Korean Journal of Radiology

  • 제22권12호
  • /
  • Pages.2073-2081
  • /
  • 2021
  • /
  • 1229-6929(pISSN)
  • /
  • 2005-8330(eISSN)
대한영상의학회 (The Korean Society of Radiology)
권호 표지
DOI QR코드

DOI QR Code

An Open Medical Platform to Share Source Code and Various Pre-Trained Weights for Models to Use in Deep Learning Research

  • Sungchul Kim (Department of Biomedical Engineering, Asan Medical Institute of Convergence Science and Technology, Asan Medical Center, University of Ulsan College of Medicine) ;
  • Sungman Cho (Asan Institute for Life Sciences, Asan Medical Center) ;
  • Kyungjin Cho (Department of Biomedical Engineering, Asan Medical Institute of Convergence Science and Technology, Asan Medical Center, University of Ulsan College of Medicine) ;
  • Jiyeon Seo (Department of Biomedical Engineering, Asan Medical Institute of Convergence Science and Technology, Asan Medical Center, University of Ulsan College of Medicine) ;
  • Yujin Nam (Department of Biomedical Engineering, Asan Medical Institute of Convergence Science and Technology, Asan Medical Center, University of Ulsan College of Medicine) ;
  • Jooyoung Park (Department of Biomedical Engineering, Asan Medical Institute of Convergence Science and Technology, Asan Medical Center, University of Ulsan College of Medicine) ;
  • Kyuri Kim (Asan Institute for Life Sciences, Asan Medical Center) ;
  • Daeun Kim (Asan Institute for Life Sciences, Asan Medical Center) ;
  • Jeongeun Hwang (Department of Medicine, Asan Medical Center, University of Ulsan College of Medicine) ;
  • Jihye Yun (Department of Radiology, Asan Medical Center, University of Ulsan College of Medicine) ;
  • Miso Jang (Department of Biomedical Engineering, Asan Medical Institute of Convergence Science and Technology, Asan Medical Center, University of Ulsan College of Medicine) ;
  • Hyunna Lee (Bigdata Research Center, Asan Institute for Life Science, Asan Medical Center) ;
  • Namkug Kim (Department of Radiology, Asan Medical Center, University of Ulsan College of Medicine)
  • 투고 : 2021.02.27
  • 심사 : 2021.08.01
  • 발행 : 2021.12.01
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

Deep learning-based applications have great potential to enhance the quality of medical services. The power of deep learning depends on open databases and innovation. Radiologists can act as important mediators between deep learning and medicine by simultaneously playing pioneering and gatekeeping roles. The application of deep learning technology in medicine is sometimes restricted by ethical or legal issues, including patient privacy and confidentiality, data ownership, and limitations in patient agreement. In this paper, we present an open platform, MI2RLNet, for sharing source code and various pre-trained weights for models to use in downstream tasks, including education, application, and transfer learning, to encourage deep learning research in radiology. In addition, we describe how to use this open platform in the GitHub environment. Our source code and models may contribute to further deep learning research in radiology, which may facilitate applications in medicine and healthcare, especially in medical imaging, in the near future. All code is available at https://github.com/mi2rl/MI2RLNet.

키워드

과제정보

All authors belong to Medical Imaging and Intelligent Reality Lab (MI2RL). We thank Dr. Yongsik Sim (Department of Radiology, Severance Hospital, Yonsei University College of Medicine, Seoul, Republic of Korea), for development of two models that chest radiographs view classification model and enhancement classification.

