Authors: Pouria Yazdian Anari, Fiona Obiezu, Nathan Lay, Fatemeh Dehghani Firouzabadi, Aditi Chaurasia, Mahshid Golagha, Shiva Singh, Fatemeh Homayounieh, Aryan Zahergivar, Stephanie Harmon, Evrim Turkbey, Rabindra Gautam, Kevin Ma, Maria Merino, Elizabeth C. Jones, Mark W. Ball, W. Marston Linehan, Baris Turkbey, Ashkan A. Malayeri
Published on: February 08, 2024
Impact Score: 8.15
Arxiv code: Arxiv:2402.05817
Summary
- What is new: The use of the latest YOLO V7 object detection method specifically for enhancing kidney detection in medical imaging, with a focus on renal cell carcinoma (RCC) and normal kidneys.
- Why this is important: Need for improved accuracy in kidney and tumor detection within medical imaging to support diagnostics.
- What the research proposes: A modified YOLO V7 model trained and tested on a comprehensive dataset of MRI scans with various subtypes of RCC and normal kidneys, employing a semi-supervised approach.
- Results: Achieved high accuracy with a PPV of up to 0.97, sensitivity up to 0.98, and mean average precision (mAP) up to 0.95.
Technical Details
Technological frameworks used: YOLO V7
Models used: Modified YOLO V7 for kidney detection
Data used: 5657 MRI scans for 1084 patients, including 326 patients with 1034 tumors
Potential Impact
Medical imaging, Health diagnostics companies, AI technology firms in healthcare, Radiology departments
Want to implement this idea in a business?
We have generated a startup concept here: RenalScan AI.
Leave a Reply