{"id":"CU26244","slug":"deep-learning-based-synthesis--CU26244","source":{"id":"CU26244","dataset":"techtransfer","title":"Deep-learning-based synthesis of PET maps from MRI for Alzheimer’s disease detection","description_":"<p>This technology is a deep-learning-based model that synthesizes positron emission tomography (PET) maps of pathological burden from MRI to detect Alzheimer’s disease.</p>\r\r<h2>Unmet Need: Safe, accessible methods for PET imaging for Alzheimer’s disease detection</h2>\r\r<p>Positron emission tomography (PET) is considered the gold standard molecular measure of Alzheimer’s pathology. However, this method is expensive, not universally available, and exposes patients to ionizing radiation. In contrast, T1-weighted (T1w) MRI is widely available, cost-effective, and does not expose patients to ionizing radiation. However, T1w MRI is unable to generate standardized uptake value ratio (SUVR) maps of pathological burden, which is necessary for determining the molecular pathology of Alzheimer’s disease. </p>\r\r<h2>The Technology: Deep-learning-based model for generating synthetic PET maps from MRI</h2>\r\r<p>This technology is a deep-learning-based framework that generates synthetic PET maps from T1w MRI for the detection of Alzheimer’s disease. Structural, morphometric, and vascular features are integrated from MRI to synthesize PET SUVR maps. This hybrid deep learning architecture achieves high concordance with ground-truth PET imaging and improves performance when vascular and morphometric priors are included. </p>\r\r<h2>Applications:</h2>\r\r<ul>\r<li>Diagnostic tool for Alzheimer’s disease</li>\r<li>Early risk stratification</li>\r<li>Longitudinal disease monitoring</li>\r<li>Therapeutic response tool</li>\r</ul>\r\r<h2>Advantages:</h2>\r\r<ul>\r<li>Cost-effective</li>\r<li>Non-invasive and non-ionizing</li>\r<li>Model input derived from widely available MRI medical equipment</li>\r<li>High concordance with ground-truth PET imaging</li>\r<li>Improved performance with vascular and morphometric priors</li>\r</ul>\r\r<h2>Lead Inventor:</h2>\r\r<p><a href=\"https://mr.research.columbia.edu/content/jia-guo\">Jia Guo, Ph.D.</a></p>\r\r<h2>Related Publications:</h2>\r\r<h2>Tech Ventures Reference:</h2>\r\r<ul>\r<li><p>IR CU26244</p></li>\r<li><p>Licensing Contact: <a href=\"mailto:techtransfer@columbia.edu\">Jerry Kokoshka</a> </p></li>\r</ul>\r","tags":["Ionizing radiation","Morphometrics","Non-ionizing radiation","Pathology","Positron emission tomography"],"file_number":"CU26244","collections":[],"meta_description":"Synthetic PET maps from MRI enable noninvasive Alzheimer's detection, matching PET accuracy while reducing cost and radiation.","apriori_judge_output":"{\"scores\":{\"novelty\":4.0,\"potential_impact\":4.0,\"readiness\":4.0,\"scalability\":3.0,\"timeliness\":4.0},\"weighted_score\":3.9,\"risks\":[\"Requires external validation across diverse populations\",\"Regulatory considerations for clinical adoption\",\"Data privacy and governance for MRI-derived proxies\",\"Need for prospective clinical utility studies\"],\"one_sentence_take\":\"High novelty and near-term readiness with strong potential impact, but moderate scalability and some regulatory/validation hurdles remain before widespread deployment.\"}","inventors":["Jia Guo"],"manager":"Jerry Kokoshka","depts":["Psychiatry"],"divs":["Columbia University Medical Center (CUMC)"],"date_released":"2026-04-24"},"highlight":{},"matched_queries":null,"score":0.0}