testing dataset, and 0.02-1.03% and 71.3-90.3% for the generalization dataset respectively. The model performance was significantly higher than the HD U-Net and interpolation methods (p < 0.05). The mean errors of the MDSR model decreased (monotonously by 0.03-0.004%) with dose and increased (by 0.01-0.73%) with the dose gradient. There was no correlation between prediction errors and the CT values. CONCLUSION The proposed MDSR model achieved good agreement with the baseline high-resolution dose distribution, with small prediction errors for DVH indices and high gamma passing rate for both seen and unseen sites, indicating a robust and generalizable dose prediction model. The model can provide fast and accurate high-resolution dose distribution for clinical dose calculation, particularly for the routine practice of OLART.
Collapse
Affiliation(s)
- Yewei Wang
- Department of Radiation Physics, The Affiliated Tumor Hospital of Harbin Medical University, Harbin, China
| | - Yaoying Liu
- School of Physics, Beihang University, Beijing, China; Manteia Technologies Co, Ltd, Xiamen, Fujian, China; Department of Radiation Oncology, PLA General Hospital, Beijing, China
| | - Yanlin Bai
- Department of Radiation Physics, The Affiliated Tumor Hospital of Harbin Medical University, Harbin, China
| | - Qichao Zhou
- Manteia Technologies Co, Ltd, Xiamen, Fujian, China
| | - Shouping Xu
- Department of Radiation Oncology, PLA General Hospital, Beijing, China
| | - Xueying Pang
- Department of Oncology, First Affiliated Hospital, Heilongjiang University of Chinese Medicine, Harbin, China.
| |
Collapse
|
5
|
Hajianfar G, Sabouri M, Salimi Y, Amini M, Bagheri S, Jenabi E, Hekmat S, Maghsudi M, Mansouri Z, Khateri M, Hosein Jamshidi M, Jafari E, Bitarafan Rajabi A, Assadi M, Oveisi M, Shiri I, Zaidi H. Artificial intelligence-based analysis of whole-body bone scintigraphy: The quest for the optimal deep learning algorithm and comparison with human observer performance. Z Med Phys 2024; 34:242-257. [PMID: 36932023 PMCID: PMC11156776 DOI: 10.1016/j.zemedi.2023.01.008] [Citation(s) in RCA: 4] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/28/2022] [Revised: 12/22/2022] [Accepted: 01/18/2023] [Indexed: 03/17/2023]
Abstract
PURPOSE Whole-body bone scintigraphy (WBS) is one of the most widely used modalities in diagnosing malignant bone diseases during the early stages. However, the procedure is time-consuming and requires vigour and experience. Moreover, interpretation of WBS scans in the early stages of the disorders might be challenging because the patterns often reflect normal appearance that is prone to subjective interpretation. To simplify the gruelling, subjective, and prone-to-error task of interpreting WBS scans, we developed deep learning (DL) models to automate two major analyses, namely (i) classification of scans into normal and abnormal and (ii) discrimination between malignant and non-neoplastic bone diseases, and compared their performance with human observers. MATERIALS AND METHODS After applying our exclusion criteria on 7188 patients from three different centers, 3772 and 2248 patients were enrolled for the first and second analyses, respectively. Data were split into two parts, including training and testing, while a fraction of training data were considered for validation. Ten different CNN models were applied to single- and dual-view input (posterior and anterior views) modes to find the optimal model for each analysis. In addition, three different methods, including squeeze-and-excitation (SE), spatial pyramid pooling (SPP), and attention-augmented (AA), were used to aggregate the features for dual-view input models. Model performance was reported through area under the receiver operating characteristic (ROC) curve (AUC), accuracy, sensitivity, and specificity and was compared with the DeLong test applied to ROC curves. The test dataset was evaluated by three nuclear medicine physicians (NMPs) with different levels of experience to compare the performance of AI and human observers. RESULTS DenseNet121_AA (DensNet121, with dual-view input aggregated by AA) and InceptionResNetV2_SPP achieved the highest performance (AUC = 0.72) for the first and second analyses, respectively. Moreover, on average, in the first analysis, Inception V3 and InceptionResNetV2 CNN models and dual-view input with AA aggregating method had superior performance. In addition, in the second analysis, DenseNet121 and InceptionResNetV2 as CNN methods and dual-view input with AA aggregating method achieved the best results. Conversely, the performance of AI models was significantly higher than human observers for the first analysis, whereas their performance was comparable in the second analysis, although the AI model assessed the scans in a drastically lower time. CONCLUSION Using the models designed in this study, a positive step can be taken toward improving and optimizing WBS interpretation. By training DL models with larger and more diverse cohorts, AI could potentially be used to assist physicians in the assessment of WBS images.
