1
|
Wen F, Chen Z, Wang X, Dou M, Yang J, Yao Y, Shen Y. Deep learning based clinical target volumes contouring for prostate cancer: Easy and efficient application. J Appl Clin Med Phys 2024:e14482. [PMID: 39120487 DOI: 10.1002/acm2.14482] [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: 12/06/2023] [Revised: 05/30/2024] [Accepted: 07/09/2024] [Indexed: 08/10/2024] Open
Abstract
BACKGROUND Radiotherapy has been crucial in prostate cancer treatment. However, manual segmentation is labor intensive and highly variable among radiation oncologists. In this study, a deep learning based automated contouring model is constructed for clinical target volumes (CTVs) of intact and postoperative prostate cancer. METHODS Computed tomography (CT) data sets of 197 prostate cancer patients were collected. Two auto-delineation models were built for radical radiotherapy and postoperative radiotherapy of prostate cancer respectively, and each model included CTVn for pelvic lymph nodes and CTVp for prostate tumors or prostate tumor beds. RESULTS In the radical radiotherapy model, the volumetric dice (VD) coefficient of CTVn calculated by AI, was higher than that of the one delineated by the junior physicians (0.85 vs. 0.82, p = 0.018); In the postoperative radiotherapy model, the quantitative parameter of CTVn and CTVp, counted by AI, was better than that of the junior physicians. The median delineation time for AI was 0.23 min in the postoperative model and 0.26 min in the radical model, which were significantly shorter than those of the physicians (50.40 and 45.43 min, respectively, p < 0.001). The correction time of the senior physician for AI was much shorter compared with that for the junior physicians in both models (p < 0.001). CONCLUSION Using deep learning and attention mechanism, a highly consistent and time-saving contouring model was built for CTVs of pelvic lymph nodes and prostate tumors or prostate tumor beds for prostate cancer, which also might be a good approach to train junior radiation oncologists.
Collapse
Affiliation(s)
- Feng Wen
- Department of Radiation Oncology, Cancer Center, West China Hospital, Sichuan University, Chengdu, China
- Abdominal Oncology Ward, Cancer Center, West China Hospital, Sichuan University, Chengdu, China
| | - Zhebin Chen
- Chengdu Institute of Computer Application, Chinese Academy of Sciences, Sichuan, Chengdu, China
- University of Chinese Academy of Sciences, Beijing, China
| | - Xin Wang
- Department of Radiation Oncology, Cancer Center, West China Hospital, Sichuan University, Chengdu, China
- Abdominal Oncology Ward, Cancer Center, West China Hospital, Sichuan University, Chengdu, China
| | - Meng Dou
- Chengdu Institute of Computer Application, Chinese Academy of Sciences, Sichuan, Chengdu, China
- University of Chinese Academy of Sciences, Beijing, China
| | - Jialuo Yang
- Department of Medicine Oncology, Shifang people's Hospital, Shifang, China
| | - Yu Yao
- Chengdu Institute of Computer Application, Chinese Academy of Sciences, Sichuan, Chengdu, China
- University of Chinese Academy of Sciences, Beijing, China
| | - Yali Shen
- Department of Radiation Oncology, Cancer Center, West China Hospital, Sichuan University, Chengdu, China
- Abdominal Oncology Ward, Cancer Center, West China Hospital, Sichuan University, Chengdu, China
| |
Collapse
|
2
|
Rouvière O, Moldovan PC, Vlachomitrou A, Gouttard S, Riche B, Groth A, Rabotnikov M, Ruffion A, Colombel M, Crouzet S, Weese J, Rabilloud M. Combined model-based and deep learning-based automated 3D zonal segmentation of the prostate on T2-weighted MR images: clinical evaluation. Eur Radiol 2022; 32:3248-3259. [PMID: 35001157 DOI: 10.1007/s00330-021-08408-5] [Citation(s) in RCA: 6] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/06/2021] [Revised: 09/28/2021] [Accepted: 10/09/2021] [Indexed: 11/04/2022]
