Cardio-pulmonary Substructure Segmentation of CT images using Convolutional Neural Networks for Clinical Outcome Analysis
Keywords: Semantic segmentation, Convolutional Neural Networks, cardio-pulmonary, clinical outcomes
TL;DR: Segmentation of cardio-pulmonary substructures from CT images using convolutional neural networks to enable outcome analysis for lung cancer patients
Abstract: Radiotherapy doses to some cardio-pulmonary substructures may be critical factors in the observed early mortality following radiotherapy for nonsmall cell lung cancer patients. Our goal is to provide an open-source tool to automatically segment cardio-vascular substructures for consistent outcomes analyses. To facilitate this, we built and validated a multi-label Deep Learning Segmentation (DLS) framework for accurate auto-segmentation of cardio-pulmonary substructures. The DLS framework utilized a deep neural network architecture to segment 12 cardio-pulmonary substructures from Computed Tomography (CT) scans of 217 patients previously treated with thoracic RT. A hold-out dataset of 24 CT scans was used for quantitative evaluation of the final model against expert contours using Dice Similarity Coefficients (DSC), as well as dose-volume histogram metrics. The model was robust against variability in image quality characteristics, including the presence/absence of contrast. The accuracy was judged adequate for extracting dose-volume histogram information for outcomes analyses, with no statistical difference between clinical expert contours against DLS contour metrics.
Code Of Conduct: I have read and accept the code of conduct.
Remove If Rejected: Remove submission from public view if paper is rejected.