Collapse
Affiliation(s)
- Ghasem Hajianfar
- Division of Nuclear Medicine and Molecular Imaging, Geneva University Hospital, CH-1211 Geneva 4, Switzerland
| | - Maziar Sabouri
- Department of Medical Physics, School of Medicine, Iran University of Medical Science, Tehran, Iran; Rajaie Cardiovascular Medical and Research Center, Iran University of Medical Sciences, Tehran, Iran
| | - Yazdan Salimi
- Division of Nuclear Medicine and Molecular Imaging, Geneva University Hospital, CH-1211 Geneva 4, Switzerland
| | - Mehdi Amini
- Division of Nuclear Medicine and Molecular Imaging, Geneva University Hospital, CH-1211 Geneva 4, Switzerland
| | - Soroush Bagheri
- Rajaie Cardiovascular Medical and Research Center, Iran University of Medical Sciences, Tehran, Iran
| | - Elnaz Jenabi
- Research Center for Nuclear Medicine, Shariati Hospital, Tehran University of Medical Sciences, Tehran, Iran
| | - Sepideh Hekmat
- Hasheminejad Hospital, Iran University of Medical Sciences, Tehran, Iran
| | - Mehdi Maghsudi
- Rajaie Cardiovascular Medical and Research Center, Iran University of Medical Sciences, Tehran, Iran
| | - Zahra Mansouri
- Division of Nuclear Medicine and Molecular Imaging, Geneva University Hospital, CH-1211 Geneva 4, Switzerland
| | - Maziar Khateri
- Department of Medical Radiation Engineering, Science and Research Branch, Islamic Azad University, Tehran, Iran
| | - Mohammad Hosein Jamshidi
- Department of Medical Imaging and Radiation Sciences, School of Allied Medical Sciences, Ahvaz Jundishapur University of Medical Sciences, Ahvaz, Iran
| | - Esmail Jafari
- The Persian Gulf Nuclear Medicine Research Center, Department of Molecular Imaging and Radionuclide Therapy, Bushehr Medical University Hospital, School of Medicine, Bushehr University of Medical Sciences, Bushehr, Iran
| | - Ahmad Bitarafan Rajabi
- Rajaie Cardiovascular Medical and Research Center, Iran University of Medical Sciences, Tehran, Iran
| | - Majid Assadi
- The Persian Gulf Nuclear Medicine Research Center, Department of Molecular Imaging and Radionuclide Therapy, Bushehr Medical University Hospital, School of Medicine, Bushehr University of Medical Sciences, Bushehr, Iran
| | - Mehrdad Oveisi
- Department of Computer Science, University of British Columbia, Vancouver, BC, Canada
| | - Isaac Shiri
- Division of Nuclear Medicine and Molecular Imaging, Geneva University Hospital, CH-1211 Geneva 4, Switzerland
| | - Habib Zaidi
- Division of Nuclear Medicine and Molecular Imaging, Geneva University Hospital, CH-1211 Geneva 4, Switzerland; Geneva University Neurocenter, Geneva University, Geneva, Switzerland; Department of Nuclear Medicine and Molecular Imaging, University of Groningen, University Medical Center Groningen, Groningen, the Netherlands; Department of Nuclear Medicine, University of Southern Denmark, Odense, Denmark.
| |
Collapse
|
6
|
Fechter T, Sachpazidis I, Baltas D. The use of deep learning in interventional radiotherapy (brachytherapy): A review with a focus on open source and open data. Z Med Phys 2024; 34:180-196. [PMID: 36376203 PMCID: PMC11156786 DOI: 10.1016/j.zemedi.2022.10.005] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/13/2022] [Revised: 10/07/2022] [Accepted: 10/10/2022] [Indexed: 11/13/2022]
Abstract
Deep learning advanced to one of the most important technologies in almost all medical fields. Especially in areas, related to medical imaging it plays a big role. However, in interventional radiotherapy (brachytherapy) deep learning is still in an early phase. In this review, first, we investigated and scrutinised the role of deep learning in all processes of interventional radiotherapy and directly related fields. Additionally, we summarised the most recent developments. For better understanding, we provide explanations of key terms and approaches to solving common deep learning problems. To reproduce results of deep learning algorithms both source code and training data must be available. Therefore, a second focus of this work is on the analysis of the availability of open source, open data and open models. In our analysis, we were able to show that deep learning plays already a major role in some areas of interventional radiotherapy, but is still hardly present in others. Nevertheless, its impact is increasing with the years, partly self-propelled but also influenced by closely related fields. Open source, data and models are growing in number but are still scarce and unevenly distributed among different research groups. The reluctance in publishing code, data and models limits reproducibility and restricts evaluation to mono-institutional datasets. The conclusion of our analysis is that deep learning can positively change the workflow of interventional radiotherapy but there is still room for improvements when it comes to reproducible results and standardised evaluation methods.
