AI can improve ovarian cancer diagnoses
Peer-Reviewed Publication
Updates every hour. Last Updated: 1-May-2025 11:08 ET (1-May-2025 15:08 GMT/UTC)
A new international study led by researchers at Karolinska Institutet in Sweden shows that AI-based models can outperform human experts at identifying ovarian cancer in ultrasound images. The study is published in Nature Medicine.
A new study conducted at the Scojen Institute for Synthetic Biology at Reichman University’s Dina Recanati School of Medicine announces the launch of the ChiTaRS 8.0 database, the world’s largest collection of chimeric genes (gene fusions) found in humans with cancer and other chronic diseases. The project, led by Dr. Dr. Milana Frenkel-Morgenstern, head of the Genomics and Computational Biology Lab, together with doctoral students Dylan D'Souza and Olwumi Giwa of the Azrieli Faculty of Medicine at Bar-Ilan University, marks a significant step in advancing the understanding of chimeric genes and supporting scientists and clinicians in their pursuit to develop more effective and personalized cancer treatments.
The Spanish National Cancer Research Centre (CNIO) and the Spanish National Research Council (CSIC) are part of the international consortium NanoBright, which has developed this new tool.
The probe reaches deep into the brain without causing appreciable damage, making it minimally invasive. It projects an ultra-thin beam of light.
The light from the probe illuminates nerve tissue and provides information about its chemical composition. This makes it possible to detect molecular changes caused by tumours or other lesions.
This "molecular flashlight" is currently a research tool, but researchers hope it will be used on patients in the future. The study is published in Nature Methods.
Monitoring the changes caused in the brain at the molecular level by cancer and other neurological pathologies in a non-invasive way is one of the great challenges of biomedical research. A new technique, still in the experimental stage, achieves this by introducing light into the brains of mice using a very thin probe. The innovation, which is published today in the journal Nature Methods, is ledby an international team including groups from the Spanish National Research Council (CSIC) and the Spanish National Cancer Research Centre (CNIO).
Pioneering research has unveiled a powerful new tool in the fight against skin cancer, combining cutting-edge artificial intelligence with deep learning to enhance the precision of skin lesion classification. This innovative approach, which utilizes a weighted ensemble of transfer learning models and test time augmentation (TTA), promises to significantly improve the accuracy of skin cancer diagnosis. By distinguishing between benign and malignant lesions with remarkable precision, this research could pave the way for earlier, more effective treatments and potentially save countless lives.
MUSC Hollings Cancer Center researcher Aguirre de Cubas, Ph.D., is a recipient of the Department of Defense Academy of Kidney Cancer Investigators Early Career Scholar Award. With funding from the award, De Cubas will study whether the release of mitochondrial DNA helps the immune system to see and kill kidney tumors better, with a view to developing a therapeutic that could be paired with immune checkpoint inhibitors, now a mainstay of treatment, to improve outcomes.
Meta-analysis of past studies conducted by University of Utah researchers calculates reduced risk of certain cancers for coffee and tea drinkers.