Deep Learning Method vs. Hand-Crafted Features for Lung Cancer Diagnosis and Breast Cancer Risk Analysis
Abstract
Breast cancer and lung cancer are two major leading causes of cancer deaths, and researchers have been developing computer aided diagnosis (CAD) system to automatically diagnose them for decades. In recent studies, we found that the techniques in CAD system can also be used for breast cancer risk analysis, like feature design and machine learning. Also we noticed that with the development of deep learning methods, the performance of CAD system can be improved by using computer automatically generated features. To explore these possibilities, we conducted a series of studies: the first two studies focused on transferring the original CAD system techniques to breast cancer risk analysis models; and the next two studies compared the performance of our proposed schemes using deep learning methods and traditional methods on breast cancer risk analysis and lung cancer diagnosis.
Subject Area
Medical imaging|Artificial intelligence|Computer science|Oncology
Recommended Citation
Sun, Wenqing, "Deep Learning Method vs. Hand-Crafted Features for Lung Cancer Diagnosis and Breast Cancer Risk Analysis" (2017). ETD Collection for University of Texas, El Paso. AAI10271382.
https://scholarworks.utep.edu/dissertations/AAI10271382