A Novel Digital Score for Abundance of Tumour Infiltrating Lymphocytes Predicts Disease Free Survival in Oral Squamous Cell Carcinoma

Abstract

Oral squamous cell carcinoma (OSCC) is the most common type of head and neck (H&N) cancers with an increasing worldwide incidence and a worsening prognosis. The abundance of tumour infiltrating lymphocytes (TILs) has been shown to be a key prognostic indicator in a range of cancers with emerging evidence of its role in OSCC progression and treatment response. However, the current methods of TIL analysis are subjective and open to variability in interpretation. An automated method for quantification of TIL abundance has the potential to facilitate better stratification and prognostication of oral cancer patients. We propose a novel method for objective quantification of TIL abundance in OSCC histology images. The proposed TIL abundance (TILAb) score is calculated by first segmenting the whole slide images (WSIs) into underlying tissue types (tumour, lymphocytes, etc.) and then quantifying the co-localization of lymphocytes and tumour areas in a novel fashion. We investigate the prognostic significance of TILAb score on digitized WSIs of Hematoxylin and Eosin (H&E) stained slides of OSCC patients. Our deep learning based tissue segmentation achieves high accuracy of 96.31%, which paves the way for reliable downstream analysis. We show that the TILAb score is a strong prognostic indicator (p = 0.0006) of disease free survival (DFS) on our OSCC test cohort. The automated TILAb score has a significantly higher prognostic value than the manual TIL score (p = 0.0024). In summary, the proposed TILAb score is a digital biomarker which is based on more accurate classification of tumour and lymphocytic regions, is motivated by the biological definition of TILs as tumour infiltrating lymphocytes, with the added advantages of objective and reproducible quantification.

The immune phenotype of tongue squamous cell carcinoma predicts early relapse and poor prognosis

“…Some authors have highlighted how the number of immune phenotypes can vary from two to four and more, based on criteria used for the classification of tumor topography. 25,28,47 Nevertheless, regardless of the classification system used, the immune-desert phenotype is uniquely defined as the absence of immune cells in both the tumor parenchyma and the tumor stroma; therefore, the prognostic role of immune-desert phenotype described in the present study is not influenced by the classification system being used. Furthermore, this subgroup shows distinctive molecular features that were identified by a F I G U R E 4 A-E, Kaplan-Meier curves for disease-specific survival (A), overall survival (OS) (B), and disease-free survival (DFS) (C) in the Italian cohort; and OS (D) and DFS (E) in the The Cancer Genome Atlas cohort molecular clustering analysis on a wider cohort of squamous cell carcinoma, 47 thus setting this immune-desert phenotype aside of other immune phenotypes.…”

“…46 A growing interest has emerged in the recent years regarding the potential importance of the spatial organization of TIL infiltrate in relation to cancer cells. 25 The new paradigm for the classification of solid tumors, based on the distribution of immune cells, has recently emerged with the aim of improving the prognostic accuracy of TIL infiltrates. 27 Hence, the present study aimed to investigate the prognostic role of immune phenotypes in OTSCC, staged according to both 7th and 8th editions of the AJCC Cancer Staging Manual.…”

Validation of machine learning models to detect amyloid pathologies across institutions

“…The use of machine learning in the field of histopathology [13][14][15][16] has shown great promise, and may in part help standardize quantitative assessment in neurodegenerative disorders. Convolutional neural networks (CNN), a class of machine learning models, are excellent for working with imaging data and have recently been shown to be capable of quantifying AD pathology comparable to an expert neuropathologist [17].…”

Knowledge, attitudes, and perceptions regarding the future of artificial intelligence in oral radiology in India: A survey

“…4 Studies have reported the use of AI in the early screening of oral cancer and cervical lymph node metastasis, as well as in the diagnosis and treatment planning of various orofacial diseases. [4][5][6][7] Nonetheless, stakeholders' opinions vary regarding the future of AI. While many think that AI will create many opportunities in the fields of medicine and dentistry and will pave a new way towards a great future, others still believe that AI is unreliable and will not even be able to replace radiologists in the future.…”