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

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...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Toxicologic pathology Jg. 53; H. 5; S. 456
Hauptverfasser: Funk, Juergen, Clement, Gregoire, Togninalli, Matteo, Cohen, Yaniv, Albrecht, Tom, Sullivan, Ruth, Pous, Josep Arus, Tecilla, Marco, Romero-Palomo, Fernando, Abramowski, Amadeusz, D'Annunzio, Angelo, Li, Yun Yvonna, Nguyen, Trung, Hu, Fangyao, Schumacher, Vanessa
Format: Journal Article
Sprache:Englisch
Veröffentlicht: United States 01.07.2025
Schlagworte:
Algorithms
Animals
Deep Learning
Liver - pathology
Multiple-Instance Learning Algorithms
Rats
Supervised Machine Learning
Toxicity Tests - methods
toxicology
digital pathology
liver
multiple instance learning
transformer
artificial intelligence
generalized lesion detection
ISSN:1533-1601, 1533-1601
Online-Zugang:Weitere Angaben
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung: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.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:1533-1601
1533-1601
DOI:10.1177/01926233251339653