Authors: Kanchan Poudel, Lisasha Poudel, Prabin Raj Shakya, Atit Poudel, Archana Shrestha, Bishesh Khanal
Published on: March 18, 2024
Impact Score: 8.0
Arxiv code: Arxiv:2403.11936
Summary
- What is new: A smartphone-based AI system for cervical cancer screening that doesn’t require separate integrated devices, using a novel image acquisition protocol and deep learning to assist nurses in resource-constrained settings.
- Why this is important: The highly subjective nature of the Visual Inspection with Acetic Acid (VIA) test for cervical cancer screening in low-resource settings and the lack of expert Gynecologists.
- What the research proposes: A robust smartphone-based AI-assisted system with a new protocol for quality image acquisition and a deep-learning-based classification model to identify precancerous lesions.
- Results: The system shows promising results in assisting VIA screening by nurses, using images captured by smartphones, and offers a path for large-scale data collection and validation.
Technical Details
Technological frameworks used: Deep learning
Models used: Classification model
Data used: Images from 1,430 women
Potential Impact
Healthcare in LMICs, mobile health tech companies, AI-driven medical imaging ventures
Want to implement this idea in a business?
We have generated a startup concept here: CerviScan AI.
Leave a Reply