Collapse
Affiliation(s)
- Tobias Fechter
- Division of Medical Physics, Department of Radiation Oncology, Medical Center University of Freiburg, Germany; Faculty of Medicine, University of Freiburg, Germany; German Cancer Consortium (DKTK), Partner Site Freiburg, Germany.
| | - Ilias Sachpazidis
- Division of Medical Physics, Department of Radiation Oncology, Medical Center University of Freiburg, Germany; Faculty of Medicine, University of Freiburg, Germany; German Cancer Consortium (DKTK), Partner Site Freiburg, Germany
| | - Dimos Baltas
- Division of Medical Physics, Department of Radiation Oncology, Medical Center University of Freiburg, Germany; Faculty of Medicine, University of Freiburg, Germany; German Cancer Consortium (DKTK), Partner Site Freiburg, Germany
| |
Collapse
|
7
|
Quetin S, Bahoric B, Maleki F, Enger SA. Deep learning for high-resolution dose prediction in high dose rate brachytherapy for breast cancer treatment. Phys Med Biol 2024; 69:105011. [PMID: 38604185 DOI: 10.1088/1361-6560/ad3dbd] [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: 12/04/2023] [Accepted: 04/11/2024] [Indexed: 04/13/2024]
Abstract
Objective.Monte Carlo (MC) simulations are the benchmark for accurate radiotherapy dose calculations, notably in patient-specific high dose rate brachytherapy (HDR BT), in cases where considering tissue heterogeneities is critical. However, the lengthy computational time limits the practical application of MC simulations. Prior research used deep learning (DL) for dose prediction as an alternative to MC simulations. While accurate dose predictions akin to MC were attained, graphics processing unit limitations constrained these predictions to large voxels of 3 mm × 3 mm × 3 mm. This study aimed to enable dose predictions as accurate as MC simulations in 1 mm × 1 mm × 1 mm voxels within a clinically acceptable timeframe.Approach.Computed tomography scans of 98 breast cancer patients treated with Iridium-192-based HDR BT were used: 70 for training, 14 for validation, and 14 for testing. A new cropping strategy based on the distance to the seed was devised to reduce the volume size, enabling efficient training of 3D DL models using 1 mm × 1 mm × 1 mm dose grids. Additionally, novel DL architecture with layer-level fusion were proposed to predict MC simulated dose to medium-in-medium (Dm,m). These architectures fuse information from TG-43 dose to water-in-water (Dw,w) with patient tissue composition at the layer-level. Different inputs describing patient body composition were investigated.Main results.The proposed approach demonstrated state-of-the-art performance, on par with the MCDm,mmaps, but 300 times faster. The mean absolute percent error for dosimetric indices between the MC and DL-predicted complete treatment plans was 0.17% ± 0.15% for the planning target volumeV100, 0.30% ± 0.32% for the skinD2cc, 0.82% ± 0.79% for the lungD2cc, 0.34% ± 0.29% for the chest wallD2ccand 1.08% ± 0.98% for the heartD2cc.Significance.Unlike the time-consuming MC simulations, the proposed novel strategy efficiently converts TG-43Dw,wmaps into preciseDm,mmaps at high resolution, enabling clinical integration.
Collapse
Affiliation(s)
- Sébastien Quetin
- Medical Physics Unit, Department of Oncology, McGill University, Montreal, QC, Canada
- Montreal Institute for Learning Algorithms, Mila, Montreal, QC, Canada
| | - Boris Bahoric
- Department of Radiation Oncology, Jewish General Hospital, McGill University, Montreal, QC, Canada
| | - Farhad Maleki
- Department of Computer Science, University of Calgary, Calgary, AB, Canada
- Department of Diagnostic Radiology, McGill University, Montreal, QC, Canada
- Department of Radiology, University of Florida, Gainesville, FL, United States of America
| | - Shirin A Enger
- Medical Physics Unit, Department of Oncology, McGill University, Montreal, QC, Canada
- Montreal Institute for Learning Algorithms, Mila, Montreal, QC, Canada
- Lady Davis Institute for Medical Research, Jewish General Hospital, Montreal, QC, Canada
| |
Collapse
|
8
|
Berumen F, Ouellet S, Enger S, Beaulieu L. Aleatoric and epistemic uncertainty extraction of patient-specific deep learning-based dose predictions in LDR prostate brachytherapy. Phys Med Biol 2024; 69:085026. [PMID: 38484398 DOI: 10.1088/1361-6560/ad3418] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/30/2023] [Accepted: 03/14/2024] [Indexed: 04/10/2024]
Abstract
Objective.In brachytherapy, deep learning (DL) algorithms have shown the capability of predicting 3D dose volumes. The reliability and accuracy of such methodologies remain under scrutiny for prospective clinical applications. This study aims to establish fast DL-based predictive dose algorithms for low-dose rate (LDR) prostate brachytherapy and to evaluate their uncertainty and stability.Approach.Data from 200 prostate patients, treated with125I sources, was collected. The Monte Carlo (MC) ground truth dose volumes were calculated with TOPAS considering the interseed effects and an organ-based material assignment. Two 3D convolutional neural networks, UNet and ResUNet TSE, were trained using the patient geometry and the seed positions as the input data. The dataset was randomly split into training (150), validation (25) and test (25) sets. The aleatoric (associated with the input data) and epistemic (associated with the model) uncertainties of the DL models were assessed.Main results.For the full test set, with respect to the MC reference, the predicted prostateD90metric had mean differences of -0.64% and 0.08% for the UNet and ResUNet TSE models, respectively. In voxel-by-voxel comparisons, the average global dose difference ratio in the [-1%, 1%] range included 91.0% and 93.0% of voxels for the UNet and the ResUNet TSE, respectively. One forward pass or prediction took 4 ms for a 3D dose volume of 2.56 M voxels (128 × 160 × 128). The ResUNet TSE model closely encoded the well-known physics of the problem as seen in a set of uncertainty maps. The ResUNet TSE rectum D2cchad the largest uncertainty metric of 0.0042.Significance.The proposed DL models serve as rapid dose predictors that consider the patient anatomy and interseed attenuation effects. The derived uncertainty is interpretable, highlighting areas where DL models may struggle to provide accurate estimations. The uncertainty analysis offers a comprehensive evaluation tool for dose predictor model assessment.
