Valentina's Interview & Publication

What inspired your research and what did it cover?
The research was inspired by the need for more objective measures in assessing tumour-infiltrating lymphocytes (TILs) in breast cancer. The current manual quantification process is subjective and time-consuming for pathologists. The study introduced a novel pathomic approach, leveraging high-throughput image feature extraction techniques to analyse microscopic patterns in whole slide images (WSI) of breast cancer tissue. The aim was to provide a standardised, reproducible, and interpretable method for TILs detection, focusing on triple-negative breast cancer (TNBC) and HER2+ breast cancer.

Looking at the potential of your findings, what difference can they make?
The findings have the potential to significantly impact the clinical assessment of TILs in breast cancer. By employing machine learning models trained on pathomic features extracted from histopathological images, a classification performance with a ROC AUC of 0.86 was reached, demonstrating the effectiveness of the proposed approach. This method can serve as a reliable and rapid tool to support pathologists in objectively assessing TILs, aiding in the development of standardised measures for infiltration grade. The approach's interpretability and explainability make it a valuable addition to existing methods, offering a promising avenue for enhanced decision-making in breast cancer diagnosis and treatment planning. 

Publication

A pathomic approach for tumor-infiltrating lymphocytes classification on breast cancer digital pathology images

National Library of Medicine – https://pubmed.ncbi.nlm.nih.gov/36950640/

The detection of tumor-infiltrating lymphocytes (TILs) could aid in the development of objective measures of the infiltration grade and can support decision-making in breast cancer (BC). However, manual quantification of TILs in BC histopathological whole slide images (WSI) is currently based on a visual assessment, thus resulting not standardized, not reproducible, and time-consuming for pathologists. In this work, a novel pathomic approach, aimed to apply high-throughput image feature extraction techniques to analyze the microscopic patterns in WSI, is proposed. In fact, pathomic features provide additional information concerning the underlying biological processes compared to the WSI visual interpretation, thus providing more easily interpretable and explainable results than the most frequently investigated Deep Learning based methods in the literature.