Discovering Clinically Meaningful Shape Features for the Analysis of Tumor Pathology Images

TL;DR

This study introduces a set of 30 shape, geometry, and topology descriptors for tumor regions in pathology images, linking these features to patient survival and developing a prognostic model validated across independent cohorts.

Contribution

It presents a novel set of shape descriptors for tumor analysis and demonstrates their association with patient outcomes, offering new insights into tumor morphology and prognosis.

Findings

Descriptor features are associated with lung adenocarcinoma survival.

A prognostic model based on descriptors was validated in independent cohorts.

Software for feature extraction is publicly available on GitHub.

Abstract

With the advanced imaging technology, digital pathology imaging of tumor tissue slides is becoming a routine clinical procedure for cancer diagnosis. This process produces massive imaging data that capture histological details in high resolution. Recent developments in deep-learning methods have enabled us to automatically detect and characterize the tumor regions in pathology images at large scale. From each identified tumor region, we extracted 30 well-defined descriptors that quantify its shape, geometry, and topology. We demonstrated how those descriptor features were associated with patient survival outcome in lung adenocarcinoma patients from the National Lung Screening Trial (n=143). Besides, a descriptor-based prognostic model was developed and validated in an independent patient cohort from The Cancer Genome Atlas Program program (n=318). This study proposes new insights into the relationship between tumor shape, geometrical, and topological features and patient prognosis. We provide software in the form of R code on GitHub: https://github.com/estfernandez/Slide_Image_Segmentation_and_Extraction.