Addressing Variations and Uncertainties in Medical Image Data for Deep Learning

PhD Thesis Proposal Defence


Title: "Addressing Variations and Uncertainties in Medical Image Data for Deep 
Learning"

by

Mr. Zengqiang YAN


Abstract:

One reason for the success of deep learning in natural image data is the 
availability of large-scale labeled data. However, labeled medical image data 
often is limited, as annotating medical image data requires extensive human 
efforts and expertise. Consequently, the capacity of deep learning usually 
cannot be fully explored. In this thesis, we propose to improve deep learning 
performance through addressing variations and uncertainties in medical image 
data.

First, we study the inter-observer problem in retinal vessel segmentation, 
where human observers can generate different pixel-wise annotations given the 
same medical image. To address the problem, we design a new evaluation metric 
and construct a new loss function based on the metric. Then, we integrate the 
loss function with a new deep learning framework for accurate retinal vessel 
segmentation. Comprehensive experiments on publicly available datasets 
demonstrate the effectiveness of our approach.

Second, we investigate the boundary uncertainty problem in gland instance 
segmentation. Due to limited image resolution, annotated boundaries usually are 
not absolutely correct, which makes it challenging to preserve shape 
information in gland instance segmentation. To address the problem, we propose 
a new shape-preserving loss function, together with pseudo domain adaptation, 
to enable one single deep learning model for accurate gland instance 
segmentation. Our evaluations confirm that our method can obtain better 
performance compared with other state-of-the-art methods.

Lastly, we discuss the cross-client variation problem, where image data from 
different sources can vary significantly. It will be the bottleneck when 
applying federated learning to train deep learning models from multi-source 
decentralized medical image data. We, for the first time, propose a 
variation-aware federated learning framework to address the problem. 
Experimental results on classification of clinically significant prostate 
cancer from multi-source decentralized ADC image data show that our framework 
outperforms other deep learning frameworks, especially in dealing with small 
datasets.


Date:			Tuesday, 30 June 2020

Time:                  	3:30pm - 5:30pm

Zoom Meeting:		https://hkust.zoom.com.cn/j/93504719794

Committee Members:	Prof. Tim Cheng (Supervisor)
  			Prof. Albert Chung (Chairperson)
 			Prof. Pedro Sander
 			Prof. Weichuan Yu (ECE)


**** ALL are Welcome ****