Semantic Segmentation of Human Thigh Quadriceps Muscle in Magnetic Resonance Images

This paper presents an end-to-end solution for MRI thigh quadriceps. This is the first attempt that deep learning methods are used for MRI thigh segmentation task. We use the state-of-the-art Fully Networks with transfer learning approach for the semantic of regions of interest in MRI thigh scans. To further improve the of the segmentation, we propose a post-processing technique using image processing methods. With our proposed method, we have established a benchmark for MRI thigh quadriceps segmentation with mean Jaccard Index of 0.9502 and processing time of 0.117 second per image.