Comparison of an Attention-Based Multiple Instance Learning (MIL) With a Visual Transformer Model: Two Weakly Supervised Deep Learning (DL) Algorithms for the Detection of Histopathologic Lesions in the Rat Liver to Distinguish Normal From Abnormal
Toxicologic Pathology · 2025-07 · 53 (5) · 456-478
DOI: 10.1177/01926233251339653 ↗Kurz gefasst
Vergleichsstudie in der Zeitschrift Toxicologic Pathology, online erschienen am 30.05.2025. Verfasst von Juergen Funk und 14 weiteren Autor:innen. Beteiligte Einrichtung: F Hoffmann-La Roche Ltd, Basel, Switzerland. Hauptthemen laut MEDLINE: Deep Learning, Liver, Supervised Machine Learning. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 39 Literaturangaben.
Abstract (Originalsprache)
The histopathologic evaluation of regulatory toxicity studies using artificial intelligence (AI) has the potential to increase study efficiency. For example, AI could initially identify and exclude all organs without histopathologic lesions, allowing pathologists to focus solely on evaluating organs with identified lesions. In this study, whole slide images (WSIs) of liver sections from 58 different rat toxicity studies were collected, along with their corresponding histopathologic lesion diagnoses. Each WSI was labeled as either “lesion” or “no lesion” based on the presence or absence of reported histopathologic lesions. Multiple instance learning (MIL) approaches, including a transformer variant, were tested to predict lesions within a weakly supervised framework. Both methods achieved acceptable to excellent area under the receiver operating characteristic curve (AUROC) scores. Heatmap overlays were employed to visually assess the MIL model’s effectiveness in detecting lesions, confirming the accuracy of targeted areas on the WSIs. In addition, using transfer learning principles, the MIL model initially developed for liver WSIs was adapted to kidney WSIs, demonstrating the model’s versatility. This study showcases the application of weakly supervised learning for lesion detection in rat WSIs from toxicity studies, with the potential to significantly enhance the efficiency of the histopathologic evaluation process.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- F Hoffmann-La Roche Ltd, Basel, Switzerland.
- Visium, Zurich, Switzerland.
- Genentech Inc, South San Francisco, California, USA.
ORCID-Profile: Juergen Funk, Gregoire Clement, Ruth Sullivan, Fernando Romero-Palomo, Fangyao Hu, Vanessa Schumacher
Zitieren
APA
Funk, J., Clement, G., Togninalli, M., Cohen, Y., Albrecht, T., Sullivan, R., Pous, J. A., Tecilla, M., Romero-Palomo, F., Abramowski, A., D'Annunzio, A., Li, Y. Y., Nguyen, T., Hu, F., & Schumacher, V. (2025). Comparison of an Attention-Based Multiple Instance Learning (MIL) With a Visual Transformer Model: Two Weakly Supervised Deep Learning (DL) Algorithms for the Detection of Histopathologic Lesions in the Rat Liver to Distinguish Normal From Abnormal. Toxicologic Pathology, 53(5), 456-478. https://doi.org/10.1177/01926233251339653
Vancouver
Funk J, Clement G, Togninalli M, Cohen Y, Albrecht T, Sullivan R, et al. Comparison of an Attention-Based Multiple Instance Learning (MIL) With a Visual Transformer Model: Two Weakly Supervised Deep Learning (DL) Algorithms for the Detection of Histopathologic Lesions in the Rat Liver to Distinguish Normal From Abnormal. Toxicologic Pathology. 2025;53(5):456-478. doi:10.1177/01926233251339653
BibTeX
@article{Funk2025,
author = {Funk, Juergen and Clement, Gregoire and Togninalli, Matteo and Cohen, Yaniv and Albrecht, Tom and Sullivan, Ruth and Pous, Josep Arus and Tecilla, Marco and Romero-Palomo, Fernando and Abramowski, Amadeusz and D'Annunzio, Angelo and Li, Yun Yvonna and Nguyen, Trung and Hu, Fangyao and Schumacher, Vanessa},
title = {Comparison of an Attention-Based Multiple Instance Learning (MIL) With a Visual Transformer Model: Two Weakly Supervised Deep Learning (DL) Algorithms for the Detection of Histopathologic Lesions in the Rat Liver to Distinguish Normal From Abnormal},
journal = {Toxicologic Pathology},
year = {2025},
volume = {53},
number = {5},
pages = {456--478},
doi = {10.1177/01926233251339653}
}
EUVIMED