The purpose of this project is to develop computer-aided diagnosis/detection (CAD) for a wide variety of radiologic images and disease types. This project uses existing NIH radiology images. We are developing techniques for segmentation of abdominal CT images to accurately locate the boundaries of the major abdominal organs such as the liver, spleen, adrenal glands, kidneys and pancreas. We made further progress on this project, providing accurate localization and measurement of the pancreas. We also made progress on automated detection of the thyroid, bone fractures and lymphadenopathy on CT scans. We made further progress on a project to develop computer-aided detection of prostate cancer on endorectal coil MRI scans. We are developing methods to identify frequently missed lesions such as epidural masses. We made progress on a new project that uses convolutional neural networks (deep learning) on big data to train computers to detect diseases on radiology images like CT and MRI scans.
Showing the most recent 10 out of 78 publications