Abstract
OBJECTIVE To train and to test for prostate zonal segmentation an existing algorithm already trained for whole-gland segmentation. METHODS The algorithm, combining model-based and deep learning-based approaches, was trained for zonal segmentation using the NCI-ISBI-2013 dataset and 70 T2-weighted datasets acquired at an academic centre. Test datasets were randomly selected among examinations performed at this centre on one of two scanners (General Electric, 1.5 T; Philips, 3 T) not used for training. Automated segmentations were corrected by two independent radiologists. When segmentation was initiated outside the prostate, images were cropped and segmentation repeated. Factors influencing the algorithm's mean Dice similarity coefficient (DSC) and its precision were assessed using beta regression. RESULTS Eighty-two test datasets were selected; one was excluded. In 13/81 datasets, segmentation started outside the prostate, but zonal segmentation was possible after image cropping. Depending on the radiologist chosen as reference, algorithm's median DSCs were 96.4/97.4%, 91.8/93.0% and 79.9/89.6% for whole-gland, central gland and anterior fibromuscular stroma (AFMS) segmentations, respectively. DSCs comparing radiologists' delineations were 95.8%, 93.6% and 81.7%, respectively. For all segmentation tasks, the scanner used for imaging significantly influenced the mean DSC and its precision, and the mean DSC was significantly lower in cases with initial segmentation outside the prostate. For central gland segmentation, the mean DSC was also significantly lower in larger prostates. The radiologist chosen as reference had no significant impact, except for AFMS segmentation. CONCLUSIONS The algorithm performance fell within the range of inter-reader variability but remained significantly impacted by the scanner used for imaging. KEY POINTS • Median Dice similarity coefficients obtained by the algorithm fell within human inter-reader variability for the three segmentation tasks (whole gland, central gland, anterior fibromuscular stroma). • The scanner used for imaging significantly impacted the performance of the automated segmentation for the three segmentation tasks. • The performance of the automated segmentation of the anterior fibromuscular stroma was highly variable across patients and showed also high variability across the two radiologists.
Collapse
Affiliation(s)
- Olivier Rouvière
- Department of Urinary and Vascular Imaging, Hôpital Edouard Herriot, Hospices Civils de Lyon, Pavillon B, 5 place d'Arsonval, F-69437, Lyon, France. .,Université de Lyon, F-69003, Lyon, France. .,Faculté de Médecine Lyon Est, Université Lyon 1, F-69003, Lyon, France. .,INSERM, LabTau, U1032, Lyon, France.
| | - Paul Cezar Moldovan
- Department of Urinary and Vascular Imaging, Hôpital Edouard Herriot, Hospices Civils de Lyon, Pavillon B, 5 place d'Arsonval, F-69437, Lyon, France
| | - Anna Vlachomitrou
- Philips France, 33 rue de Verdun, CS 60 055, 92156, Suresnes Cedex, France
| | - Sylvain Gouttard
- Department of Urinary and Vascular Imaging, Hôpital Edouard Herriot, Hospices Civils de Lyon, Pavillon B, 5 place d'Arsonval, F-69437, Lyon, France
| | - Benjamin Riche
- Service de Biostatistique Et Bioinformatique, Pôle Santé Publique, Hospices Civils de Lyon, F-69003, Lyon, France.,Laboratoire de Biométrie Et Biologie Évolutive, Équipe Biostatistique-Santé, UMR 5558, CNRS, F-69100, Villeurbanne, France
| | - Alexandra Groth
- Philips Research, Röntgenstrasse 24-26, 22335, Hamburg, Germany
| | | | - Alain Ruffion
- Department of Urology, Centre Hospitalier Lyon Sud, Hospices Civils de Lyon, F-69310, Pierre-Bénite, France
| | - Marc Colombel
