Benchmarking Hierarchical Image Pyramid Transformer for the Classification of Colon Biopsies and Polyps Histopathology Images

Benchmarking Hierarchical Image Pyramid Transformer for the Classification of Colon Biopsies and Polyps Histopathology Images

Training neural networks with high-quality pixel-level annotation in histopathology whole-slide images (WSI) is an expensive process due to gigapixel resolution of WSIs. However, recent advances in self-supervised learning have shown that highly descriptive image representations can be learned witho...

Full description

Saved in:
Bibliographic Details
Published in:2024 IEEE International Symposium on Biomedical Imaging (ISBI) pp. 1 - 4
Main Authors: Contreras, Nohemi S. Leon, Grisi, Clement, Aswolinskiy, Witali, Vatrano, Simona, Fraggetta, Filippo, Nagtegaal, Iris, D'Amato, Marina, Ciompi, Francesco
Format: Conference Proceeding
Language:English
Published: IEEE 27-05-2024
Subjects:
Annotations
Biological system modeling
Biopsy
Colon
colon biopsies
Computational pathology
Data models
Histopathology
self-supervision
Transformers
vision transformers
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Training neural networks with high-quality pixel-level annotation in histopathology whole-slide images (WSI) is an expensive process due to gigapixel resolution of WSIs. However, recent advances in self-supervised learning have shown that highly descriptive image representations can be learned without the need for annotations. We investigate the application of the recent Hierarchical Image Pyramid Transformer (HIPT) model for the specific task of classification of colorec-tal biopsies and polyps. After evaluating the effectiveness of TCGA-learned features in the original HIPT model, we incorporate colon biopsy image information into HIPT's pretraining using two distinct strategies: (1) fine-tuning HIPT from the existing TCGA weights and (2) pretraining HIPT from random weight initialization. We compare the performance of these pretraining regimes on two colorectal biopsy classification tasks: binary and multiclass classification.
ISSN:1945-8452
DOI:10.1109/ISBI56570.2024.10635841