Collapse
Affiliation(s)
- Francisco Berumen
- Service de Physique Médicale et de Radioprotection, Centre Intégré de Cancérologie, CHU de Québec-Université Laval et Centre de recherche du CHU de Québec, Quebec, Quebec, Canada
- Département de Physique, de Génie Physique et d'Optique et Centre de Recherche sur le Cancer, Université Laval, Quebec, Quebec, Canada
| | - Samuel Ouellet
- Service de Physique Médicale et de Radioprotection, Centre Intégré de Cancérologie, CHU de Québec-Université Laval et Centre de recherche du CHU de Québec, Quebec, Quebec, Canada
- Département de Physique, de Génie Physique et d'Optique et Centre de Recherche sur le Cancer, Université Laval, Quebec, Quebec, Canada
| | - Shirin Enger
- Medical Physics Unit, Department of Oncology, McGill University, Montreal, Quebec, Canada
- Lady Davis Institute for Medical Research, Jewish General Hospital, Montreal, Quebec, Canada
| | - Luc Beaulieu
- Service de Physique Médicale et de Radioprotection, Centre Intégré de Cancérologie, CHU de Québec-Université Laval et Centre de recherche du CHU de Québec, Quebec, Quebec, Canada
- Département de Physique, de Génie Physique et d'Optique et Centre de Recherche sur le Cancer, Université Laval, Quebec, Quebec, Canada
| |
Collapse
|
9
|
Xiao Z, Xiong T, Geng L, Zhou F, Liu B, Sun H, Ji Z, Jiang Y, Wang J, Wu Q. Automatic planning for head and neck seed implant brachytherapy based on deep convolutional neural network dose engine. Med Phys 2024; 51:1460-1473. [PMID: 37757449 DOI: 10.1002/mp.16760] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/24/2023] [Revised: 08/30/2023] [Accepted: 09/15/2023] [Indexed: 09/29/2023] Open
Abstract
BACKGROUND Seed implant brachytherapy (SIBT) is an effective treatment modality for head and neck (H&N) cancers; however, current clinical planning requires manual setting of needle paths and utilizes inaccurate dose calculation algorithms. PURPOSE This study aims to develop an accurate and efficient deep convolutional neural network dose engine (DCNN-DE) and an automatic SIBT planning method for H&N SIBT. METHODS A cohort of 25 H&N patients who received SIBT was utilized to develop and validate the methods. The DCNN-DE was developed based on 3D-unet model. It takes single seed dose distribution from a modified TG-43 method, the CT image and a novel inter-seed shadow map (ISSM) as inputs, and predicts the dose map of accuracy close to the one from Monte Carlo simulations (MCS). The ISSM was proposed to better handle inter-seed attenuation. The accuracy and efficacy of the DCNN-DE were validated by comparing with other methods taking MCS dose as reference. For SIBT planning, a novel strategy inspired by clinical practice was proposed to automatically generate parallel or non-parallel potential needle paths that avoid puncturing bone and critical organs. A heuristic-based optimization method was developed to optimize the seed positions to meet clinical prescription requirements. The proposed planning method was validated by re-planning the 25 cases and comparing with clinical plans. RESULTS The absolute percentage error in the TG-43 calculation for CTV V100 and D90 was reduced from 5.4% and 13.2% to 0.4% and 1.1% with DCNN-DE, an accuracy improvement of 93% and 92%, respectively. The proposed planning method could automatically obtain a plan in 2.5 ± 1.5 min. The generated plans were judged clinically acceptable with dose distribution comparable with those of the clinical plans. CONCLUSIONS The proposed method can generate clinically acceptable plans quickly with high accuracy in dose evaluation, and thus has a high potential for clinical use in SIBT.
