Translator Disclaimer
Presentation + Paper
10 March 2020 Fully convolutional network with sparse feature-maps composition for automatic lung tumor segmentation from PET images
Author Affiliations +
Abstract
Accurate lung tumor delineation plays an important role in radiotherapy treatment planning. Since the lung tumor has poor boundary in positron emission tomography (PET) images, it is a challenging task to accurately segment lung tumor. In addition, the heart, liver, bones and other tissues generally have the similar gray value as the lung tumor, therefore the segmentation results usually have high false positive. In this paper, we propose a novel and efficient fully convolutional network with a trainable compressed sensing module and deep supervision mechanism with sparse constraints to comprehensively address these challenges; and we call it fully convolutional network with sparse feature-maps composition (SFC-FCN). Our SFC-FCN is able to conduct end-to-end learning and inference, compress redundant features within channels and extract key uncorrelated features. In addition, we use deep a supervision mechanism with sparse constraints to guide the features extraction by a compressed sensing module. The mechanism is developed by driving an objective function that directly guides the training of both lower and upper layers in the network. We have achieved more accurate segmentation results than that of state-of-the-art approaches with a much faster speed and much fewer parameters.
Conference Presentation
© (2020) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Haihong Tian, Dehui Xiang, Weifang Zhu, Fei Shi, and Xinjian Chen "Fully convolutional network with sparse feature-maps composition for automatic lung tumor segmentation from PET images", Proc. SPIE 11313, Medical Imaging 2020: Image Processing, 113131O (10 March 2020); https://doi.org/10.1117/12.2548670
PROCEEDINGS
8 PAGES + PRESENTATION

SHARE
Advertisement
Advertisement
Back to Top