Semantic Segmentation Using Deep Learning to Extract Total Extraocular Muscles and Optic Nerve from Orbital Computed Tomography Images

Objectives: Precise segmentation of total extraocular muscles (EOM) and optic nerve (ON) is essential to assess anatomical development and progression of thyroid-associated ophthalmopathy (TAO). We aim to develop a semantic segmentation method based on deep learning to extract the total EOM and ON from orbital CT images in patients with suspected TAO. Materials and Methods: A total of 7,879 images obtained from 97 subjects who underwent orbit CT scans due to suspected TAO were enrolled in this study. Eighty-eight patients were randomly selected into the training/validation dataset, and the rest were put into the test dataset. Contours of the total EOM and ON in all the patients were manually delineated by experienced radiologists as the ground truth. A three-dimensional (3D) end-to-end fully convolutional neural network called semantic V-net (SV-net) was developed for our segmentation task. Intersection over Union (IoU) was measured to evaluate the accuracy of the segmentation results, and Pearson correlation analysis was used to evaluate the volumes measured from our segmentation results against those from the ground truth. Results: Our model in the test dataset achieved an overall IoU of 0.8207; the IoU was 0.7599 for the superior rectus muscle, 0.8183 for the lateral rectus muscle, 0.8481 for the medial rectus muscle, 0.8436 for the inferior rectus muscle and 0.8337 for the optic nerve. The volumes measured from our segmentation results agreed well with those from the ground truth (all R>0.98, P<0.0001). Conclusion: The qualitative and quantitative evaluations demonstrate excellent performance of our method in automatically extracting the total EOM and ON and measuring their volumes in orbital CT images. There is a great promise for clinical application to assess these anatomical structures for the diagnosis and prognosis of TAO.

Fubao Zhu, Zhengyuan Gao, Chen Zhao, Zelin Zhu, Yanyun Liu, Shaojie Tang, Chengzhi Jiang, Xinhui Li, Min Zhao, Weihua Zhou (2) __INSTITUTION_10__ School of Computer, Communication Engineering, Zhengzhou University of Light Industry, Zhengzhou, Henan, China (2) College of Computing, Michigan Technological University, Houghton, MI, USA (3) School of Automation, Xi'an University of Posts, Telecommunications, Xi'an, Shaanxi, China (4) Department of PET-CT Center, Hunan Cancer Hospital, Changsha, China (5) Department of Nuclear Medicine, Xiangya Hospital, Central South University, Changsha, China) · 2020