Automated knee cartilage segmentation for heterogeneous clinical MRI using generative adversarial networks with transfer learning

Quantitative Imaging in Medicine and Surgery

article

Mingrui Yang¹  Ceylan Colak³  Kishore K. Chundru³  Sibaji Gaj¹  Andreas Nanavati¹  Morgan H. Jones⁴  Carl S. Winalski¹  Naveen Subhas²  Xiaojuan Li¹ 

[1] Department of Biomedical Engineering, Lerner Research Institute , Cleveland Clinic;Program of Advanced Musculoskeletal Imaging ,(PAMI) , Cleveland Clinic;Department of Diagnostic Radiology, Imaging Institute , Cleveland Clinic;Department of Orthopaedic Surgery , Brigham and Women’s Hospital

关键词: Generative adversarial networks;    transfer learning;    deep learning;    automated segmentation;    clinical knee MRI;   

DOI  :  10.21037/qims-21-459

学科分类：外科医学

来源: AME Publications

【 摘 要 】

Background: This study aimed to build a deep learning model to automatically segment heterogeneous clinical MRI scans by optimizing a pre-trained model built from a homogeneous research dataset with transfer learning. Methods: Conditional generative adversarial networks pretrained on the Osteoarthritis Initiative MR images was transferred to 30 sets of heterogenous MR images collected from clinical routines. Two trained radiologists manually segmented the 30 sets of clinical MR images for model training, validation and test. The model performance was compared to models trained from scratch with different datasets, as well as two radiologists. A 5-fold cross validation was performed. Results: The transfer learning model obtained an overall averaged Dice coefficient of 0.819, an averaged 95 percentile Hausdorff distance of 1.463 mm, and an averaged average symmetric surface distance of 0.350 mm on the 5 random holdout test sets. A 5-fold cross validation had a mean Dice coefficient of 0.801, mean 95 percentile Hausdorff distance of 1.746 mm, and mean average symmetric surface distance of 0.364 mm. It outperformed other models and performed similarly as the radiologists. Conclusions: A transfer learning model was able to automatically segment knee cartilage, with performance comparable to human, using heterogeneous clinical MR images with a small training data size. In addition, the model proved robust when tested through cross validation and on images from a different vendor. We found it feasible to perform fully automated cartilage segmentation of clinical knee MR images, which would facilitate the clinical application of quantitative MRI techniques and other prediction models for improved patient treatment planning.

【 授权许可】

All Rights reserved