Scholarlink

This research introduces the Multi-branch Residual Convolutional Neural Network (MRes-CNN) to enhance the accuracy of colorectal histopathological image classification. MRes-CNN incorporates MRes Blocks and Attention Module, optimizing efficiency in analyzing images. Employing the open-sourced Enteroscope Biopsy Histopathological Hematoxylin and Eosin Image Dataset (EBHI) for empirical validation, MRes-CNN achieves an impressive average accuracy of 92.44% across three experiments, significantly outperforming 21 existing deep learning (DL) models. Ablation studies confirm the crucial roles of MRes Blocks and Attention Module in enhancing model performance. These findings underscore the potential of MRes-CNN to transform colorectal histopathological image classification, promising substantial benefits for clinical practice and medical research.

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

MRes-CNN: A Multi-branch Residual CNN for Colorectal Histopathological Image Classification

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Lingling Yuan,
  • Md Mamunur Rahaman,
  • Hongzan Sun,
  • Xiaoyan Li,
  • Marcin Grzegorzek,
  • Ning Xu,
  • Chen Li

摘要

This research introduces the Multi-branch Residual Convolutional Neural Network (MRes-CNN) to enhance the accuracy of colorectal histopathological image classification. MRes-CNN incorporates MRes Blocks and Attention Module, optimizing efficiency in analyzing images. Employing the open-sourced Enteroscope Biopsy Histopathological Hematoxylin and Eosin Image Dataset (EBHI) for empirical validation, MRes-CNN achieves an impressive average accuracy of 92.44% across three experiments, significantly outperforming 21 existing deep learning (DL) models. Ablation studies confirm the crucial roles of MRes Blocks and Attention Module in enhancing model performance. These findings underscore the potential of MRes-CNN to transform colorectal histopathological image classification, promising substantial benefits for clinical practice and medical research.