February 27, 2025 This image presents heatmaps highlighting the areas LILAC focuses on when making predictions. The top section illustrates LILAC’s prediction of changes in the Clinical Dementia Rating Scale Sum of Boxes, a dementia scoring system, while the bottom section accounts for age and sex as additional factors. The differences in the highlighted regions...
Tag: <span>medical images</span>
Post
Ultrasound selfies: With little training, patients could produce high-quality medical images at home
by National Institutes of Health Study participants scanned themselves with ultrasound at home as part of a study aimed at uncovering whether patients could produce high-quality diagnostic images outside of the clinic. Credit: Duggan et al., CC BY 4.0 license One day, the ultrasound equipment that health care professionals use for essential diagnostic imaging may no longer be...
Post
Artificial intelligence predicts patients’ race from their medical images
by Rachel Gordon, Massachusetts Institute of Technology Samples of the images after low-pass filters and high-pass filters in MXR dataset. HPF=high-pass filtering. LPF=low-pass filtering. MXR=MIMIC-CXR dataset. Credit: The Lancet Digital Health (2022). DOI: 10.1016/S2589-7500(22)00063-2 The miseducation of algorithms is a critical problem; when artificial intelligence mirrors unconscious thoughts, racism, and biases of the humans who generated these algorithms,...
Post
Artificial intelligence spots anomalies in medical images
Scientists from Skoltech, Philips Research, and Goethe University Frankfurt have trained a neural network to detect anomalies in medical images to assist physicians in sifting through countless scans in search of pathologies. Reported in IEEE Access, the new method is adapted to the nature of medical imaging and is more successful in spotting abnormalities than...