- Université de Lyon, F-69003, Lyon, France.,Faculté de Médecine Lyon Est, Université Lyon 1, F-69003, Lyon, France.,Department of Urology, Hôpital Edouard Herriot, Hospices Civils de Lyon, F-69437, Lyon, France
| | - Sébastien Crouzet
- Department of Urology, Hôpital Edouard Herriot, Hospices Civils de Lyon, F-69437, Lyon, France
| | - Juergen Weese
- Philips Research, Röntgenstrasse 24-26, 22335, Hamburg, Germany
| | - Muriel Rabilloud
- Université de Lyon, F-69003, Lyon, France.,Faculté de Médecine Lyon Est, Université Lyon 1, F-69003, Lyon, France.,Service de Biostatistique Et Bioinformatique, Pôle Santé Publique, Hospices Civils de Lyon, F-69003, Lyon, France.,Laboratoire de Biométrie Et Biologie Évolutive, Équipe Biostatistique-Santé, UMR 5558, CNRS, F-69100, Villeurbanne, France
| |
Collapse
|
3
|
Savenije MHF, Maspero M, Sikkes GG, van der Voort van Zyp JRN, T. J. Kotte AN, Bol GH, T. van den Berg CA. Clinical implementation of MRI-based organs-at-risk auto-segmentation with convolutional networks for prostate radiotherapy. Radiat Oncol 2020; 15:104. [PMID: 32393280 PMCID: PMC7216473 DOI: 10.1186/s13014-020-01528-0] [Citation(s) in RCA: 51] [Impact Index Per Article: 12.8] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/20/2020] [Accepted: 04/01/2020] [Indexed: 02/08/2023] Open
Abstract
BACKGROUND Structure delineation is a necessary, yet time-consuming manual procedure in radiotherapy. Recently, convolutional neural networks have been proposed to speed-up and automatise this procedure, obtaining promising results. With the advent of magnetic resonance imaging (MRI)-guided radiotherapy, MR-based segmentation is becoming increasingly relevant. However, the majority of the studies investigated automatic contouring based on computed tomography (CT). PURPOSE In this study, we investigate the feasibility of clinical use of deep learning-based automatic OARs delineation on MRI. MATERIALS AND METHODS We included 150 patients diagnosed with prostate cancer who underwent MR-only radiotherapy. A three-dimensional (3D) T1-weighted dual spoiled gradient-recalled echo sequence was acquired with 3T MRI for the generation of the synthetic-CT. The first 48 patients were included in a feasibility study training two 3D convolutional networks called DeepMedic and dense V-net (dV-net) to segment bladder, rectum and femurs. A research version of an atlas-based software was considered for comparison. Dice similarity coefficient, 95% Hausdorff distances (HD95), and mean distances were calculated against clinical delineations. For eight patients, an expert RTT scored the quality of the contouring for all the three methods. A choice among the three approaches was made, and the chosen approach was retrained on 97 patients and implemented for automatic use in the clinical workflow. For the successive 53 patients, Dice, HD95 and mean distances were calculated against the clinically used delineations. RESULTS DeepMedic, dV-net and the atlas-based software generated contours in 60 s, 4 s and 10-15 min, respectively. Performances were higher for both the networks compared to the atlas-based software. The qualitative analysis demonstrated that delineation from DeepMedic required fewer adaptations, followed by dV-net and the atlas-based software. DeepMedic was clinically implemented. After retraining DeepMedic and testing on the successive patients, the performances slightly improved. CONCLUSION High conformality for OARs delineation was achieved with two in-house trained networks, obtaining a significant speed-up of the delineation procedure. Comparison of different approaches has been performed leading to the succesful adoption of one of the neural networks, DeepMedic, in the clinical workflow. DeepMedic maintained in a clinical setting the accuracy obtained in the feasibility study.
