摘要
Deep learning (DL)-based auto-segmentation has the potential for accurate organ delineation in radiotherapy applications but requires large amounts of clean labeled data to train a robust model. However, annotating medical images is extremely time-consuming and requires clinical expertise, especially for segmentation that demands voxel-wise labels. On the other hand, medical images without annotations are abundant and highly accessible. To alleviate the influence of the limited number of clean labels, we propose a weakly supervised DL training approach using deformable image registration (DIR)-based annotations, leveraging the abundance of unlabeled data. We generate pseudo-contours by utilizing DIR to propagate atlas contours onto abundant unlabeled images and train a robust DL-based segmentation model. With 10 labeled TCIA dataset and 50 unlabeled CT scans from our institution, our model achieved Dice similarity coefficient of 87.9%, 73.4%, 73.4%, 63.2% and 61.0% on mandible, left & right parotid glands and left & right submandibular glands of TCIA test set and competitive performance on our institutional clinical dataset and a third party (PDDCA) dataset. Experimental results demonstrated the proposed method outperformed traditional multi-atlas DIR methods and fully supervised limited data training and is promising for DL-based medical image segmentation application with limited annotated data.
学科与关键词
- Weakly-Supervised Deep Learning Based Automatic Image Segmentation Via Deformable Image RegistrationChi, W.; Lu, W.; Ma, L.; Wu, J.; Chen, H.; Tan, M.; Gu, X.
- Medical Image Segmentation With Limited Supervision: A Review of Deep Network ModelsPeng, Jialin*; Wang, YeIEEE Access, 2021, 9: 36827-36851.被引 33
- Recent advances and clinical applications of deep learning in medical image analysisChen, Xuxin; Wang, Ximin; Zhang, Ke; Fung, Kar-Ming; Thai, Theresa C.; Moore, Kathleen; Mannel, Robert S.; Liu, Hong; Zheng, Bin; Qiu, Yuchen*Medical Image Analysis, 2022, 79: 102444.被引 371
