Enabling Early Stage Breast Cancer Detection Using AI
summary
A portable, non‑contact screening system combines thermal imaging + AI that extracts 117 handcrafted features from five thermograms, classifies with classical machine learning and produces a three‑page PDF report. Validated on over 6,000 patients with three clinical papers, it shows ~95% sensitivity, ~27% higher accuracy than mammography for dense breasts and under‑45 women, and detected tumors as small as 4–5 mm in multiple cases. Deployed in 21 hospitals across nine cities and approved for use in India, it runs on lightweight hardware and local nursing staff.
AI-written summary · about
chapters (7)
- 0:00The breast cancer crisis
- 2:08Barriers to screening
- 4:44Limitations of mammography
- 8:22The NirAmai solution
- 13:52How the technology works
- 21:37Deployment and recognition
- 26:39Q&A session
related talks
28mHow AI Can Help Detect Breast Cancer
01h 02mArtificial Intelligence for Early Detection and Diagnosis of Cervical Cancer
24mBreast cancer detection with IBM PowerAI Vision
44mDay 2 Keynote
15mCan AI Finally Solve India’s Cancer Crisis?
29mCancer diagnostics enabled by machines: finding and classifying single tumor....
18mCan AI make us smarter than cancer
24mMachine Learning & Medical Imaging: The Future of Early Cancer Detection