Semantic Segmentation of Thigh Muscle using 2.5D Deep Learning Network Trained with Limited Datasets

Hasnine Haque, Masahiro Hashimoto, Nozomu Uetake +1

Purpose: We propose a 2.5D deep learning neural network (DLNN) to automatically classify thigh muscle into 11 classes and evaluate its classification accuracy over 2D and 3D DLNN w…