A GPT-4o-powered AI system enhances early-stage ovarian cancer diagnosis using pelvic CT exams.
Key Details
- 1Study published in Annals of Surgical Oncology; team led by Shimin Zhang, MD.
- 2GPT-4o trained to identify four key CT features linked to ovarian cancer malignancy.
- 3Dataset included 479 patients with confirmed benign or early malignant ovarian lesions.
- 4AI achieved diagnostic accuracies of 80.8%, 79.1%, and 93.3% across lesion identification, feature recognition, and malignancy status, respectively.
- 5Clinician reliability ratings for AI detection: 4.2–4.3 out of 5 across key features.
- 6AI assistance improved diagnosis accuracy for gynecologic oncologists (from 67.9% to 78.1%).
Why It Matters
This approach could reduce diagnostic variability and support less experienced clinicians by improving the consistency and accuracy of CT-based ovarian cancer diagnosis. Earlier detection enables better patient outcomes and survival rates.
Source
AuntMinnie
Related News
•AuntMinnie
Study: Computer Vision Models Best LLMs in Chest CT Breast Abnormality Detection
Computer vision models (CVMs) surpass large language models (LLMs) in accurately labeling incidental breast abnormalities on chest CT scans.
•Cardiovascular Business
Radiology Maintains Lead in FDA-Cleared AI Algorithms, Cardiology Follows
Radiology remains the top specialty for FDA-cleared AI, with cardiology as a strong second, particularly in cardiovascular imaging.
•AuntMinnie
Deep Learning Models Rival Radiologists for Pancreatic Cancer Detection on CT
Deep-learning models achieved comparable or superior accuracy to experienced radiologists in detecting pancreatic cancer on CT scans, especially for small tumors.