EndoInsights : Machine Learning Powered Insights for Better Endometriosis Care

Rakesh M. R., Shallen Crissle Sequeira, Amrutha G Y, Sparsha S Shriyan, Vaishnavi P Poojari
In: 2025 International Conference on Intelligent Systems and Pioneering Innovations in Robotics and Electric Mobility (INSPIRE) · 2025 · pp. 554–559 · doi:10.1109/inspire67328.2025.11300576 · W7117472823
OA: closed CC0
View on OpenAlex View at publisher
⚙ AI-generated summary by gemini-2.5-flash-lite, 2026-06-07 ⓘ

This study introduces EndoInsights, a deep learning framework using CNNs and ViTs to analyze ultrasound images for faster, more accurate, and accessible endometriosis diagnosis without invasive procedures.

One-sentence paraphrase of the abstract; not a substitute for reading it. No clinical advice. How this works

Abstract

Endometriosis is a widely prevalent condition that continues to be overlooked or misdiagnosed in women, primarily because of the limitations of standard ultrasound imaging and the heavy dependence on invasive diagnostic procedures. To tackle this, our project presents a smart diagnostic solution powered by artificial intelligence. At its core is a unified deep learning framework that integrates the capabilities of Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) to better analyze ultrasound images. Designed to run efficiently on regular CPUs, the system can be easily deployed even in resource-constrained clinical settings. It features robust preprocessing techniques, performs real-time lesion detection, and uses SmoothGrad to visually explain how predictions are made. With this approach, we aim to make endometriosis diagnosis faster, more accurate, and accessible without the need for invasive procedures.

My notes (saved in your browser only)

Condition tags

endometriosis

Citation neighborhood (2-hop)

Papers in the corpus that this work cites (lower rings, blue) and that cite this one (upper rings, green). Dot size scales with the paper's in-corpus citation count — bigger dot = more influential within the endo/adeno field. Click a dot to open that paper. Outer rings show 2-hop neighbours — papers reached through the immediate citers/citees. [ collapse to 1-hop ]

References (13)

Source provenance

openalex
last seen: 2026-06-10T17:14:06.276822+00:00
unpaywall
last seen: 2026-10-14T06:23:58.021457+00:00
License: CC0 · commercial use OK