In response to coronavirus and to help minimize its spread, many UCF events are being canceled.

If you have questions about what’s still open around campus, please check out this regularly updated guide.

Tuesday, November 5, 2019 1:15 p.m. to 3:15 p.m.

Final Examination of Naji Khosravan for the degree of Doctor of Philosophy in Computer Science

Download Bifold

Although radiology screening is proved to be a vital step for cancer detection in many applications, human errors stay as a significant issue in this process. Missing cases and over-diagnosis can have serious outcomes and increase mortality rate. In this dissertation, we propose novel machine learning algorithms for high-risk medical imaging applications. Specifically, we tackle current challenges in radiology screening process and introduce cutting-edge methods for image-based diagnosis, detection and segmentation. We incorporate expert knowledge through eye-tracking, making the whole process human-centered.

This dissertation contributes to machine learning, computer vision, and medical imaging research by: 1) introducing a mathematical formulation of radiologists level of attention, and sparsifying their gaze data for a better extraction and comparison of search patterns. 2) proposing novel, local and global, image analysis algorithms. Imaging based diagnosis and pattern analysis are "high-risk" Artificial Intelligence applications. A standard radiology screening procedure includes detection, diagnosis and measurement (often done with segmentation) of abnormalities. We hypothesize that having a true collaboration is essential for a better control mechanism, in such applications. In this regard, we propose to form a collaboration medium between radiologists and machine learning algorithms through eye-tracking. Further, we build a generic platform consisting of novel machine learning algorithms for each of these tasks.


ENG II: 202A


CS/CRCV Seminars