Open Access3D FULLY CONVOLUTIONAL NETWORK FOR THORAX MULTI-ORGANS SEMANTIC SEGMENTATION
Author(s) -
Qian Wu,
QI CHEN,
YONGJIAN YU,
LIANGJUN FAN
Publication year - 2022
Publication title -
journal of mechanics in medicine and biology
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.236
H-Index - 30
eISSN - 1793-6810
pISSN - 0219-5194
DOI - 10.1142/s0219519422400061
Subject(s) - dice , sørensen–dice coefficient , segmentation , computer science , similarity (geometry) , artificial intelligence , pattern recognition (psychology) , thorax (insect anatomy) , noise (video) , feature (linguistics) , image segmentation , medicine , anatomy , mathematics , statistics , image (mathematics) , linguistics , philosophy
Automatically delineating Organs-at-Risks (OARs) on computed tomography (CT) has the benefit of both reducing the time and improving the quality of radiotherapy (RT) planning. A 3D convolutional deep learning framework for multi-organs segmentation is proposed in this work; moreover, for the small volume OARs, a robust 3D squeeze-and-excitation (SE) feature extraction mechanism and a new Dice loss function are incorporated in the traditional 3D U-Net. We collected 60 thorax CT images set with annotations and expanded to 260 patients by the augmented method of randomly rotating [Formula: see text]6 degrees with a 1/3 probability and adding Gaussian noise. The objective is to segment five important organs: esophagus, spinal cord, heart, and bilateral lungs. Compared with 3D U-Net, 3D-2D U-Net proposed in our work increases the Dice similarity coefficient by 5% on average for the heart and bilateral lungs, and 3D Small Volume U-Net can further increase the Dice similarity coefficient to above 80% for the spinal cord. The experiment results demonstrate that the proposed model can improve the delineation accuracy of OARs from CT images.