نوع مقاله : مقاله پژوهشی
نویسندگان
1 دانشکده مهندسی انرژی، دانشگاه صنعتی شریف، صندوقپستی: 14565-1114، تهران - ایران
2 بخش پزشکی هستهای و تصویربرداری مولکولی، گروه تصویربرداری پزشکی، بیمارستان ژنو، ژنو- سوئیس
چکیده
طراحی پرتودرمانی نیازمند شناسایی و قطعهبندی دقیق اندامهای در معرض خطر (OAR) است، که بهطور معمول عملیاتی دستی و زمانبر میباشد. هدف از این پژوهش، بررسی امکان استفاده از الگوریتمهای یادگیری عمیق بهعنوان ابزاری خودکار برای قطعهبندی تصاویر سیتیاسکن است. از اینرو عملکرد چند شبکه عصبی کانولوشنال (CNN) شامل U-Net، Residual U-Net و SegResNet بهعنوان ابزارهای قطعهبندی خودکار اندامهای در معرض خطر در تصاویر سیتیاسکن لگنی (مثانه، پروستات، رکتوم، استخوان فمورال چپ و استخوان فمورال راست) با قطعهبندی دستی توسط متخصص مقایسه شد. این مطالعه، شامل 238 بیمار برای قطعهبندی پروستات و 218 بیمار برای چهار اعضای دیگر بود. عملکرد مدلها با استفاده از معیارهایی نظیر ضریب شباهت دایس، شاخص ژاکارد و معیار فاصله هاسدورف ارزیابی شد. مدل SegResNet با ارائه بهترین عملکرد، توانست به ضریب دایس 0/956، 0/832، 0/864، 0/980 و 0/985 بهترتیب برای مثانه، پروستات، رکتوم، فمورال چپ و فمورال راست دست یابد. بهطور خلاصه، نتایج حاصله نشانمیدهد که شبکههای عصبی کانولوشنال در عین حال که میتوانند قطعهبندی اعضای در معرض خطر در طراحی پرتودرمانی را با دقت بالایی انجام دهند (استخوانها و مثانه بالاتر از 95درصد و رکتوم و پروستات بالای 83درصد)، فرایند قطعهبندی را نیز تسریع میبخشند.
کلیدواژهها
عنوان مقاله [English]
An investigation of deep learning techniques for automatic pelvic CT scan segmentation
نویسندگان [English]
- E. Ghaedi 1
- A. Asadi 1
- S.A. Hosseini 1
- H. Arabi 2
1 Department of Energy Engineering, Sharif University of Technology, P.O.BOX: 1114-14565, Tehran – Iran
2 Department of Nuclear Medicine and Molecular Imaging, Department of Medical Imaging Geneva University Hospital, Geneva – Switzerland
چکیده [English]
Radiotherapy treatment planning requires accurate delineation of organs at risk (OAR), which is typically a manual and time-consuming process. This research aims to explore the feasibility of using deep learning algorithms as an automatic tool for segmenting CT scan images. Accordingly, the performance of several convolutional neural networks (CNNs), including U-Net, Residual U-Net, and SegResNet, was compared as tools for automatic segmentation of OARs in pelvic CT scans (bladder, prostate, rectum, left femoral head, and right femoral head) against manual segmentation by specialists. This study involved 238 patients for prostate segmentation and 218 patients for the other four organs. The models' performance was assessed using metrics such as the Dice similarity coefficient, Jaccard index, and Hausdorff distance. The SegResNet model, providing the best performance, achieved Dice coefficients of 0.956, 0.832, 0.864, 0.980, and 0.985 for the bladder, prostate, rectum, left femoral head, and right femoral head, respectively. In summary, the results indicate that convolutional neural networks can accurately segment organs at risk in radiotherapy planning, with accuracies above 95% for bones and bladder, and over 83% for the rectum and prostate, while also speeding up the segmentation process.
کلیدواژهها [English]
- Segmentation
- Organs at risk
- Convolutional neural networks
- CT scan
- Prostate
- Sung H. Global cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA: a cancer journal for clinicians. 2021;71(3):209-249.
