HistoEM: A Pathologist-Guided and Explainable Workflow Using Histogram Embedding for Gland Classification
Modern Pathology · 2024
DOI: 10.1016/j.modpat.2024.100447 ↗Kurz gefasst
Fachartikel in der Zeitschrift Modern Pathology, 2024. Verfasst von Alessandro Ferrero und 8 weiteren Autor:innen. Beteiligte Einrichtung: Scientific Computing and Imaging Institute, University of Utah, Salt Lake City, Utah. Hauptthemen laut MEDLINE: Pathologists, Prostatic Neoplasms. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 56 Literaturangaben. Gefördert von: U.S. Department of Defense, U.S. Department of Veterans Affairs, Department of Defense Prostate Cancer Research Program.
Abstract (Originalsprache)
Pathologists have, over several decades, developed criteria for diagnosing and grading prostate cancer. However, this knowledge has not, so far, been included in the design of convolutional neural networks (CNN) for prostate cancer detection and grading. Further, it is not known whether the features learned by machine-learning algorithms coincide with diagnostic features used by pathologists. We propose a framework that enforces algorithms to learn the cellular and subcellular differences between benign and cancerous prostate glands in digital slides from hematoxylin and eosin-stained tissue sections. After accurate gland segmentation and exclusion of the stroma, the central component of the pipeline, named HistoEM, utilizes a histogram embedding of features from the latent space of the CNN encoder. Each gland is represented by 128 feature-wise histograms that provide the input into a second network for benign vs cancer classification of the whole gland. Cancer glands are further processed by a U-Net structured network to separate low-grade from high-grade cancer. Our model demonstrates similar performance compared with other state-of-the-art prostate cancer grading models with gland-level resolution. To understand the features learned by HistoEM, we first rank features based on the distance between benign and cancer histograms and visualize the tissue origins of the 2 most important features. A heatmap of pixel activation by each feature is generated using Grad-CAM and overlaid on nuclear segmentation outlines. We conclude that HistoEM, similar to pathologists, uses nuclear features for the detection of prostate cancer. Altogether, this novel approach can be broadly deployed to visualize computer-learned features in histopathology images.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Scientific Computing and Imaging Institute, University of Utah, Salt Lake City, Utah.
- Department of Pathology, University of Utah, Salt Lake City, Utah.
- Division of Epidemiology, University of Utah, Salt Lake City, Utah.
- Department of Pathology, University of Utah, Salt Lake City, Utah. Electronic address: Beatrice.Knudsen@path.utah.edu.
Förderung
- U.S. Department of Defense
- U.S. Department of Veterans Affairs
- Department of Defense Prostate Cancer Research Program
Zitieren
APA
Ferrero, A., Ghelichkhan, E., Manoochehri, H., Ho, M. M., Albertson, D. J., Brintz, B. J., Tasdizen, T., Whitaker, R. T., & Knudsen, B. S. (2024). HistoEM: A Pathologist-Guided and Explainable Workflow Using Histogram Embedding for Gland Classification. Modern Pathology. https://doi.org/10.1016/j.modpat.2024.100447
Vancouver
Ferrero A, Ghelichkhan E, Manoochehri H, Ho MM, Albertson DJ, Brintz BJ, et al. HistoEM: A Pathologist-Guided and Explainable Workflow Using Histogram Embedding for Gland Classification. Modern Pathology. 2024. doi:10.1016/j.modpat.2024.100447
BibTeX
@article{Ferrero2024,
author = {Ferrero, Alessandro and Ghelichkhan, Elham and Manoochehri, Hamid and Ho, Man Minh and Albertson, Daniel J and Brintz, Benjamin J and Tasdizen, Tolga and Whitaker, Ross T and Knudsen, Beatrice S},
title = {HistoEM: A Pathologist-Guided and Explainable Workflow Using Histogram Embedding for Gland Classification},
journal = {Modern Pathology},
year = {2024},
doi = {10.1016/j.modpat.2024.100447}
}
EUVIMED