AI-based prognosis and therapy response prediction from pathology images
The principle of platform is as follows:
1. A potent multi-class tissue segmentation algorithm will be applied to hematoxylin&eosin (H&E) stained whole slide images of the lung cancer tumors and will precisely segment it into all relevant tumor-associated and benign tissue classes (e.g., for tumor regions these are such classes as tumor, tumoral stroma, necrosis, mucin, tertiary lymphoid structures, etc.).
2. A cell-level algorithm will be applied that detects all single cells and classifies them (tumor cells and 5 types of microenvironment cells).
This platform allows full, quantitative, explainable deciphering of pathology images of malignant tumors.
Based on this information, powerful prognostic (patient survival) and predictive (response to therapy) algorithms can be built. Thousand of different parameters, including combinations based on simple metrics or spatial distribution of tumor and tumor microenvironment structures can be easily established in the platform.
Thus, for lung cancer (non-small cell lung cancer, NSCLC) we developed image-based, quantitative, explainable prognostic parameters with independent value when investigated together with common clinicopathological prognostic variables (pT and pN categories, age), such as based on necrosis and tertiary lymphoid structure quantification, composition of tumor stroma, ratio between different cell types in tumor microenvironment, etc. These parameters work for all clinical endpoints in NSCLC such as progression-free survival, cancer-specific, and overall survival and were tested in one own patient cohort and using one open cohort (The Cancer Genome Atlas).
- Validate the previously developed prognostic image-based parameters for NSCLC using pathology images and associated clinical / pathological / follow-up information.
- Develop new prognostic (patient survival) and predictive (therapy response, metastasis development) parameters using a large, well-characterized cohorts of patients (NLST, also PLCO) and above mentioned computational pathology platform
- Additionally study intratumoral heterogeneity of different image-based parameters as potential confounder of prognostic and predictive information.
- Develop a image-based system for searching of similar cases.
Reinhard Büttner, Institute of Pathology, University Hospital Cologne
Christian Harder, Institute of Pathology, University Hospital Cologne
Zhilong Weng, Institute of Pathology, University Hospital Cologne