CS Events Monthly View
Effective Medical Image Segmentation for Osteoarthritis Analysis
Monday, September 30, 2019, 01:30pm
Osteoarthritis (OA) is the most common degenerative joint disease worldwide, tending to occur in the joints of hip and knee. Effective medical image segmentation methods play fundamental roles in the clinical analysis of the disease. In this dissertation, two deep learning based tissue segmentation for the proximal femur and knee cartilages will be mainly discussed, respectively.
First of all, a deep multi-task learning network is exploited for the shape-preserved segmentation of the proximal part of femur (i.e., femoral head and neck) in 2D magnetic resonance (MR) images. This method combines the tasks of region identification and boundary distance regression, and thus enables the task-specific feature learning for continuous segmented object with smooth boundary. This bone depiction can be further used for the alpha angle measurements to reflect the evolution of hip OA.
Second, the knee cartilages (i.e., femoral, tibial, and patellar cartilage) are essential tissue for knee radiographic OA diagnosis. We propose an effective extraction of knee cartilages in large-sized and high-resolution 3D MR data, and further explore the defect/loss conditions in cartilages which are important factors of knee OA. The key contribution is an adversarial learning based collaborative multi-agent network. We use three parallel segmentation agents to label cartilages in their respective region of interest (ROI), and then fuse the three cartilages by a ROI-fusion layer and drive a collaborative learning by an adversarial sub-network. The ROI-fusion layer not only fuses the individual cartilages, but also backpropagates the training loss from the adversarial sub-network to each agent to enable joint learning of shape and spatial constraints.
Speaker: Chaowei Tan
Location : CBIM 22
Prof. Dimitris N. Metaxas (Chair),Prof. Kang Li, Prof. Jingjin Yu, Dr. Xin Dou (SenseBrain Technology Limited, Princeton)
Event Type: PhD Defense
Dept. of Computer Science