Improving the 3D Segmentation of Nodules in Lung CT Images

Please enable javascript in your browser.

Moradi, Puria | 2019

598 Viewed

Type of Document: M.Sc. Thesis
Language: Farsi
Document No: 51580 (19)
University: Sharif University of Technology
Department: Computer Engineering
Advisor(s): Jamzad, Mansour; Beigy, Hamid
Abstract:
Lung cancer is one of the most common types of cancers, and its early diagnosis can save many lives. Due to the high number of computed tomography (CT) images used to detect lung cancer, it is difficult to accurately and rapidly diagnose this disease. Doing so requires high expertise by radiologists. Therefore the demand for computer aided diagnosis systems in this area has been increased. The core of all lung cancer detection systems is the distinction between cancer and non-cancerous tissues. The main objective of this study is to present a new method based on 3D convolutional neural networks (CNN) that can perform false positives reduction operations while providing high sensitivity. In this study, we used 3D multi-level contextual CNNs to automatically detect lung nodules and designed a meta-classifer in order to properly utilize the knowledge gained through the CNNs for fusion. By using this architecture we got 91.23% sensitivity in detecting lung nodules with 4 false positive per scan
Keywords:
Lung Cancer ; Convolutional Neural Network ; CT Scan ; Computer Aided Diagnosis Medicine ; Tomography

No TOC