Scoring of tumor-infiltrating lymphocytes: From visual estimation to machine learning

Abstract

The extent of tumor-infiltrating lymphocytes (TILs), along with immunomodulatory ligands, tumor-mutational burden and other biomarkers, has been demonstrated to be a marker of response to immune-checkpoint therapy in several cancers. Pathologists have therefore started to devise standardized visual approaches to quantify TILs for therapy prediction. However, despite successful standardization efforts visual TIL estimation is slow, with limited precision and lacks the ability to evaluate more complex properties such as TIL distribution patterns. Therefore, computational image analysis approaches are needed to provide standardized and efficient TIL quantification. Here, we discuss different automated TIL scoring approaches ranging from classical image segmentation, where cell boundaries are identified and the resulting objects classified according to shape properties, to machine learning-based approaches that directly classify cells without segmentation but rely on large amounts of training data. In contrast to conventional machine learning (ML) approaches that are often criticized for their "black-box" characteristics, we also discuss explainable machine learning. Such approaches render ML results interpretable and explain the computational decision-making process through high-resolution heatmaps that highlight TILs and cancer cells and therefore allow for quantification and plausibility checks in biomedical research and diagnostics.

Pitfalls in assessing stromal tumor infiltrating lymphocytes (sTILs) in breast cancer

“…background than, for example, to distinguishing malignant cells from normal epithelium. There is a surge in the development of machine learning methods for TIL assessment 44 . The histopathologic diagnostic responsibility will continue to reside with the pathologist.…”

Quantitative multiplex immunofluorescence analysis identifies infiltrating PD1+CD8+ and CD8+ T cells as predictive of response to neoadjuvant chemotherapy in breast cancer

“…[18][19][20] Computational pathology can provide objective, quantitative, and reproducible tissue metrics and represents a viable means of outcome prediction in BC. 21 However, different methods may have varied accuracy in special quantification, and full slides may be preferable to TMA-based analysis. 22 The International TILs Working Group recommended analyses of TILs or CD8 + T cells using AIbased approaches for further investigation.…”

The Cancer Immunotherapy Biomarker Testing Landscape

“…159 Beyond manual human interpretation of TILs, computational image analysis-based TIL scoring approaches have been developed, including traditional object-oriented image-segmentation methods and more advanced machine learning-based classification algorithms that rely on extensive training sets but are able to morphologically identify cellular subsets. 160 TRANSCRIPTIONAL SIGNATURES OF IMMUNE RESPONSIVENESS (STATUS: EMERGING) RNA-based gene expression studies have been used to identify specific transcriptional patterns and signatures in tumors and the tumor microenvironment that may help elucidate details of immune physiology underlying immunotherapy benefit. Summarized here are selected studies exploring gene expression signatures that appear to play an important role in the prediction of cancer immunotherapy response.…”