참고문헌

  1. Kennedy AD, Leigh-Brown AP, Torgerson DJ, Campbell J, Grant A. Resource use data by patient report or hospital records: do they agree? BMC Health Serv Res 2002;2:2
  2. Jiang F, Jiang Y, Zhi H, Dong Y, Li H, Ma S, et al. Artificial intelligence in healthcare: past, present and future. Stroke Vasc Neurol 2017;2:230-243
  3. Shen D, Wu G, Suk HI. Deep learning in medical image analysis. Annu Rev Biomed Eng 2017;19:221-248
  4. Hesamian MH, Jia W, He X, Kennedy P. Deep learning techniques for medical image segmentation: achievements and challenges. J Digit Imaging 2019;32:582-596
  5. Hwang EJ, Nam JG, Lim WH, Park SJ, Jeong YS, Kang JH, et al. Deep learning for chest radiograph diagnosis in the emergency department. Radiology 2019;293:573-580
  6. Weikert T, Rapaka S, Grbic S, Re T, Chaganti S, Winkel DJ, et al. Prediction of patient management in COVID-19 using deep learning-based fully automated extraction of cardiothoracic CT metrics and laboratory findings. Korean J Radiol 2021;22:994-1004
  7. Abouelmehdi K, Beni-Hessane A, Khaloufi H. Big healthcare data: preserving security and privacy. J Big Data 2018;5:1
  8. Lecun Y, Bottou L, Bengio Y, Haffner P. Gradient-based learning applied to document recognition. Proceedings of the IEEE 1998;86:2278-2324
  9. Deng J, Dong W, Socher R, Li L, Kai L, Fei-Fei L. ImageNet: a large-scale hierarchical image database. Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition; 2009 Jun 20-25; Miami, FL, USA: IEEE; 2009; p. 248-255
  10. Lin TY, Maire M, Belongie S, Hays J, Perona P, Ramanan D, et al. Microsoft coco: common objects in context. In: Fleet D, Pajdla T, Schiele B, Tuytelaars T, eds. Computer vision--ECCV 2014. Cham: Springer International Publishing, 2014:740-755
  11. Liu Z, Luo P, Wang X, Tang X. Deep learning face attributes in the wild. Proceedings of the IEEE International Conference on Computer Vision (ICCV); 2015 Dec 7-13; Washington, DC, USA: IEEE; 2015; p. 3730-3738
  12. Ke A, Ellsworth W, Banerjee O, Ng AY, Rajpurkar P. CheXtransfer: performance and parameter efficiency of ImageNet models for chest X-Ray interpretation. Proceedings of the Conference on Health, Inference, and Learning; 2021 Apr 8-10; Virtual: CHIL; 2021; p. 116-124
  13. Ronneberger O, Fischer P, Brox T. U-Net: convolutional networks for biomedical image segmentation. In: Navab N, Hornegger J, Wells W, Frangi A, eds. Medical image computing and computer-assisted intervention - MICCAI 2015. MICCAI 2015. Lecture notes in computer science, vol 9351. Cham: Springer, 2015:234-241
  14. Cicek O, Abdulkadir A, Lienkamp SS, Brox T, Ronneberger O. 3D U-Net: learning dense volumetric segmentation from sparse annotation. In: Ourselin S, Joskowicz L, Sabuncu M, Unal G, Wells W, eds. Medical image computing and computer-assisted intervention - MICCAI 2016. MICCAI 2016. Lecture notes in computer science, vol 9901. Cham: Springer, 2016:424-432
  15. He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR); 2016 Jun 27-30; Las Vegas, NV, USA: IEEE; 2016; p. 770-778
  16. Tan M, Pang R, Le QV. Efficientdet: scalable and efficient object detection. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR); 2020 Jun 13-19; Seattle, WA, USA: IEEE; 2020; p. 10778-10787
  17. Tan M, Le Q. Efficientnet: rethinking model scaling for convolutional neural networks. Proceedings of the 36th International Conference on Machine Learning; 2019 Jun 9-15; Long Beach, CA, USA: PMLR; 2019; p. 6105-6114
  18. Shiraishi J, Katsuragawa S, Ikezoe J, Matsumoto T, Kobayashi T, Komatsu K, et al. Development of a digital image database for chest radiographs with and without a lung nodule: receiver operating characteristic analysis of radiologists' detection of pulmonary nodules. AJR Am J Roentgenol 2000;174:71-74
  19. Heller N, Sathianathen N, Kalapara A, Walczak E, Moore K, Kaluzniak H, et al. The KiTS19 challenge data: 300 kidney tumor cases with clinical context, CT semantic segmentations, and surgical outcomes. arXiv preprint 2019;arXiv:1904.00445
  20. Marcus DS, Fotenos AF, Csernansky JG, Morris JC, Buckner RL. Open access series of imaging studies: longitudinal MRI data in nondemented and demented older adults. J Cogn Neurosci 2010;22:2677-2684
  21. Abadi M, Agarwal A, Barham P, Brevdo E, Chen Z, Citro C, et al. Tensorflow: large-scale machine learning on heterogeneous distributed systems. arXiv preprint 2016;arXiv:1603.04467
  22. Paszke A, Gross S, Massa F, Lerer A, Bradbury J, Chanan G, et al. Pytorch: an imperative style, high-performance deep learning library. In: Wallach H, Larochelle H, Beygelzimer A, d'Alche-Buc F, Fox E, Garnett R, eds. Advances in neural information processing systems 32 (NeurIPS 2019). Vancouver: NeurIPS, 2019:8026-8037