A novel synthetic intelligence (AI) utility able to diagnosing endocrine cancers with velocity and accuracy is being introduced Sunday at ENDO 2025, the Endocrine Society’s annual assembly in San Francisco, Calif.
The analysis, introduced by Jansi Rani Sethuraj, B.S.N., R.N., C.C.R.N., from the College of Texas Well being Science Heart at Houston, introduces a universally accessible and computationally environment friendly AI utility. This AI utility goals to democratize expert-level most cancers diagnostics, making them accessible on fundamental internet-connected units, together with smartphones.
Endocrine cancers, affecting organs such because the thyroid, ovary, pancreas, pituitary, and adrenal glands, pose distinctive challenges attributable to their advanced hormonal results and tough diagnostic profiles. With an estimated 10 million cancer-related deaths every year, the necessity for revolutionary, scalable diagnostic options is imminent.
This new AI-powered instrument leverages superior deep studying architectures, equivalent to EfficientNet and ResNet, to investigate various medical information, together with computerized tomography (CT) scans, magnetic resonance imaging (MRI), ultrasonography (USG), and histopathology pictures, enabling complete and correct most cancers detection.
In response to Sethuraj, the AI fashions demonstrated distinctive diagnostic accuracy, reportedly exceeding 99% in sure validation datasets throughout a number of endocrine most cancers sorts. These outcomes align with latest research exhibiting AI can obtain excessive accuracy in endocrine tumor classification, although real-world efficiency might differ.
Two researchers, Ramya Elangovan and Kavin Elangovan of AIM Physician in Houston, Texas, curated anonymized endocrine most cancers picture datasets representing various populations spanning six continents. These pictures have been used to coach and validate deep studying fashions able to detecting and staging a number of endocrine cancers with very excessive accuracy.
The applying’s reliability and value have been independently evaluated by well being care professionals from a number of worldwide establishments, highlighting its potential for world applicability. The applying’s streamlined design permits fast picture evaluation, processing every picture in beneath one second, even on units with restricted computational sources.
By enabling clinicians and first care suppliers to entry expert-level diagnostic assist wherever, this expertise has the potential to cut back diagnostic errors, speed up remedy selections, and enhance affected person outcomes globally, particularly in resource-limited settings.
“By democratizing entry to superior diagnostics, this AI innovation marks a paradigm shift in most cancers care, providing hope for earlier detection, extra exact remedy, and higher survival for sufferers going through endocrine malignancies,” mentioned the chief mentor of this challenge, Elangovan Krishnan, M.B., B.S., P.G.D.H.M., M.Tech., M.S., Ph.D., of AIM Physician.
“This AI-powered utility can ship quick, dependable, and reasonably priced endocrine most cancers diagnostics to anybody, wherever, thereby serving to to shut gaps in most cancers care and advance well being fairness worldwide.”
The examine is titled, “A Universally Accessible, Computationally Environment friendly, Synthetic Intelligence Powered Software for Diagnosing Endocrine Cancers,” and it is going to be introduced on Sunday, July 13.
Quotation:
AI-powered utility permits clinicians to diagnose endocrine cancers sooner and extra precisely (2025, July 13)
retrieved 13 July 2025
from https://medicalxpress.com/information/2025-07-ai-powered-application-enables-clinicians.html
This doc is topic to copyright. Aside from any truthful dealing for the aim of personal examine or analysis, no
half could also be reproduced with out the written permission. The content material is offered for info functions solely.
