The importance of stain normalization in colorectal tissue classification with convolutional networks

2017/02/20 by Francesco Ciompi, Ciompi, Francesco, Oscar Geessink +16 · 4 citations
Computer Science · Medicine · #AI in cancer detection #Digital Imaging for Blood Diseases #Radiomics and Machine Learning in Medical Imaging #cs.CV #cs.LG

paper · pdf · doi:10.48550/arxiv.1702.05931

Published in Proceedings of IEEE International Symposium on Biomedical Imaging (ISBI) 2017

arxiv created 2017/05/23 · arxiv updated 2017/05/24

Abstract

The development of reliable imaging biomarkers for the analysis of colorectal cancer (CRC) in hematoxylin and eosin (H&E) stained histopathology images requires an accurate and reproducible classification of the main tissue components in the image. In this paper, we propose a system for CRC tissue classification based on convolutional networks (ConvNets). We investigate the importance of stain normalization in tissue classification of CRC tissue samples in H&E-stained images. Furthermore, we report the performance of ConvNets on a cohort of rectal cancer samples and on an independent publicly available dataset of colorectal H&E images.

Citations

• Very Deep Convolutional Networks for Large-Scale Image Recognition

Cited by

• Scanner-Induced Domain Shifts Undermine the Robustness of Pathology Foundation Models
• Adaptive Stain Normalization for Cross-Domain Medical Histology
• Deep Learning Framework for Multi-class Breast Cancer Histology Image Classification
• Neural Stain-Style Transfer Learning using GAN for Histopathological Images

Related

• Staining normalization in histopathology: Method benchmarking using multicenter dataset
• CGC-Net: Cell Graph Convolutional Network for Grading of Colorectal Cancer Histology Images
• STARC-9: A Large-scale Dataset for Multi-Class Tissue Classification for CRC Histopathology
• MSRANetV2: An Explainable Deep Learning Architecture for Multi-class Classification of Colorectal Histopathological Images
• NCT-CRC-HE: Not All Histopathological Datasets Are Equally Useful