AI methods for breast cancer risk prediction using multimodal data

Breast cancer is one of the top cancers worldwide, both in developed and less developed countries and late detection makes the treatment less successful and reduced the survival chances. There are deep learning methods developed, however the performance based only on MMG is still low for clinical us...

Full description

Saved in:
Bibliographic Details
Main Author: Xiao, Qinhui
Other Authors: Jiang Xudong
Format: Thesis-Master by Coursework
Language:English
Published: Nanyang Technological University 2024
Subjects:
Online Access:https://hdl.handle.net/10356/172961
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
Description
Summary:Breast cancer is one of the top cancers worldwide, both in developed and less developed countries and late detection makes the treatment less successful and reduced the survival chances. There are deep learning methods developed, however the performance based only on MMG is still low for clinical usage. We will develop new AI model for multimodal breast cancer risk prediction, based on large datasets. Strategies of active learning and Visual transformer will be explored to enhance the risk prediction performance.