Role of AI and digital pathology for colorectal immuno-oncology

Abstract

Immunotherapy deals with therapeutic interventions to arrest the progression of tumours using the immune system. These include checkpoint inhibitors, T-cell manipulation, cytokines, oncolytic viruses and tumour vaccines. In this paper, we present a survey of the latest developments on immunotherapy in colorectal cancer (CRC) and the role of artificial intelligence (AI) in this context. Among these, microsatellite instability (MSI) is perhaps the most popular IO biomarker globally. We first discuss the MSI status of tumours, its implications for patient management, and its relationship to immune response. In recent years, several aspiring studies have used AI to predict the MSI status of patients from digital whole-slide images (WSIs) of routine diagnostic slides. We present a survey of AI literature on the prediction of MSI and tumour mutation burden from digitised WSIs of haematoxylin and eosin-stained diagnostic slides. We discuss AI approaches in detail and elaborate their contributions, limitations and key takeaways to drive future research. We further expand this survey to other IO-related biomarkers like immune cell infiltrates and alternate data modalities like immunohistochemistry and gene expression. Finally, we underline possible future directions in immunotherapy for CRC and promise of AI to accelerate this exploration for patient benefits.

Deep Learning Applied to Raman Spectroscopy for the Detection of Microsatellite Instability/MMR Deficient Colorectal Cancer

“…DL has also been explored for MSI-H prediction performed on H&E stained samples [ 4 , 6 ]. These take CNNs designed for image classification, which tend to be very large models and require more data to train.…”

“…Hence, the detection of MSI-H is recommended in every case of CRC to screen for LS [ 3 ]. The high mutational burden seen in MSI-H tumours also has implications for treatment, providing potential targets for immunotherapy such as immune checkpoint inhibitors [ 4 ].…”

“…Testing for dMMR/MSI-H typically involves either immunohistochemistry (IHC) of the mismatch repair proteins or PCR amplification of consensus microsatellite repeats. Recent developments in machine learning (ML) have led to the possibility of exploiting morphological information in standard H&E slides [ 4 , 6 ]. Such digital pathology techniques require few additional resources and have proven highly accurate in high quality, curated datasets.…”

Computational Pathology: A Survey Review and The Way Forward

“…The first focuses on the design and applications of smart diagnosis tools. 15 , 16 , 17 , 33 , 34 , 35 , 36 , 37 , 38 , 39 , 40 , 41 , 42 , 43 These works focus on designing novel architectures for artificial intelligence (AI) models with regards to specific clinical tasks, although they may briefly discuss clinical challenges and limitations. A second group of works focus on clinical barriers for AI integration discussing specific certifications and regulations required for the development of medical devices under clinical settings.…”

Development and validation of AI-based pre-screening of large bowel biopsies

“…In recent years, an increasing number of weakly supervised deep learning methods for whole-slide image classification have been proposed for various histopathology problems (14)(15)(16)(17)(18)(19)(20). An attractive feature of weakly supervised methods is their ability to enable automatic classification without the need for detailed pixel or region level annotations.…”