Improving Data Efficiency on Histopathological Image Analysis Using Deep Learning

Speaker: Wenyuan Li
Affiliation: Ph.D. Candidate

Via Zoom Only: https://uclahs.zoom.us/j/8394923158?pwd=K3BVUEEyNTVHQWtnRGJ3MUhUQytJdz09

Password: 049836

Abstract:  Histopathology images have been widely used to detect and diagnose a variety of cancers. With the growing availability of large scale gigapixel whole-slide images (WSI) of tissue specimens, digital pathology has become a very popular application area for deep learning techniques. Nevertheless, challenges exist in current computer-aided histopathology image analysis. Perhaps the biggest challenge is the insufficiency of annotated data. Deep learning requires extremely abundant training data to achieve good performance. However, only pathologists, who have been trained for years, can annotate the histopathology image accurately. Therefore, labeling histopathology images is both expensive and labor-intensive. The scarcity of the annotation can also be found at different scales. For example, to do a semantic segmentation task, it requires the network to have annotations at “pixel-wise” level; by tiling WSIs into different patches, patch-level labels are needed to provide accurate predictions. But in reality, most labels of WSIs are at case-level (e.g. final diagnosis) at most.

In this talk, I will present methods to improve data efficiency on histopathology image analysis. We first start with a novel fully-supervised segmentation model for Gleason grading of prostate cancer. Then we present a series of studies on semi-supervised learning, where we can take advantage of unannotated data. We focus on methods using generative adversarial networks (GANs). To this end, we demonstrate a pyramid GAN structure for high-resolution large-scale histopathology image generation and segmentation on both fully-supervised and semi-supervised scenarios. Finally, we present an active learning framework that is able to reduce the annotations required from the expert and handle noisy labels simultaneously.

Biography:  Wenyuan Li received the B.S. degree in the department of Optical Engineering from Zhejiang University, Hangzhou, China, in 2014 and the M.S. degree in the department of Electrical Engineering from University of California, Los Angeles (UCLA), CA, USA, in 2016. He is currently pursuing the Ph.D. degree at the Computational Diagnostic Lab in UCLA. His research focuses on histopathology image analysis. He was the recipient of Chiang Chen Overseas Fellowship and UCLA ECE Department Fellowship. He was a machine learning Intern with IQVIA Inc., in 2018 summer and Facebook Inc., in 2019 summer.

For more information, contact Prof. Gregory Pottie (pottie@ee.ucla.edu) or Co-advisor: Prof. Corey Arnold (cwarnold@ucla.edu)

Date/Time:
Date(s) - Sep 23, 2020
4:00 pm - 6:00 pm

Location:
Via Zoom Only
No location, Los Angeles
Map Unavailable