Collapse
Affiliation(s)
- Mark H. F. Savenije
- Department of Radiotherapy, Division of Imaging & Oncology, University Medical Center Utrecht, Heidelberglaan 100, Utrecht, 3508 GA The Netherlands
- Computational Imaging Group for MR diagnostics & therapy, Center for Image Sciences, University Medical Center Utrecht, Heidelberglaan 100, Utrecht, 3508 GA The Netherlands
| | - Matteo Maspero
- Department of Radiotherapy, Division of Imaging & Oncology, University Medical Center Utrecht, Heidelberglaan 100, Utrecht, 3508 GA The Netherlands
- Computational Imaging Group for MR diagnostics & therapy, Center for Image Sciences, University Medical Center Utrecht, Heidelberglaan 100, Utrecht, 3508 GA The Netherlands
| | - Gonda G. Sikkes
- Department of Radiotherapy, Division of Imaging & Oncology, University Medical Center Utrecht, Heidelberglaan 100, Utrecht, 3508 GA The Netherlands
| | - Jochem R. N. van der Voort van Zyp
- Department of Radiotherapy, Division of Imaging & Oncology, University Medical Center Utrecht, Heidelberglaan 100, Utrecht, 3508 GA The Netherlands
| | - Alexis N. T. J. Kotte
- Department of Radiotherapy, Division of Imaging & Oncology, University Medical Center Utrecht, Heidelberglaan 100, Utrecht, 3508 GA The Netherlands
| | - Gijsbert H. Bol
- Department of Radiotherapy, Division of Imaging & Oncology, University Medical Center Utrecht, Heidelberglaan 100, Utrecht, 3508 GA The Netherlands
| | - Cornelis A. T. van den Berg
- Department of Radiotherapy, Division of Imaging & Oncology, University Medical Center Utrecht, Heidelberglaan 100, Utrecht, 3508 GA The Netherlands
- Computational Imaging Group for MR diagnostics & therapy, Center for Image Sciences, University Medical Center Utrecht, Heidelberglaan 100, Utrecht, 3508 GA The Netherlands
| |
Collapse
|
4
|
Wang B, Lei Y, Tian S, Wang T, Liu Y, Patel P, Jani AB, Mao H, Curran WJ, Liu T, Yang X. Deeply supervised 3D fully convolutional networks with group dilated convolution for automatic MRI prostate segmentation. Med Phys 2019; 46:1707-1718. [PMID: 30702759 DOI: 10.1002/mp.13416] [Citation(s) in RCA: 122] [Impact Index Per Article: 24.4] [Reference Citation Analysis] [Abstract] [Key Words] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/01/2018] [Revised: 01/18/2019] [Accepted: 01/24/2019] [Indexed: 12/15/2022] Open
Abstract
PURPOSE Reliable automated segmentation of the prostate is indispensable for image-guided prostate interventions. However, the segmentation task is challenging due to inhomogeneous intensity distributions, variation in prostate anatomy, among other problems. Manual segmentation can be time-consuming and is subject to inter- and intraobserver variation. We developed an automated deep learning-based method to address this technical challenge. METHODS We propose a three-dimensional (3D) fully convolutional networks (FCN) with deep supervision and group dilated convolution to segment the prostate on magnetic resonance imaging (MRI). In this method, a deeply supervised mechanism was introduced into a 3D FCN to effectively alleviate the common exploding or vanishing gradients problems in training deep models, which forces the update process of the hidden layer filters to favor highly discriminative features. A group dilated convolution which aggregates multiscale contextual information for dense prediction was proposed to enlarge the effective receptive field of convolutional neural networks, which improve the prediction accuracy of prostate boundary. In addition, we introduced a combined loss function including cosine and cross entropy, which measures similarity and dissimilarity between segmented and manual contours, to further improve the segmentation accuracy. Prostate volumes manually segmented by experienced physicians were used as a gold standard against which our segmentation accuracy was measured. RESULTS The proposed method was evaluated on an internal dataset comprising 40 T2-weighted prostate MR volumes. Our method achieved a Dice similarity coefficient (DSC) of 0.86 ± 0.04, a mean surface distance (MSD) of 1.79 ± 0.46 mm, 95% Hausdorff distance (95%HD) of 7.98 ± 2.91 mm, and absolute relative volume difference (aRVD) of 15.65 ± 10.82. A public dataset (PROMISE12) including 50 T2-weighted prostate MR volumes was also employed to evaluate our approach. Our method yielded a DSC of 0.88 ± 0.05, MSD of 1.02 ± 0.35 mm, 95% HD of 9.50 ± 5.11 mm, and aRVD of 8.93 ± 7.56. CONCLUSION We developed a novel deeply supervised deep learning-based approach with a group dilated convolution to automatically segment the MRI prostate, demonstrated its clinical feasibility, and validated its accuracy against manual segmentation. The proposed technique could be a useful tool for image-guided interventions in prostate cancer.
