Novel histopathologic feature identified through image analysis augments stage II colorectal cancer clinical reporting

Abstract

A number of candidate histopathologic factors show promise in identifying stage II colorectal cancer (CRC) patients at a high risk of disease-specific death, however they can suffer from low reproducibility and none have replaced classical pathologic staging. We developed an image analysis algorithm which standardized the quantification of specific histopathologic features and exported a multi-parametric feature-set captured without bias. The image analysis algorithm was executed across a training set (n = 50) and the resultant big data was distilled through decision tree modelling to identify the most informative parameters to sub-categorize stage II CRC patients. The most significant, and novel, parameter identified was the ‘sum area of poorly differentiated clusters’ (AreaPDC). This feature was validated across a second cohort of stage II CRC patients (n = 134) (HR = 4; 95% CI, 1.5– 11). Finally, the AreaPDC was integrated with the significant features within the clinical pathology report, pT stage and differentiation, into a novel prognostic index (HR = 7.5; 95% CI, 3–18.5) which improved upon current clinical staging (HR = 4.26; 95% CI, 1.7– 10.3). The identification of poorly differentiated clusters as being highly significant in disease progression presents evidence to suggest that these features could be the source of novel targets to decrease the risk of disease specific death.

Automated Analysis of Lymphocytic Infiltration, Tumor Budding, and Their Spatial Relationship Improves Prognostic Accuracy in Colorectal Cancer

“…Previous research has demonstrated the ability to automatically quantify CD3 + and CD8 + T cells within the TME, thereby achieving a greater level of standardization than with subjective, manual reporting (9). Similarly we have previously shown that tumor budding can be standardized through automated image analysis (12,13). Although the automatic quantification of both immune infiltrate and tumor budding has been associated with patient prognosis, they have not been studied together.…”

Automated tumour budding quantification by machine learning augments TNM staging in muscle-invasive bladder cancer prognosis

“…www.nature.com/scientificreports www.nature.com/scientificreports/ Image analysis for automated TB quantification. Despite the fact that most previous studies have evaluated TB using haematoxylin and eosin (H&E), recent reports have provided meaningful information about TB and disease progression using both immunohistochemistry (IHC) [33][34][35][36] and immunofluorescence (IF) 37,38 . The use of cytokeratin-based immuno-labelling as a tumour mask clearly identifies TB even in cases that display a high density of peri-tumoural inflammatory infiltrate or reactive stromal cells.…”

Poorly differentiated clusters in colorectal cancer: a current review and implications for future practice

“…For example, studies investigating the greatest linear extent of PDC and total area of PDC have shown early promise. 57,58 Finally, AI-based tools, such as a recently described multiplex-immunohistochemistry-based system, 59 might be leveraged to integrate the assessment of invasive front markers such as PDC, TB and DST into a single unified grading system.…”