Event Details
Weakly Supervised Classification and Localization of Thorax Diseases on X-Ray images
Presenter: Alinstein Jose
Supervisor:
Date: Thu, March 25, 2021
Time: 13:00:00 - 14:00:00
Place: Remote via Zoom - please see link below
ABSTRACT
Zoom meeting link: https://uvic.zoom.us/j/86858287584?pwd=NUVvWWpnWGhtYWFORm1Bci9Eem9LZz09
Meeting ID: 868 5828 7584
Password: 140691
Abstract:
The ability to solve many computer vision problems like image classification, object detection, localization, and tracking has grown significantly in terms of performance and efficiency in recent years when the field is equipped with state-of-the-art deep learning techniques. In this seminar, we focus on the classification and localization of diseases in the Chest X-ray images. Specifically, in the first part of the seminar, we present a deep neural network that predicts disease in Chest X-ray images. However, a supervised localization of diseases in the X-ray images is not possible because of the unavailability of labels for region-level bounding boxes of diseases in X-ray images. In the second part of the talk, we propose a weakly supervised localization method to locate disease regions in X-ray images to address the issue.