Scholarlink

In recent years, deep learning has demonstrated its relevance in breast cancer diagnosis using mammography screening data in classification and detection tasks. The implementation of learning from longitudinal data of individual patients in deep learning models may lead to better risk prediction for breast cancer in the near future. This paper provides an overview of the work that has been done to date on longitudinal changes in mammography. The works on longitudinal data in mammography were divided according to the deep learning models that were used to retain the time information during the training: 1. recurrent neural networks and 2. transformers. To facilitate navigation through the mammography databases containing longitudinal data we provide summary of conforming datasets.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Review of Recent Deep Learning Techniques Using Longitudinal Mammogram Data

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Aneta Gábrišová,
  • Ivan Cimrák

摘要

In recent years, deep learning has demonstrated its relevance in breast cancer diagnosis using mammography screening data in classification and detection tasks. The implementation of learning from longitudinal data of individual patients in deep learning models may lead to better risk prediction for breast cancer in the near future. This paper provides an overview of the work that has been done to date on longitudinal changes in mammography. The works on longitudinal data in mammography were divided according to the deep learning models that were used to retain the time information during the training: 1. recurrent neural networks and 2. transformers. To facilitate navigation through the mammography databases containing longitudinal data we provide summary of conforming datasets.