Advanced diagnostics are enabling cancer treatments to become increasingly tailored to the individual through developments in immunotherapies and targeted therapies. However, long turnaround times and high costs of molecular testing hinder the widespread implementation of targeted cancer treatments. Meanwhile, gold-standard histopathological assessment carried out by a trained pathologist is widely regarded as routine and mandatory in most cancers. Recently, methods have been developed to mine hidden information from histopathological slides using deep learning applied to scanned and digitized slides; deep learning comprises a collection of computational methods which learn patterns in data in order to make predictions. Such methods have been reported to be successful in a variety of cancers for predicting the presence of biomarkers such as driver mutations, tumour mutational burden, and microsatellite instability. This information could prove valuable to pathologists and oncologists in clinical decision making for cancer treatment and triage for in-depth sequencing. In addition to identifying molecular features, deep learning has been applied to predict prognosis and treatment response in certain cancers. Despite reported successes, many challenges remain before the clinical implementation of such diagnostic strategies in the clinical setting is possible. This review aims to outline recent developments in the field of deep learning for predicting molecular genetics from histopathological slides, as well as to highlight limitations and pitfalls of working with histopathology slides in deep learning.

Studies have demonstrated that men with Prostate Cancer (PCa) harboring BRCA2/BRCA1 genetic aberrations, are more likely to have worse disease and a poorer prognosis. A mutation in BRCA2 is known to confer the highest risk of PCa for men (8.6 fold in men ≤65 years) making BRCA genes a conceivable genomic biomarker for risk in PCa. These genes have attracted a lot of research attention however their role in the clinical assessment and treatment of PCa remains complex. Multiple studies have been published examining the relationship between prostate cancer and BRCA mutations. Here BRCA mutations are explored specifically as a biomarker for risk in PCa. It is in this context, we examined the prognostic, clinical and therapeutic role of BRCA2/BRCA1 mutations across the evolution of PCa. The impact of the inclusion of BRCA genes on genetic screening will also be outlined.

Developing artificial intelligence (AI) models for digital pathology requires large datasets from multiple sources. However, without careful implementation, AI models risk learning confounding site-specific features in datasets instead of clinically relevant information, leading to overestimated performance, poor generalizability to real-world data, and potential misdiagnosis. Whole-slide images (WSIs) from The Cancer Genome Atlas (TCGA) colon (COAD), and stomach adenocarcinoma datasets were selected for inclusion in this study. Patch embeddings were obtained using three feature extraction models, followed by ComBat harmonization. Attention-based multiple instance learning models were trained to predict tissue-source site (TSS), as well as clinical and genetic attributes, using raw, Macenko normalized, and Combat-harmonized patch embeddings. TSS prediction achieved high accuracy (AUROC > 0.95) with all three feature extraction models. ComBat harmonization significantly reduced the AUROC for TSS prediction, with mean AUROCs dropping to approximately 0.5 for most models, indicating successful mitigation of batch effects (e.g., CCL-ResNet50 in TCGA-COAD: Pre-ComBat AUROC = 0.960, Post-ComBat AUROC = 0.506, p < 0.001). Clinical attributes associated with TSS, such as race and treatment response, showed decreased predictability post-harmonization. Notably, the prediction of genetic features like MSI status remained robust after harmonization (e.g., MSI in TCGA-COAD: Pre-ComBat AUROC = 0.667, Post-ComBat AUROC = 0.669, p=0.952), indicating the preservation of true histological signals. ComBat harmonization of deep learning-derived histology features effectively reduces the risk of AI models learning confounding features in WSIs, ensuring more reliable performance estimates. This approach is promising for the integration of large-scale digital pathology datasets.

Background: Recent advances in computational pathology have shown potential in predicting biomarkers from haematoxylin and eosin (H&E) whole-slide images (WSI). However, predicting the outcome directly from WSIs remains a substantial challenge. In this study, we aimed to investigate how gene expression, predicted from WSIs, could be used to evaluate overall survival (OS) in patients with lung adenocarcinoma (LUAD). Methods: Differentially expressed genes (DEGs) were identified from The Cancer Genome Atlas (TCGA)-LUAD cohort. Cox regression analysis was performed on DEGs to identify the gene prognostics of OS. Attention-based multiple instance learning (AMIL) models were trained to predict the expression of identified prognostic genes from WSIs using the TCGA-LUAD dataset. Models were externally validated in the Clinical Proteomic Tumour Analysis Consortium (CPTAC)-LUAD dataset. The prognostic value of predicted gene expression values was then compared to the true gene expression measurements. Results: The expression of 239 prognostic genes could be predicted in TCGA-LUAD with cross-validated Pearson’s R > 0.4. Predicted gene expression demonstrated prognostic performance, attaining a cross-validated concordance index of up to 0.615 in TCGA-LUAD through Cox regression. In total, 36 genes had predicted expression in the external validation cohort that was prognostic of OS. Conclusions: Gene expression predicted from WSIs is an effective method of evaluating OS in patients with LUAD. These results may open up new avenues of cost- and time-efficient prognosis assessment in LUAD treatment.

Purpose HPV driven oropharyngeal squamous cell carcinoma (OPSCC) proffers a more favorable prognosis in contrast to its HPV negative counterparts. Consequently, studies have analyzed de-intensification measures of current treatment practices to minimize the associated morbidity. However, 25% of patients with HPV positive OPSCC experience a locoregional recurrence (LR) and/or distant metastasis (DM). This study aimed to determine if patient demographics, tumor characteristics and specific HPV genotyping were attributable to HPV positive OPSCC who develop LR and/or DM based on data collated from the largest Head and Neck Cancer center in the Republic of Ireland, with a mean follow up period of 11.16 years. Methods Patient demographics was obtained from HPV positive OPSCC patients from 3 Dublin Hospitals diagnosed over a 10-year period. In addition, HPV genotyping via Ion Torrent Next Generation Sequencing (NGS) and mutations analysis using smMIP panel based NGS was conducted on the cohort archival tumor DNA. Results 67 patients met the criteria for inclusion and had a mean follow-up period of 11.16 years. 28.36% developed LR and/or DM. A statistically significant correlation was identified linking age at diagnosis (p = 0.047), excessive alcohol consumption (p = 0.017) and a higher clinical stage (p = 0.01) with LR and/or DM.HPV 16 was the most prevalent genotype (93.65%), with dual HPV infection illustrated in 4 cases. BRAF, EGFR, ERBB2, KIT, KRAS, NRAS, PDGFRA somatic mutations were not identified in the recurrence cohort. Conclusion With the ongoing focus to reduce treatment for patient with HPV positive OPSCC, upfront recognition of patients at greater risk of LR and/or DM is essential. In the era of personalized medicine, it is hoped that interrogation of archival tumor tissue via similar techniques used in this study may yield pioneering findings with a clinical and prognostic significance.