Beyond Multiple Instance Learning: Full Resolution All-In-Memory End-To-End Pathology Slide Modeling

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Campanella, Gabriele, Fluder, Eugene, Zeng, Jennifer, Vanderbilt, Chad, Fuchs, Thomas J.
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866929353294610432
author Campanella, Gabriele
Fluder, Eugene
Zeng, Jennifer
Vanderbilt, Chad
Fuchs, Thomas J.
author_facet Campanella, Gabriele
Fluder, Eugene
Zeng, Jennifer
Vanderbilt, Chad
Fuchs, Thomas J.
contents Artificial Intelligence (AI) has great potential to improve health outcomes by training systems on vast digitized clinical datasets. Computational Pathology, with its massive amounts of microscopy image data and impact on diagnostics and biomarkers, is at the forefront of this development. Gigapixel pathology slides pose a unique challenge due to their enormous size and are usually divided into tens of thousands of smaller tiles for analysis. This results in a discontinuity in the machine learning process by separating the training of tile-level encoders from slide-level aggregators and the need to adopt weakly supervised learning strategies. Training models from entire pathology slides end-to-end has been largely unexplored due to its computational challenges. To overcome this problem, we propose a novel approach to jointly train both a tile encoder and a slide-aggregator fully in memory and end-to-end at high-resolution, bridging the gap between input and slide-level supervision. While more computationally expensive, detailed quantitative validation shows promise for large-scale pre-training and fine-tuning of pathology foundation models.
format Preprint
id arxiv_https___arxiv_org_abs_2403_04865
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Beyond Multiple Instance Learning: Full Resolution All-In-Memory End-To-End Pathology Slide Modeling
Campanella, Gabriele
Fluder, Eugene
Zeng, Jennifer
Vanderbilt, Chad
Fuchs, Thomas J.
Image and Video Processing
Computer Vision and Pattern Recognition
Artificial Intelligence (AI) has great potential to improve health outcomes by training systems on vast digitized clinical datasets. Computational Pathology, with its massive amounts of microscopy image data and impact on diagnostics and biomarkers, is at the forefront of this development. Gigapixel pathology slides pose a unique challenge due to their enormous size and are usually divided into tens of thousands of smaller tiles for analysis. This results in a discontinuity in the machine learning process by separating the training of tile-level encoders from slide-level aggregators and the need to adopt weakly supervised learning strategies. Training models from entire pathology slides end-to-end has been largely unexplored due to its computational challenges. To overcome this problem, we propose a novel approach to jointly train both a tile encoder and a slide-aggregator fully in memory and end-to-end at high-resolution, bridging the gap between input and slide-level supervision. While more computationally expensive, detailed quantitative validation shows promise for large-scale pre-training and fine-tuning of pathology foundation models.
title Beyond Multiple Instance Learning: Full Resolution All-In-Memory End-To-End Pathology Slide Modeling
topic Image and Video Processing
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2403.04865