Collapse
Affiliation(s)
- Zhuo Xiao
- Image Processing Center, Beihang University, Beijing, People's Republic of China
| | - Tianyu Xiong
- School of Physics, Beihang University, Beijing, People's Republic of China
| | - Lishen Geng
- School of Physics, Beihang University, Beijing, People's Republic of China
| | - Fugen Zhou
- Image Processing Center, Beihang University, Beijing, People's Republic of China
- Beijing Advanced Innovation Center for Biomedical Engineering, Beihang University, Beijing, People's Republic of China
| | - Bo Liu
- Image Processing Center, Beihang University, Beijing, People's Republic of China
- Beijing Advanced Innovation Center for Biomedical Engineering, Beihang University, Beijing, People's Republic of China
| | - Haitao Sun
- Department of Radiation Oncology, Peking University Third Hospital, Beijing, People's Republic of China
| | - Zhe Ji
- Department of Radiation Oncology, Peking University Third Hospital, Beijing, People's Republic of China
| | - Yuliang Jiang
- Department of Radiation Oncology, Peking University Third Hospital, Beijing, People's Republic of China
| | - Junjie Wang
- Department of Radiation Oncology, Peking University Third Hospital, Beijing, People's Republic of China
| | - Qiuwen Wu
- Department of Radiation Oncology, Duke University Medical Center, Durham, North Carolina, USA
| |
Collapse
|
10
|
Li Z, Yang Z, Lu J, Zhu Q, Wang Y, Zhao M, Li Z, Fu J. Deep learning-based dose map prediction for high-dose-rate brachytherapy. Phys Med Biol 2023; 68:175015. [PMID: 37589292 DOI: 10.1088/1361-6560/acecd2] [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: 03/27/2023] [Accepted: 08/02/2023] [Indexed: 08/18/2023]
Abstract
Background. Creating a clinically acceptable plan in the time-sensitive clinic workflow of brachytherapy is challenging. Deep learning-based dose prediction techniques have been reported as promising solutions with high efficiency and accuracy. However, current dose prediction studies mainly target EBRT which are inappropriate for brachytherapy, the model designed specifically for brachytherapy has not yet well-established.Purpose. To predict dose distribution in brachytherapy using a novel Squeeze and Excitation Attention Net (SE_AN) model.Method. We hypothesized the tracks of192Ir inside applicators are essential for brachytherapy dose prediction. To emphasize the applicator contribution, a novel SE module was integrated into a Cascaded UNet to recalibrate informative features and suppress less useful ones. The Cascaded UNet consists of two stacked UNets, with the first designed to predict coarse dose distribution and the second added for fine-tuning 250 cases including all typical clinical applicators were studied, including vaginal, tandem and ovoid, multi-channel, and free needle applicators. The developed SE_AN was subsequently compared to the classic UNet and classic Cascaded UNet (without SE module) models. The model performance was evaluated by comparing the predicted dose against the clinically approved plans using mean absolute error (MAE) of DVH metrics, includingD2ccandD90%.Results. The MAEs of DVH metrics demonstrated that SE_AN accurately predicted the dose with 0.37 ± 0.25 difference for HRCTVD90%, 0.23 ± 0.14 difference for bladderD2cc, and 0.28 ± 0.20 difference for rectumD2cc. In comparison studies, UNet achieved 0.34 ± 0.24 for HRCTV, 0.25 ± 0.20 for bladder, 0.25 ± 0.21 for rectum, and Cascaded UNet achieved 0.42 ± 0.31 for HRCTV, 0.24 ± 0.19 for bladder, 0.23 ± 0.19 for rectum.Conclusion. We successfully developed a method specifically for 3D brachytherapy dose prediction. Our model demonstrated comparable performance to clinical plans generated by experienced dosimetrists. The developed technique is expected to improve the standardization and quality control of brachytherapy treatment planning.
Collapse
Affiliation(s)
- Zhen Li
- Shanghai Sixth People's Hospital, Shanghai, People's Republic of China
| | - Zhenyu Yang
- Duke University, Durham, NC, United States of America
| | - Jiayu Lu
- Boston University, Boston, MA, United States of America
| | - Qingyuan Zhu
- Shanghai Sixth People's Hospital, Shanghai, People's Republic of China
| | - Yanxiao Wang
- Shanghai Sixth People's Hospital, Shanghai, People's Republic of China
| | - Mengli Zhao
- Shanghai Sixth People's Hospital, Shanghai, People's Republic of China
| | - Zhaobin Li
- Shanghai Sixth People's Hospital, Shanghai, People's Republic of China
| | - Jie Fu
- Shanghai Sixth People's Hospital, Shanghai, People's Republic of China
| |
Collapse
|
11
|
Zhao JZ, Ni R, Chow R, Rink A, Weersink R, Croke J, Raman S. Artificial intelligence applications in brachytherapy: A literature review. Brachytherapy 2023; 22:429-445. [PMID: 37248158 DOI: 10.1016/j.brachy.2023.04.003] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/02/2023] [Revised: 04/02/2023] [Accepted: 04/07/2023] [Indexed: 05/31/2023]
Abstract
PURPOSE Artificial intelligence (AI) has the potential to simplify and optimize various steps of the brachytherapy workflow, and this literature review aims to provide an overview of the work done in this field. METHODS AND MATERIALS We conducted a literature search in June 2022 on PubMed, Embase, and Cochrane for papers that proposed AI applications in brachytherapy. RESULTS A total of 80 papers satisfied inclusion/exclusion criteria. These papers were categorized as follows: segmentation (24), registration and image processing (6), preplanning (13), dose prediction and treatment planning (11), applicator/catheter/needle reconstruction (16), and quality assurance (10). AI techniques ranged from classical models such as support vector machines and decision tree-based learning to newer techniques such as U-Net and deep reinforcement learning, and were applied to facilitate small steps of a process (e.g., optimizing applicator selection) or even automate the entire step of the workflow (e.g., end-to-end preplanning). Many of these algorithms demonstrated human-level performance and offer significant improvements in speed. CONCLUSIONS AI has potential to augment, automate, and/or accelerate many steps of the brachytherapy workflow. We recommend that future studies adhere to standard reporting guidelines. We also stress the importance of using larger sample sizes and reporting results using clinically interpretable measures.
