PulseJournal ClubResearchersJournalsExplore
Instagram
HomeJournal ClubExplore
Synapse
⌘+K
Synapse
June 18, 2026Virchows ArchivOpen Access

High performance deep-learning model for the diagnosis of auto-immune hepatitis based on histological whole slide images

View Full Paper
Ask AI
Bookmark
Share

Authors

PAPierre AllaumeNRNoémie RabilloudASAnna Sessa

Discussion

Loading...

Member takes

Overview

Randomized trial demonstrates effective AI-based diagnosis of autoimmune hepatitis with comparability to expert pathologists.

Key Points

  • The aim is to develop a deep-learning model for accurate diagnosis of autoimmune hepatitis using histological images.
  • Trained a deep-learning model using 170 untreated AIH and 232 control cases.
  • Tested the model on an external dataset of 61 AIH and 124 controls.
  • Assessed performance metrics including AUC, sensitivity, specificity, and F1-score.
  • Achieved AUC of 0.92 ± 0.02 on the training dataset and AUC of 0.74 on the external dataset.
  • Sensitivity of 0.86 and specificity of 0.76 in prospective testing.
  • Provided interpretability by retrieving the five most predictive image tiles.

Cite This Study

Allaume et al. (2026) studied this question.

synapsesocial.com/papers/6a338e14630953a74978ecf0https://doi.org/10.1007/s00428-026-04621-z
View Full Paper
Ask AI
Bookmark
Share