相关实验视频

Updated: Sep 13, 2025

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

可解释的多视图变压器框架与相互学习,用于精确的乳腺癌病理学图像分类

Haewon Byeon¹, Mahmood Alsaadi², Richa Vijay³

¹Convergence Department, Korea University of Technology and Education, Cheonan, Republic of Korea.

Frontiers in oncology

|July 29, 2025

概括

一个新的AI框架,多视图变压器在线融合相互学习 (MVT-OFML),通过结合CNN和变压器来增强乳腺癌诊断. 这种可解释的模型提高了准确性,并为临床决策提供了视觉解释.

科学领域:

人工智能的人工智能
医学图像分析医学图像分析
计算病理学计算病理学

背景情况:

准确的乳腺癌诊断依赖于病理图像分析,但目前的AI模型难以平衡性能和可解释性.
卷积神经网络 (CNN) 在局部细节方面表现出色,但错过了全球上下文,而变压器捕捉了全球上下文,但缺乏细粒度的局部特征建模.

研究的目的:

开发一种新的,可解释的AI框架,用于乳腺癌病理图像分类,克服现有模型的局限性.
通过混合方法在精确癌症诊断中推进可解释AI (XAI).

主要方法:

拟议的MVT-OFML (多视图变压器在线融合相互学习) 框架集成ResNet-50用于本地特征和多视图变压器用于全球背景.
实现在线融合相互学习 (OFML),用于CNN和变压器组件之间的双向知识共享.
生成可解释的注意力地图和特征可视化,以实现模型透明度.

主要成果:

在BreakHis和BACH数据集上,MVT-OFML显著超过了基线模型.
实现了0.90% (BreakHis) 和2.26% (BACH) 的精度改进.
证明F1得分增长了4.75% (BreakHis) 和3.21% (BACH) 的时间.

结论:

MVT-OFML提供了一个有前途的AI解决方案,用于准确和可解释的乳腺癌诊断和预后.
该框架通过提供透明的决策流程来提高临床可用性.
将互补的AI范式与可解释的策略相结合,可以支持明智的临床决策.

关键词:

在MVT-OFML中.乳腺癌乳腺癌乳腺癌可以解释的人工智能AI 多视图变压器多视图变压器相互学习的相互学习.病理学图像分类图像分类

更多相关视频

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

相关概念视频

Improving Translational Accuracy

Improving Translational Accuracy

Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...