Collapse
Affiliation(s)
- Jonathan Zl Zhao
- Princess Margaret Hospital Cancer Centre, Radiation Medicine Program, Toronto, Canada; Temerty Faculty of Medicine, University of Toronto, Toronto, Canada
| | - Ruiyan Ni
- Princess Margaret Hospital Cancer Centre, Radiation Medicine Program, Toronto, Canada; Department of Medical Biophysics, University of Toronto, Toronto, Canada
| | - Ronald Chow
- Princess Margaret Hospital Cancer Centre, Radiation Medicine Program, Toronto, Canada; Temerty Faculty of Medicine, University of Toronto, Toronto, Canada; Institute of Biomedical Engineering, University of Toronto, Toronto, Canada
| | - Alexandra Rink
- Princess Margaret Hospital Cancer Centre, Radiation Medicine Program, Toronto, Canada; Department of Radiation Oncology, University of Toronto, Toronto, Canada; Department of Medical Biophysics, University of Toronto, Toronto, Canada
| | - Robert Weersink
- Princess Margaret Hospital Cancer Centre, Radiation Medicine Program, Toronto, Canada; Department of Radiation Oncology, University of Toronto, Toronto, Canada; Department of Medical Biophysics, University of Toronto, Toronto, Canada; Institute of Biomedical Engineering, University of Toronto, Toronto, Canada
| | - Jennifer Croke
- Princess Margaret Hospital Cancer Centre, Radiation Medicine Program, Toronto, Canada; Department of Radiation Oncology, University of Toronto, Toronto, Canada
| | - Srinivas Raman
- Princess Margaret Hospital Cancer Centre, Radiation Medicine Program, Toronto, Canada; Department of Radiation Oncology, University of Toronto, Toronto, Canada.
| |
Collapse
|
12
|
Kallis K, Moore LC, Cortes KG, Brown D, Mayadev J, Moore KL, Meyers SM. Automated treatment planning framework for brachytherapy of cervical cancer using 3D dose predictions. Phys Med Biol 2023; 68:10.1088/1361-6560/acc37c. [PMID: 36898161 PMCID: PMC10101723 DOI: 10.1088/1361-6560/acc37c] [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: 12/05/2022] [Accepted: 03/10/2023] [Indexed: 03/12/2023]
Abstract
Objective. To lay the foundation for automated knowledge-based brachytherapy treatment planning using 3D dose estimations, we describe an optimization framework to convert brachytherapy dose distributions directly into dwell times (DTs).Approach. A dose rate kernelḋ(r,θ,φ)was produced by exporting 3D dose for one dwell position from the treatment planning system and normalizing by DT. By translating and rotating this kernel to each dwell position, scaling by DT and summing over all dwell positions, dose was computed (Dcalc). We used a Python-coded COBYLA optimizer to iteratively determine the DTs that minimize the mean squared error betweenDcalcand reference doseDref, computed using voxels withDref80%-120% of prescription. As validation of the optimization, we showed that the optimizer replicates clinical plans whenDref= clinical dose in 40 patients treated with tandem-and-ovoid (T&O) or tandem-and-ring (T&R) and 0-3 needles. Then we demonstrated automated planning in 10 T&O usingDref= dose predicted from a convolutional neural network developed in past work. Validation and automated plans were compared to clinical plans using mean absolute differences (MAD=1N∑n=1Nabsxn-xn') over all voxels (xn= Dose,N= #voxels) and DTs (xn= DT,N= #dwell positions), mean differences (MD) in organD2ccand high-risk CTV D90 over all patients (where positive indicates higher clinical dose), and mean Dice similarity coefficients (DSC) for 100% isodose contours.Main results. Validation plans agreed well with clinical plans (MADdose= 1.1%, MADDT= 4 s or 0.8% of total plan time,D2ccMD = -0.2% to 0.2% and D90 MD = -0.6%, DSC = 0.99). For automated plans, MADdose= 6.5% and MADDT= 10.3 s (2.1%). The slightly higher clinical metrics in automated plans (D2ccMD = -3.8% to 1.3% and D90 MD = -5.1%) were due to higher neural network dose predictions. The overall shape of the automated dose distributions were similar to clinical doses (DSC = 0.91).Significance. Automated planning with 3D dose predictions could provide significant time savings and standardize treatment planning across practitioners, regardless of experience.
