Harvard Medical School Researchers Develop AI-Assisted Imaging Method for Tissue Analysis
Researchers at Harvard Medical School's Blavatnik Institute have developed a new AI-assisted imaging pipeline, named NoR-AI, that significantly advances the study of tissue by overcoming limitations of traditional histopathology. For centuries, tissue analysis has relied on methods that can distort features and remove lipids and water-soluble materials, leading to an incomplete view. NoR-AI combines a custom microscopy method, Normalized Raman Imaging (NoRI), with AI-powered image analysis to capture high-quality, quantitative images that include lipids, proteins, and water content. This technique requires minimal tissue preprocessing and can be completed in 30 minutes, a stark contrast to the several days required for traditional biopsy analysis. In a study published in Proceedings of the National Academy of Sciences, the team used NoR-AI to identify previously unrecognized fine-scale changes in a mouse model of acute kidney injury, characterizing and quantifying known features while uncovering new aspect...