H&E Stained

Hematoxylin and eosin (H&E) staining is a fundamental technique in histopathology, providing crucial visual information about tissue morphology for disease diagnosis and prognosis. Current research focuses on leveraging deep learning, particularly convolutional neural networks and transformer architectures like Swin Transformers, to analyze H&E-stained whole slide images (WSIs) for automated tasks such as tumor segmentation, biomarker prediction (e.g., microsatellite instability), and risk stratification (e.g., breast cancer recurrence). These advancements offer the potential to improve diagnostic accuracy, personalize treatment strategies, and accelerate the overall workflow in pathology, ultimately impacting patient care and research efficiency.

Papers

September 24, 2024

Automatic Registration of SHG and H&E Images with Feature-based Initial Alignment and Intensity-based Instance Optimization: Contribution to the COMULIS Challenge
Marek Wodzinski, Henning Müller
Feature Alignment Pre Registration Instance Optimal Equivariant Imaging Multi Modal Registration H&E Stained

June 10, 2024

Predicting the risk of early-stage breast cancer recurrence using H\&E-stained tissue images
Geongyu Lee, Joonho Lee, Tae-Yeong Kwak, Sun Woo Kim, Youngmee Kwon, Chungyeul Kim, Hyeyoon Chang
Breast Cancer Deep Learning Algorithm High Quality Risk Description Pathology Image Risk Prediction H&E Stained

July 22, 2023

SCPAT-GAN: Structural Constrained and Pathology Aware Convolutional Transformer-GAN for Virtual Histology Staining of Human Coronary OCT images
Xueshen Li, Hongshan Liu, Xiaoyu Song, Brigitta C. Brott, Silvio H. Litovsky, Yu Gan
Optical Coherence Tomography C Gan Transformer Based Generative Adversarial Structural Constraint H&E Stained

July 12, 2023

The Whole Pathological Slide Classification via Weakly Supervised Learning
Qiehe Sun, Jiawen Li, Jin Xu, Junru Cheng, Tian Guan, Yonghong He
Multiple Instance Learning Weakly Supervised Learning Tissue Image H&E Stained Whole Slide Pathological Image

August 22, 2022

Predicting microsatellite instability and key biomarkers in colorectal cancer from H&E-stained images: Achieving SOTA predictive performance with fewer data using Swin Transformer
Bangwei Guo, Xingyu Li, Jitendra Jonnagaddala, Hong Zhang, Xu Steven Xu
Swin Transformer Cross Validation Colorectal Cancer DNA Methylation H&E Stained Microsatellite Instability

June 16, 2022

Rank the triplets: A ranking-based multiple instance learning framework for detecting HPV infection in head and neck cancers using routine H&E images
Ruoyu Wang, Syed Ali Khurram, Amina Asif, Lawrence Young, Nasir Rajpoot
Neck Cancer H&E Stained Human Papillomavirus

March 23, 2022

Interpretable Prediction of Lung Squamous Cell Carcinoma Recurrence With Self-supervised Learning
Weicheng Zhu, Carlos Fernandez-Granda, Narges Razavian
Self Supervised Learning Interpretable Prediction Recurrence Prediction H&E Stained

February 15, 2022

Deep Learning-Assisted Co-registration of Full-Spectral Autofluorescence Lifetime Microscopic Images with H&E-Stained Histology Images
Qiang Wang, Susan Fernandes, Gareth O. S. Williams, Neil Finlayson, Ahsan R. Akram, Kevin Dhaliwal, James R. Hopgood, Marta Vallejo
Deformable Registration Fluorescence Image H&E Stained Fluorescence Lifetime Endogenous Fluorescence

December 1, 2021

Automatic tumour segmentation in H&E-stained whole-slide images of the pancreas
Pierpaolo Vendittelli, Esther M. M. Smeets, Geert Litjens
Tumor Segmentation Disease Detection Fetal Liver Pancreatic Cancer H&E Stained Multi Task Convolutional Neural Network Spatial Pathomics

H&E Stained

Papers

Automatic Registration of SHG and H&E Images with Feature-based Initial Alignment and Intensity-based Instance Optimization: Contribution to the COMULIS Challenge

Predicting the risk of early-stage breast cancer recurrence using H\&E-stained tissue images

SCPAT-GAN: Structural Constrained and Pathology Aware Convolutional Transformer-GAN for Virtual Histology Staining of Human Coronary OCT images

The Whole Pathological Slide Classification via Weakly Supervised Learning

Predicting microsatellite instability and key biomarkers in colorectal cancer from H&E-stained images: Achieving SOTA predictive performance with fewer data using Swin Transformer

Rank the triplets: A ranking-based multiple instance learning framework for detecting HPV infection in head and neck cancers using routine H&E images

Interpretable Prediction of Lung Squamous Cell Carcinoma Recurrence With Self-supervised Learning

Deep Learning-Assisted Co-registration of Full-Spectral Autofluorescence Lifetime Microscopic Images with H&E-Stained Histology Images

Automatic tumour segmentation in H&E-stained whole-slide images of the pancreas