相关实验视频

Updated: Jun 9, 2025

Doppler Optical Coherence Tomography of Retinal Circulation

Doppler Optical Coherence Tomography of Retinal Circulation

Published on: September 18, 2012

通过非对称双分类器调整等级偏向域调整,最大限度地减少糖尿病视网膜病变分级的差异

Yuan Ma, Yang Gu, Shuai Guo

IEEE transactions on medical imaging

|October 23, 2024

概括

糖尿病视网膜病变 (DR) 评级的深度学习模型与领域转移和不平衡的数据作斗争. 我们的新型非对称双分类器差异最小化 (ABiD) 方法提高了DR分级的概括性.

科学领域:

眼科医生眼科眼科
计算机科学计算机科学
医疗成像医学成像

背景情况:

糖尿病视网膜病变 (DR) 是全球可预防的视力丧失的主要原因.
深度学习显示了DR分级的潜力,但在跨不同数据集的概括方面面临着挑战.
在DR数据集中,域移动和不平衡的等级分配阻碍了模型性能.

研究的目的:

通过深度学习解决糖尿病视网膜病变分级的领域转移和等级不平衡的挑战.
提出一种新的图像级监督DR分级方法,以改善一般化.

主要方法:

开发了非对称双分类器差异最小化 (ABiD) 用于等级扭曲域调整.
通过最小化分类器预测差异来优化特征提取器,以增强相邻等级特征探索.
使用分布补偿最大化分类器差异,以减轻伪标签偏差.

主要成果:

拟议的ABiD方法在公共和私人DR数据集上显著优于最先进的方法.
在交叉中心,交叉供应商和交叉用户场景中展示了改进的泛化性能.
有效地处理不平衡的等级分布和小损伤检测.

结论:

ABiD为域适应DR分级提供了一个强大的解决方案,克服了现有方法的关键局限性.
这种方法显示了人工智能在眼科中更可靠和更广泛的临床应用的前景.
进一步的研究可以探索先进的技术,以提高DR检测的准确性和适应性.

更多相关视频

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

Published on: January 11, 2020

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

相关概念视频

Receiver Operating Characteristic Plot

Receiver Operating Characteristic Plot

A ROC (Receiver Operating Characteristic) plot is a graphical tool used to assess the performance of a binary classification model by illustrating the trade-off between sensitivity (true positive rate) and specificity (false positive rate). By plotting sensitivity against 1 - specificity across various threshold settings, the ROC curve shows how well the model distinguishes between classes, with a curve closer to the top-left corner indicating a more accurate model. The area under the ROC curve...