Training AI’s view on clinically relevant areas improves medical image analysis

Credit: Journal of Biomedical Informatics (2024). DOI: 10.1016/j.jbi.2024.104673 Duke-NUS Quantitative Biology and Medicine Ph.D. candidate Yuan Han has developed a new method to improve the accuracy of AI when it is used to diagnose a collapsed lung, or pneumothorax, by limiting the area of a chest X-ray that AI uses when interpreting the image. Working with radiologists to understand how they read such X-rays, Yuan created a simple filter or template that is applied over the X-ray to direct the AI’s analysis. With its sharpened focus, Yuan’s model reduced the Read More

Related posts:

  1. Training AI models to answer ‘what if?’ questions could improve medical treatments
  2. Comparative analysis shows FAPI PET/CT improves staging of newly diagnosed breast cancer
  3. Off-the-shelf wearable trackers provide clinically-useful information for patients with heart disease
  4. The 7 Best BCAA Supplements In 2025 — Our Expert View
  5. Taylor Swift’s impact on fans’ body image attitudes is mostly positive, research shows
  6. Study shows 60% of women with disabilities view cannabis as a ‘harmless’ drug
  7. Skip the fancy perks—better staff well-being could be as simple as the view from the office window
  8. Funding instability plagues program that brings docs to underserved areas

Leave a Reply

Your email address will not be published. Required fields are marked *