Collapse
Affiliation(s)
- Karoline Kallis
- Department of Radiation Medicine and Applied Sciences, University of California, San Diego, La Jolla, CA, United States of America
| | - Lance C Moore
- Department of Radiation Medicine and Applied Sciences, University of California, San Diego, La Jolla, CA, United States of America
| | - Katherina G Cortes
- Department of Radiation Medicine and Applied Sciences, University of California, San Diego, La Jolla, CA, United States of America
| | - Derek Brown
- Department of Radiation Medicine and Applied Sciences, University of California, San Diego, La Jolla, CA, United States of America
| | - Jyoti Mayadev
- Department of Radiation Medicine and Applied Sciences, University of California, San Diego, La Jolla, CA, United States of America
| | - Kevin L Moore
- Department of Radiation Medicine and Applied Sciences, University of California, San Diego, La Jolla, CA, United States of America
| | - Sandra M Meyers
- Department of Radiation Medicine and Applied Sciences, University of California, San Diego, La Jolla, CA, United States of America
| |
Collapse
|
13
|
Salehi M, Vafaei Sadr A, Mahdavi SR, Arabi H, Shiri I, Reiazi R. Deep Learning-based Non-rigid Image Registration for High-dose Rate Brachytherapy in Inter-fraction Cervical Cancer. J Digit Imaging 2023; 36:574-587. [PMID: 36417026 PMCID: PMC10039214 DOI: 10.1007/s10278-022-00732-6] [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: 09/29/2021] [Revised: 07/04/2022] [Accepted: 07/18/2022] [Indexed: 11/25/2022] Open
Abstract
In this study, an inter-fraction organ deformation simulation framework for the locally advanced cervical cancer (LACC), which considers the anatomical flexibility, rigidity, and motion within an image deformation, was proposed. Data included 57 CT scans (7202 2D slices) of patients with LACC randomly divided into the train (n = 42) and test (n = 15) datasets. In addition to CT images and the corresponding RT structure (bladder, cervix, and rectum), the bone was segmented, and the coaches were eliminated. The correlated stochastic field was simulated using the same size as the target image (used for deformation) to produce the general random deformation. The deformation field was optimized to have a maximum amplitude in the rectum region, a moderate amplitude in the bladder region, and an amplitude as minimum as possible within bony structures. The DIRNet is a convolutional neural network that consists of convolutional regressors, spatial transformation, as well as resampling blocks. It was implemented by different parameters. Mean Dice indices of 0.89 ± 0.02, 0.96 ± 0.01, and 0.93 ± 0.02 were obtained for the cervix, bladder, and rectum (defined as at-risk organs), respectively. Furthermore, a mean average symmetric surface distance of 1.61 ± 0.46 mm for the cervix, 1.17 ± 0.15 mm for the bladder, and 1.06 ± 0.42 mm for the rectum were achieved. In addition, a mean Jaccard of 0.86 ± 0.04 for the cervix, 0.93 ± 0.01 for the bladder, and 0.88 ± 0.04 for the rectum were observed on the test dataset (15 subjects). Deep learning-based non-rigid image registration is, therefore, proposed for the high-dose-rate brachytherapy in inter-fraction cervical cancer since it outperformed conventional algorithms.
Collapse
Affiliation(s)
- Mohammad Salehi
- Department of Medical Physics, School of Medicine, Iran University of Medical Sciences, Tehran, Iran
| | - Alireza Vafaei Sadr
- Department of Theoretical Physics and Center for Astroparticle Physics, University of Geneva, Geneva, Switzerland
- Institute of Pathology, RWTH Aachen University Hospital, Aachen, Germany
| | - Seied Rabi Mahdavi
- Department of Medical Physics, School of Medicine, Iran University of Medical Sciences, Tehran, Iran
| | - Hossein Arabi
- Division of Nuclear Medicine and Molecular Imaging, Geneva University Hospital, CH-1211, Geneva 4, Switzerland
| | - Isaac Shiri
- Division of Nuclear Medicine and Molecular Imaging, Geneva University Hospital, CH-1211, Geneva 4, Switzerland.
| | - Reza Reiazi
- Department of Medical Physics, School of Medicine, Iran University of Medical Sciences, Tehran, Iran.
