相关实验视频

Updated: Mar 12, 2026

Analyzing Mitochondrial Morphology Through Simulation Supervised Learning

Analyzing Mitochondrial Morphology Through Simulation Supervised Learning

Published on: March 3, 2023

基于分解的课程风格的自我培训,用于计算病理学的无源通用域适应

Wentao Liu¹, Zhiwei Ni¹, Xuhui Zhu²

¹School of Management, Hefei University of Technology, Anhui 230009, China; Key Laboratory of Process Optimization and Intelligent Decision-making, Ministry of Education, Anhui 230009, China.

Neural networks : the official journal of the International Neural Network Society

|March 11, 2026

概括

由于数据法规,计算病理学模型面临部署挑战. 一个新的基于分解的课程式自我训练 (DCST) 框架通过更好地处理数据变化和噪声来改善无源通用域适应 (SF-UniDA).

科学领域:

数字病理学数字病理学
机器学习在医学中的应用
计算机辅助诊断是一种计算机辅助的诊断.

背景情况:

计算病理学模型有助于组织类型和整个幻灯片图像分析.
跨机构的部署受到数据法规和领域转移的阻碍.
无源通用域调整 (SF-UniDA) 能够通过未标记的目标数据进行知识传输.

研究的目的:

解决现有的SF-UniDA方法的局限性,这些方法忽视了内部数据变化和噪声.
提出一个新的框架,以改善计算病理学领域的适应性.
加强病理学模型的跨机构部署.

主要方法:

开发了一个基于分解的课程式自我训练 (DCST) 框架.
引入了使用高斯混合模型进行简单/硬数据分离的自适应式划分策略.
实现了原型意识的规范化和对齐,以保持类间的变化和平衡学习.

主要成果:

DCST框架有效地处理私人数据中的内部变化.
拟议的方法减轻了噪音样本的干扰.
与最先进的方法相比,结肠直肠癌表型化数据集实现了一致的性能增长.

结论:

通过改进数据审查和学习范式,DCST为SF-UniDA提供了强大的方法.
该框架提高了计算病理学模型在不同机构的可靠性和适用性.
这项工作推动了AI在临床应用的数字病理学领域的发展.

关键词:

计算病理学计算病理学课程自我训练课程自我训练特征分解特性分解没有源代码的通用域调整.

更多相关视频

A Virtual Machine Platform for Non-Computer Professionals for Using Deep Learning to Classify Biological Sequences of Metagenomic Data

A Virtual Machine Platform for Non-Computer Professionals for Using Deep Learning to Classify Biological Sequences of Metagenomic Data

Published on: September 25, 2021

A Web Tool for Generating High Quality Machine-readable Biological Pathways

A Web Tool for Generating High Quality Machine-readable Biological Pathways

Published on: February 8, 2017

相关概念视频

Improving Translational Accuracy

Improving Translational Accuracy

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...