← Back to the feed
AI & softwareResearch findings

Digital Pathology-Based AI Model Shows Promise in OKC Diagnosis and Prognosis

Original published 2024.02.26 09:00 KSTAdded to Blackdeck 2026.11.09 21:05 KST

What has changed?

Development of patch-level and whole slide image-based AI models using Inception_v3 network and integrated machine learning algorithms

Key points

  1. A digital pathology-based AI model was developed for diagnosis and prognosis of odontogenic keratocyst (OKC)
  2. Both patch-level and whole slide image models were integrated to improve diagnostic performance
  3. The model achieved high accuracy in diagnosis (AUC 0.935) and prognosis (AUC 0.840)

Connect it to your work

AI-generated features show correlation with pathological findings, indicating interpretability potential

What remains unproven

This research note is based on an abstract; check the original for test conditions and application scope.

Originals used for this note

Links open the original publisher in a new tab.

  1. medicineDigital pathology-based artificial intelligence models for differential diagnosis and prognosis of sporadic odontogenic keratocysts.