This technology is an automated imaging analysis platform for identifying and quantifying biomarkers that can be used to predict lung adenocarcinoma subtypes.
Adenocarcinoma is the most common type of lung cancer, which is the leading cause of cancer-related deaths across the world. There are multiple subtypes of lung adenocarcinoma which have association with patient’s disease-free-survival. In current clinical routine, the subtypes of lung adenocarcinoma are generally classified using a limited number of pathology specimens from a resected tumor. Due to the spatial limitations of the current pathological methods, there is a need for a method that can analyze images of the entire lung tumor to predict adenocarcinoma subtype and associated patient outcomes.
This technology is an imaging analysis platform that uses automated machine learning and deep learning methods to identify quantitative imaging biomarkers (QIB) related to disease-free-survival (DFS)- associated subtypes of lung adenocarcinoma. This analytic platform is generalizable, overcomes the limited sample sizes of traditional pathology methods, and works with computed tomography (CT) images routinely acquired from patients. Using this platform, clinicians can analyze full images of a tumor to help guide further pathological analysis for improved disease diagnostics and monitoring.
This pathology has been validated using 1313 CT images from patients with lung adenocarcinoma.
Lin Lu, Ph.D.
Lawrence H. Schwartz, M.D.
Patent Pending
IR CU20338
Licensing Contact: Sara Gusik