- Delaney G, Jacob S, Featherstone C, Barton M. The role of radiotherapy in cancer treatment: estimating optimal utilization from a review of evidence‐based clinical guidelines. Cancer: Interdisciplinary International Journal of the American Cancer Society. 2005;104(6):1129-1137.
- Liu Z, Liu X, Xiao B, Wang S, Miao Z, Sun Y, Zhang F. Segmentation of organs-at-risk in cervical cancer CT images with a convolutional neural network. Physica Medica. 2020;69:184-191.
- Wang S, He K, Nie D, Zhou S, Gao Y, Shen D. CT male pelvic organ segmentation using fully convolutional networks with boundary sensitive representation. Medical image analysis. 2019;54:168-178.
- Yazdanpanah F, Houshi S, Hosseini M, Bagherieh S, Ebrahimian Sadabad F, Nejati S.F, Arabi H, Zangiabadian M, Subtirelu R, Teichner E, Werner Th, Alavi A, Revheim M.E. Machine learning based radiomics features of theranostics PET features in detection of Prostate cancer (PCa): A systematic review of 1703 patients. ed: Soc Nuclear Med. 2023.
- Bagheri H. Mahdavi S.R, Geramifar P, Neshasteh-Riz A, Sajadi Rad M, Dadgar H, Arabi H, Zaidi H. An Update on the Role of mpMRI and 68Ga-PSMA PET Imaging in Primary and Recurrent Prostate Cancer. Clinical genitourinary cancer. 2024;102076.
- Ibragimov B, Xing L. Segmentation of organs‐at‐risks in head and neck CT images using convolutional neural networks. Medical physics. 2017;44(2):547-557.
- Men K, Dai J, Li Y. Automatic segmentation of the clinical target volume and organs at risk in the planning CT for rectal cancer using deep dilated convolutional neural networks. Medical physics. 2017;44(12):6377-6389.
- Wang J, Lu J, Qin G, Shen L, Sun Y, Ying H, Zhang Z, Hu W. A deep learning‐based autosegmentation of rectal tumors in MR images. Medical physics. 2018;45(6):2560-2564.
- Arabi H, Dowling J.A, Burgos N, Han X, Greer P.B, Koutsouvelis N, Zaidi H. Comparative study of algorithms for synthetic CT generation from MRI: consequences for MRI‐guided radiation planning in the pelvic region. Medical physics. 2018;45(11):5218-5233.
- Schreier J, Genghi A, Laaksonen H, Morgas T, Haas B. Clinical evaluation of a full-image deep segmentation algorithm for the male pelvis on cone-beam CT and CT. Radiotherapy and Oncology. 2020;145:1-6.
- Arabi H, Koutsouvelis N, Rouzaud M, Miralbell R, Zaidi H. Atlas-guided generation of pseudo-CT images for MRI-only and hybrid PET–MRI-guided radiotherapy treatment planning. Physics in Medicine & Biology. 2016;61(17):6531.
- Arabi H, Zaidi H. Applications of artificial intelligence and deep learning in molecular imaging and radiotherapy. European Journal of Hybrid Imaging. 2020;4(1):17.
- Karimzadeh R, Fatemizadeh E, Arabi H. Attention-based deep learning segmentation: Application to brain tumor delineation. in 2021 28th National and 6th International Iranian Conference on Biomedical Engineering (ICBME). IEEE. 2021;248-252.
- Kiljunen T, Akram S, Niemelä J, Löyttyniemi E, Seppälä J, Heikkilä J, Vuolukka K, Kääriäinen O.S, Heikkilä V.P, Lehtiö K, Nikkinen J, Gershkevitsh E, Borkvel A, Adamson M, Zolotuhhin D, Kolk K, Pei Ping Pang E, Tuan J.K.L, Master Z, Chua M.L.K , Joensuu T, Kononen J, Myllykangas M, Riener M, Mokka M, Keyriläinen J. A deep learning-based automated CT segmentation of prostate cancer anatomy for radiation therapy planning-a retrospective multicenter study. Diagnostics. 2020;10(11):959.
- Balagopal A, Kazemifar S, Nguyen D, Lin M.H, Hannan R, Owrangi A, Jiang S. Fully automated organ segmentation in male pelvic CT images. Physics in Medicine & Biology. 2018;63(24):245015.