Collapse
Affiliation(s)
- Bo Wang
- Department of Radiation Oncology and Winship Cancer Institute, Emory University, Atlanta, GA, 30322, USA.,School of Physics and Electronic-Electrical Engineering, Ningxia University, Yinchuan, Ningxia, 750021, P.R. China
| | - Yang Lei
- Department of Radiation Oncology and Winship Cancer Institute, Emory University, Atlanta, GA, 30322, USA
| | - Sibo Tian
- Department of Radiation Oncology and Winship Cancer Institute, Emory University, Atlanta, GA, 30322, USA
| | - Tonghe Wang
- Department of Radiation Oncology and Winship Cancer Institute, Emory University, Atlanta, GA, 30322, USA
| | - Yingzi Liu
- Department of Radiation Oncology and Winship Cancer Institute, Emory University, Atlanta, GA, 30322, USA
| | - Pretesh Patel
- Department of Radiation Oncology and Winship Cancer Institute, Emory University, Atlanta, GA, 30322, USA
| | - Ashesh B Jani
- Department of Radiation Oncology and Winship Cancer Institute, Emory University, Atlanta, GA, 30322, USA
| | - Hui Mao
- Department of Radiology and Imaging Sciences and Winship Cancer Institute, Emory University, Atlanta, GA, 30322, USA
| | - Walter J Curran
- Department of Radiation Oncology and Winship Cancer Institute, Emory University, Atlanta, GA, 30322, USA
| | - Tian Liu
- Department of Radiation Oncology and Winship Cancer Institute, Emory University, Atlanta, GA, 30322, USA
| | - Xiaofeng Yang
- Department of Radiation Oncology and Winship Cancer Institute, Emory University, Atlanta, GA, 30322, USA
| |
Collapse
|
5
|
Kerkmeijer LGW, Maspero M, Meijer GJ, van der Voort van Zyp JRN, de Boer HCJ, van den Berg CAT. Magnetic Resonance Imaging only Workflow for Radiotherapy Simulation and Planning in Prostate Cancer. Clin Oncol (R Coll Radiol) 2018; 30:692-701. [PMID: 30244830 DOI: 10.1016/j.clon.2018.08.009] [Citation(s) in RCA: 42] [Impact Index Per Article: 7.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/07/2018] [Revised: 06/29/2018] [Accepted: 08/21/2018] [Indexed: 01/06/2023]
Abstract
Magnetic resonance imaging (MRI) is often combined with computed tomography (CT) in prostate radiotherapy to optimise delineation of the target and organs-at-risk (OAR) while maintaining accurate dose calculation. Such a dual-modality workflow requires two separate imaging sessions, and it has some fundamental and logistical drawbacks. Due to the availability of new MRI hardware and software solutions, CT examinations can be omitted for prostate radiotherapy simulations. All information for treatment planning, including electron density maps and bony anatomy, can nowadays be obtained with MRI. Such an MRI-only simulation workflow reduces delineation ambiguities, eases planning logistics, and improves patient comfort; however, careful validation of the complete MRI-only workflow is warranted. The first institutes are now adopting this MRI-only workflow for prostate radiotherapy. In this article, we will review technology and workflow requirements for an MRI-only prostate simulation workflow.
Collapse
Affiliation(s)
- L G W Kerkmeijer
- Department of Radiotherapy, University Medical Center Utrecht, The Netherlands.
| | - M Maspero
- Department of Radiotherapy, University Medical Center Utrecht, The Netherlands
| | - G J Meijer
- Department of Radiotherapy, University Medical Center Utrecht, The Netherlands
| | | | - H C J de Boer
- Department of Radiotherapy, University Medical Center Utrecht, The Netherlands
| | - C A T van den Berg
- Department of Radiotherapy, University Medical Center Utrecht, The Netherlands
| |
Collapse
|