The Procia retrospective study describes the potential of AI in diagnosing melanoma, among other diseases | Tech Rasta


Digital and computational pathology solutions provider Proscia on Tuesday announced the results of a retrospective study highlighting the potential of artificial intelligence (AI) to improve diagnostic accuracy for melanoma and other diseases with less pathologist coordination.

“Our technology relies on self-supervised learning to recognize incredibly subtle patterns, demonstrating the power of one of the most advanced approaches in AI,” Sam Grullan, principal AI scientist at Procia and lead author of the study, said in a statement.

Procia said the study, presented at the European Conference on Computer Vision (ECCV) 2022, demonstrated the AI’s performance on 1,412 full-slide images (WSIs) of 1,412 skin biopsies.

Each image was evaluated by three to five dermatologists to establish a concordance rate. An R2 correlation of 0.51 was demonstrated between AI- and dermatopathologist-based estimates, Procia added.

The company said it will conduct additional research on the potential benefits of AI, such as reducing the false diagnosis rate for difficult cases, speeding up results turnaround time for difficult results, and reducing costs and suffering for patients.

AI will also be expanded to other diagnoses that exhibit low pathologist agreement, such as breast cancer staging and Gleason grading of prostate cancer, Procia said.



Source link