MedSight AI Research Lab

Scientists train deep-learning models to scrutinize biopsies like a human pathologist

A team of researchers developed a method to annotate biopsy image data with eye-tracking devices, reducing the burden on pathologists. The resulting AI model achieved an accuracy of 96.3% and surpassed human pathologists' performance in diagnosing skin lesions.

SourceMedSight AI Research Lab·JournalNature Communications·DateAug 21, 2025

Machine learning to aid in classification of pathological images for disease diagnosis

A new machine learning technique called Dual-Channel Prototype Network (DCPN) can efficiently classify pathological images with limited data, which is essential for diagnosing rare diseases. The DCPN uses few-shot learning to make predictions and achieves noticeable advantages over other methods on three public datasets.

SourceMedSight AI Research Lab·JournalIEEE Journal of Biomedical and Health Informatics·DateJul 4, 2024