- Division of Radiation Oncology, Department of Radiation Physics, University of Texas MD Anderson Cancer Center, Houston, USA.
| |
Collapse
|
14
|
|
15
|
Shiri I, Arabi H, Salimi Y, Sanaat A, Akhavanallaf A, Hajianfar G, Askari D, Moradi S, Mansouri Z, Pakbin M, Sandoughdaran S, Abdollahi H, Radmard AR, Rezaei‐Kalantari K, Ghelich Oghli M, Zaidi H. COLI-Net: Deep learning-assisted fully automated COVID-19 lung and infection pneumonia lesion detection and segmentation from chest computed tomography images. INTERNATIONAL JOURNAL OF IMAGING SYSTEMS AND TECHNOLOGY 2022; 32:12-25. [PMID: 34898850 PMCID: PMC8652855 DOI: 10.1002/ima.22672] [Citation(s) in RCA: 9] [Impact Index Per Article: 4.5] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 06/10/2021] [Revised: 09/18/2021] [Accepted: 10/17/2021] [Indexed: 05/17/2023]
Abstract
We present a deep learning (DL)-based automated whole lung and COVID-19 pneumonia infectious lesions (COLI-Net) detection and segmentation from chest computed tomography (CT) images. This multicenter/multiscanner study involved 2368 (347'259 2D slices) and 190 (17 341 2D slices) volumetric CT exams along with their corresponding manual segmentation of lungs and lesions, respectively. All images were cropped, resized, and the intensity values clipped and normalized. A residual network with non-square Dice loss function built upon TensorFlow was employed. The accuracy of lung and COVID-19 lesions segmentation was evaluated on an external reverse transcription-polymerase chain reaction positive COVID-19 dataset (7'333 2D slices) collected at five different centers. To evaluate the segmentation performance, we calculated different quantitative metrics, including radiomic features. The mean Dice coefficients were 0.98 ± 0.011 (95% CI, 0.98-0.99) and 0.91 ± 0.038 (95% CI, 0.90-0.91) for lung and lesions segmentation, respectively. The mean relative Hounsfield unit differences were 0.03 ± 0.84% (95% CI, -0.12 to 0.18) and -0.18 ± 3.4% (95% CI, -0.8 to 0.44) for the lung and lesions, respectively. The relative volume difference for lung and lesions were 0.38 ± 1.2% (95% CI, 0.16-0.59) and 0.81 ± 6.6% (95% CI, -0.39 to 2), respectively. Most radiomic features had a mean relative error less than 5% with the highest mean relative error achieved for the lung for the range first-order feature (-6.95%) and least axis length shape feature (8.68%) for lesions. We developed an automated DL-guided three-dimensional whole lung and infected regions segmentation in COVID-19 patients to provide fast, consistent, robust, and human error immune framework for lung and pneumonia lesion detection and quantification.
Collapse
Affiliation(s)
- Isaac Shiri
- Division of Nuclear Medicine and Molecular ImagingGeneva University HospitalGenevaSwitzerland
| | - Hossein Arabi
- Division of Nuclear Medicine and Molecular ImagingGeneva University HospitalGenevaSwitzerland
| | - Yazdan Salimi
- Division of Nuclear Medicine and Molecular ImagingGeneva University HospitalGenevaSwitzerland
| | - Amirhossein Sanaat
- Division of Nuclear Medicine and Molecular ImagingGeneva University HospitalGenevaSwitzerland
| | - Azadeh Akhavanallaf
- Division of Nuclear Medicine and Molecular ImagingGeneva University HospitalGenevaSwitzerland
| | - Ghasem Hajianfar
- Rajaie Cardiovascular Medical and Research CenterIran University of Medical SciencesTehranIran
| | - Dariush Askari
- Department of Radiology TechnologyShahid Beheshti University of Medical SciencesTehranIran
| | - Shakiba Moradi
- Research and Development DepartmentMed Fanavaran Plus Co.KarajIran
| | - Zahra Mansouri
- Division of Nuclear Medicine and Molecular ImagingGeneva University HospitalGenevaSwitzerland
| | - Masoumeh Pakbin
- Clinical Research Development CenterQom University of Medical SciencesQomIran
| | - Saleh Sandoughdaran
- Men's Health and Reproductive Health Research CenterShahid Beheshti University of Medical SciencesTehranIran
| | - Hamid Abdollahi
- Department of Radiologic Technology, Faculty of Allied MedicineKerman University of Medical SciencesKermanIran
| | - Amir Reza Radmard
- Department of RadiologyShariati Hospital, Tehran University of Medical SciencesTehranIran
| | - Kiara Rezaei‐Kalantari
- Rajaie Cardiovascular Medical and Research CenterIran University of Medical SciencesTehranIran
| | - Mostafa Ghelich Oghli
- Research and Development DepartmentMed Fanavaran Plus Co.KarajIran
- Department of Cardiovascular SciencesKU LeuvenLeuvenBelgium
| | - Habib Zaidi
- Division of Nuclear Medicine and Molecular ImagingGeneva University HospitalGenevaSwitzerland
- Geneva University NeurocenterGeneva UniversityGenevaSwitzerland
- Department of Nuclear Medicine and Molecular ImagingUniversity of Groningen, University Medical Center GroningenGroningenNetherlands
- Department of Nuclear MedicineUniversity of Southern DenmarkOdenseDenmark
| |
Collapse
|