- Lei Y, Wang T, Tian S, Fu Y, Patel P, Jani A.B, Curran W.J, Liu T, Yang X. Male pelvic CT multi-organ segmentation using synthetic MRI-aided dual pyramid networks. Physics in Medicine & Biology. 2021;66(8):085007.
- Gibbons E, Hoffmann M, Westhuyzen J, Hodgson A, Chick B, Last A. Clinical evaluation of deep learning and atlas‐based auto‐segmentation for critical organs at risk in radiation therapy. Journal of Medical Radiation Sciences. 2023;70:15-25.
- Mofid B, Mosalla S.M.M, Goodarzi M, Tavakoli H. Deep CNN-based Fully Automated Segmentation of Pelvic Multi-Organ on CT Images for Prostate Cancer Radiotherapy. Journal of Biomedical Physics and Engineering. 2024.
- Wong J, Huang V, Wells D, Giambattista J, Giambattista J, Kolbeck C, Otto K, Implementation of deep learning-based auto-segmentation for radiotherapy planning structures: a workflow study at two cancer centers. Radiation Oncology. 2021;16(1):101.
- Ronneberger O, Fischer P, Brox T. U-net: Convolutional networks for biomedical image segmentation. in Medical image computing and computer-assisted intervention–MICCAI 2015: 18th international conference, Munich, Germany, October 5-9, 2015, proceedings, part III 18, 2015;234-241. Springer.
- Zhang Z, Liu Q, Wang Y. Road extraction by deep residual u-net. IEEE Geoscience and Remote Sensing Letters. 2018;15(5):749-753.
- Myronenko A. 3D MRI brain tumor segmentation using autoencoder regularization. in Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries: 4th International Workshop, BrainLes 2018, Held in Conjunction with MICCAI 2018, Granada, Spain, September 16, 2018, Revised Selected Papers, Part II 4, 2019;311-320. Springer.
- Luo X, Liao W, Xiao J, Chen J, Song J, Zhang X, Li K, Metaxas D.N, Wang G, Zhang S. WORD: A large scale dataset, benchmark and clinical applicable study for abdominal organ segmentation from CT image. arXiv preprint arXiv:2111.02403. 2021.
- Ji Y, Bai H, Ge C, Yang J, Zhu Y, Zhang R, Li Z, Zhanng L, Ma W, Wan X, Luo P. Amos: A large-scale abdominal multi-organ benchmark for versatile medical image segmentation. Advances in Neural Information Processing Systems. 2022;35:36722-36732.
- He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. in Proceedings of the IEEE conference on computer vision and pattern recognition. 2016;770-778.
- Gholamiankhah F, Mostafapour S, Arabi H. Deep learning-based synthetic CT generation from MR images: comparison of generative adversarial and residual neural networks. arXiv preprint arXiv:2103.01609. 2021.
- Abdelhafiz D, Bi J, Ammar R, Yang C, Nabavi S. Convolutional neural network for automated mass segmentation in mammography. BMC bioinformatics. 2020;21:1-19.
- Bertels J, Eelbode T, Berman M, Vandermeulen D, Maes F, Bisschops R, Blaschko M.B. Optimizing the dice score and jaccard index for medical image segmentation: Theory and practice. in Medical Image Computing and Computer Assisted Intervention–MICCAI 2019: 22nd International Conference, Shenzhen, China, October 13–17 2019, Proceedings, Part II 22, 2019;92-100. Springer.
- Zhang D, Yang Z, Jiang S, Zhou Z, Meng M, Wang W. Automatic segmentation and applicator reconstruction for CT‐based brachytherapy of cervical cancer using 3D convolutional neural networks. Journal of Applied Clinical Medical Physics. 2020;21(10):158-169.
- Wang Z, Chang Y, Peng Z, Lv Y, Shi W, Wang F, Pei X, Xu X.G. Evaluation of deep learning‐based auto‐segmentation algorithms for delineating clinical target volume and organs at risk involving data for 125 cervical cancer patients. Journal of Applied Clinical Medical Physics. 2020;21(12):272-279