Back to search

Cornell University

Deep Learning for Localizing and Segmenting Anatomies in Medical Imaging

Abstract

dc:description.abstract

Machine learning and deep learning have recently witnessed great successes in various fields such as computer vision and natural language processing.In many image analysis applications, deep learning and neural networks have achieved state-of-the-art results, thanks to hardware advancement and improved data quality and accessibility over the past decades. Deep learning based methods such as convolutional neural networks (CNNs) and Transformer have shown better than human performance in some visual recognition tasks including medical imaging analysis. Among all the applications that machine learning algorithms show great potential in, localizing and segmenting anatomies in medical images is one of the most important, and usually the first step before any subsequent tasks such as computer-aided diagnosis. Although there are many successful deep learning methods for keypoint detection and image segmentation, a lot of them focus on natural images, which is very different from medical imaging such as CT and MRI. Indeed, there are still many challenges we face today that hamper the adoption of deep learning in the hospital and other clinical settings. In this thesis, we talk about some of those limitations deep learning has in the field of medical image analysis, and our algorithmic innovations and solutions to these challenges.

Degree

thesis:*
Name thesis:degree_name
Ph. D., Physics
Level thesis:degree_level
Doctor of Philosophy
Discipline thesis:degree_discipline
Physics
Grantor
Cornell University
Year dc:date.issued
2022

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Ma, Tianyu
Chair dc:contributor.chair
  • Sabuncu, Mert
Committee members dc:contributor.committeemember
  • Reeves, Anthony P.
  • Alexander, Jim
  • Elser, Veit

Subjects

dc:subject × 4

Rights

dc:rights
Statement dc:rights
  • Attribution 4.0 International
Language dc:language.iso
en

Identifiers

dc:identifier.*
Dc Identifier Bibid
15529983
Dc Identifier Other
ProQuest Submission ID: 12987
ProQuest Publication ID: 29163650

Chain of custody

source
Harvested from
Cornell University
Base URL
ecommons.cornell.edu/server/oai/request
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Ma, Tianyu. Deep Learning for Localizing and Segmenting Anatomies in Medical Imaging. Doctor of Philosophy thesis, Cornell University, 2022. https://hdl.handle.net/1813/111745