Semantic Segmentation of Human Thigh Quadriceps Muscle in Magnetic\n Resonance Images

2018/01/01 by Manu Goyal, Ahmad, Ezak, Goyal, Manu +7
Computer Science · Engineering · Medicine · #Advanced Neural Network Applications #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Infrared Thermography in Medicine #Medical Imaging and Analysis

paper · pdf · doi:10.48550/arxiv.1801.00415

openalex publication_date 2018/01/01 · openalex created_date 2022/09/01 · openalex updated_date 2026/07/28

Abstract

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

Citations

• ADADELTA: An Adaptive Learning Rate Method
• Adam: A Method for Stochastic Optimization
• Very Deep Convolutional Networks for Large-Scale Image Recognition
• The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation
• Pyramid Scene Parsing Network

Related

• Semantic Segmentation of Thigh Muscle using 2.5D Deep Learning Network Trained with Limited Datasets
• Segmentation of Skeletal Muscle in Thigh Dixon MRI Based on Texture Analysis
• Precise Few-shot Fat-free Thigh Muscle Segmentation in T1-weighted MRI
• Single Slice Thigh CT Muscle Group Segmentation with Domain Adaptation and Self-Training
• Performance Analysis of Deep Learning Models for Femur Segmentation in MRI Scan