Automatic lung nodule graph cuts segmentation with deep learning false positive reduction

Wenqing Sun; Xia Huang; Tzu-Liang Bill Tseng; Wei Qian

doi:10.1117/12.2251302

Translator Disclaimer

3 March 2017 Automatic lung nodule graph cuts segmentation with deep learning false positive reduction

Wenqing Sun, Xia Huang, Tzu-Liang Bill Tseng, Wei Qian

Author Affiliations +

Proceedings Volume 10134, Medical Imaging 2017: Computer-Aided Diagnosis; 101343M (2017) https://doi.org/10.1117/12.2251302
Event: SPIE Medical Imaging, 2017, Orlando, Florida, United States

Abstract

To automatic detect lung nodules from CT images, we designed a two stage computer aided detection (CAD) system. The first stage is graph cuts segmentation to identify and segment the nodule candidates, and the second stage is convolutional neural network for false positive reduction. The dataset contains 595 CT cases randomly selected from Lung Image Database Consortium and Image Database Resource Initiative (LIDC/IDRI) and the 305 pulmonary nodules achieved diagnosis consensus by all four experienced radiologists were our detection targets. Consider each slice as an individual sample, 2844 nodules were included in our database. The graph cuts segmentation was conducted in a two-dimension manner, 2733 lung nodule ROIs are successfully identified and segmented. With a false positive reduction by a seven-layer convolutional neural network, 2535 nodules remain detected while the false positive dropped to 31.6%. The average F-measure of segmented lung nodule tissue is 0.8501.

Citation Download Citation

Wenqing Sun, Xia Huang, Tzu-Liang Bill Tseng, and Wei Qian "Automatic lung nodule graph cuts segmentation with deep learning false positive reduction", Proc. SPIE 10134, Medical Imaging 2017: Computer-Aided Diagnosis, 101343M (3 March 2017); https://doi.org/10.1117/12.2251302

ACCESS THE FULL ARTICLE