Non-invasive imaging analysis for predicting lung adenocarcinoma subtypes

This technology is an automated imaging analysis platform for identifying and quantifying biomarkers that can be used to predict lung adenocarcinoma subtypes.

Unmet Need: Non-invasive method to classify cancer type and predict patient outcomes

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.

The Technology: Automated imaging analysis platform for adenocarcinoma using CT images

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.

Applications:

Diagnostic assay for lung cancer
Prognostic assay
Pathology research tool

Advantages:

Automated
Compatible with common CT scans
Non-invasive
High-throughput
Unlimited with respect to sample size
High specificity for predicting mid to poor DFS-associated subtypes

Lead Inventor:

Binsheng Zhao, D.Sc.

Lin Lu, Ph.D.

Lawrence H. Schwartz, M.D.

Patent Information:

Patent Pending

Related Publications:

Lu L, Wang D, Wang L, E L, Guo P, Li Z, Xiang J, Yang H, Li H, Yin S, Schwartz LH, Xie C, Zhao B. “A quantitative imaging biomarker for predicting disease-free-survival-associated histologic subgroups in lung adenocarcinoma” Eur Radiol. 2020 Jul; 30(7): 3614-3623.

Tech Ventures Reference:

IR CU20338
Licensing Contact: Sara Gusik