Pixel Club: Digital Pathologist - Segmentation and Classification of Biopsy Images

Speaker:
Assaf Cohen (Haifa University)
Date:
Tuesday, 20.5.2014, 11:30
Place:
EE Meyer Building 1061

Cancer is diagnosed by a biopsy – a pathologist’s examination of a tissue sample via a microscope. Biopsy image is very rich with data and contains many variations and artifacts, which makes the analysis of it to be very difficult. Most of the previous approaches for segmentation and classification of biopsy images do not understand the meaning of each pixel and the structure of its basic elements.

In this talk, I will present a novel biopsy analysis system. The biopsy analysis is based on pixel-level classification (PLC) of the biopsy image. First, segmenting the basic elements of the biopsy (crypts) using novel Active Contour algorithm based on the PLC. Second, partitioning the biopsy to cancerous and healthy regions using the crypt architecture.

This is a joint work with Ilan Shimshoni (Haifa Uni), Ehud Rivlin (Technion), and Edmond Sabo (MD) from Rambam Hospital, giving the clinical guidance and the biopsies data.

Bio:
I did my first degree in Computer Science at the Technion. I am currently doing my MSc in Computer Science at the Haifa University and doing the thesis with the supervision of Prof. Ilan Shimshoni from Dept. of Information Systems, Haifa University, and Ehud Rivlin from the Dept. of Computer Science, Technion. I am working at Philips Healthcare, and my passions are Computer Vision and Medical Imaging.

Back to the index of events