Training immunophenotyping deep learning models with the same-section ground truth cell label derivation method improves virtual staining accuracy.

Introduction: Deep learning (DL) models predicting biomarker expression in images of hematoxylin and eosin (H&E)-stained tissues can improve access to multi-marker immunophenotyping, crucial for therapeutic monitoring, biomarker discovery, and personalized treatment development. Conventionally, these models are trained on ground truth cell labels derived from IHC-stained tissue sections adjacent to H&E-stained ones, which might be less accurate than labels from the same section. Although many such DL models have been developed, the impact of ground truth cell label derivation methods on their performance has not been studied. Methodology: In this study, we assess the impact of cell label derivation on H&E model performance, with CD3+ T-cells in lung cancer tissues as a proof-of-concept. We compare two Pix2Pix generative adversarial network (P2P-GAN)-based virtual staining models: one trained with cell labels obtained from the same tissue section as the H&E-stained section (the 'same-section' model) and one trained on cell labels from an adjacent tissue section (the 'serial-section' model). Results: We show that the same-section model exhibited significantly improved prediction performance compared to the 'serial-section' model. Furthermore, the same-section model outperformed the serial-section model in stratifying lung cancer patients within a public lung cancer cohort based on survival outcomes, demonstrating its potential clinical utility. Discussion: Collectively, our findings suggest that employing ground truth cell labels obtained through the same-section approach boosts immunophenotyping DL solutions.

The immunomodulatory role of paracrine signalling factor VSIG4 in peritoneal metastases.

Peritoneal metastasis (PM), the regional progression of intra-abdominal malignancies, is a common sequelae of colorectal cancer (CRC). Immunotherapy is slated to be effective in generating long-lasting anti-tumour response as it utilizes the specificity and memory of the immune system. In the tumour microenvironment, tumour associated macrophages (TAMs) are posited to create an anti-inflammatory pro-tumorigenic environment. In this paper, we aimed to identify immunomodulatory factors associated with colorectal PM (CPM). A publicly available colorectal single cell database (GSE183916) was analysed to identify possible immunological markers that are associated with the activation of macrophages in cancers. Immunohistochemical analysis for V-set and immunoglobin containing domain 4 (VSIG4) expression was performed on tumour microarrays (TMAs) of tumours of colorectal origin (n = 211). Expression of VSIG4 in cell-free ascites obtained from CPM patients (n = 39) was determined using enzyme-linked immunosorbent assay (ELISA). CD163-positive TAMs cluster expression was extracted from a publicly available single cell database and evaluated for the top 100 genes. From these macrophage-expressed genes, VSIG4, a membrane protein produced by the M2 macrophages, mediates the up-regulation of anti-inflammatory and down-regulation of pro-inflammatory macrophages, contributing to an overall anti-inflammatory state. CRC TMA IHC staining showed that low expression of VSIG4 in stromal tissues of primary CRC are associated with poor prognosis (p = 0.0226). CPM ascites also contained varying concentrations of VSIG4, which points to a possible role of VSIG4 in the ascites. The contribution of VSIG4 to CPM development can be further evaluated for its potential as an immunotherapeutic agent.

Comparison of an amplicon-based large panel next generation sequencing (NGS) assay with conventional testing methods for MET and HER2 amplification in lung and breast cancers.

The frequency of MET and HER2 amplification being detected by next generation sequencing (NGS) is increasing due to NGS being increasingly adopted for molecular profiling of cancers. However, the accuracy of NGS in detecting these gene amplifications remains uncertain due to conflicting reports in the scientific literature. We studied the accuracy of an amplicon-based large panel NGS assay in detecting MET and HER2 amplification in lung and breast cancers, respectively, by comparing it against conventional testing methods. Amongst 48 lung cancers, four of five cancers that were MET amplified on fluorescence in situ hybridisation (FISH) were classified as amplified on NGS while 42 of the remaining 43 non-amplified cancers were classified as non-amplified on NGS, giving a sensitivity of 80%, specificity of 97.7% and overall concordance of 95.8%. Of the 46 breast cancers tested, only six of the nine cancers that were HER2-positive on immunohistochemistry (IHC)/FISH were HER2-positive on NGS, while all the remaining HER2-negative cases were negative on NGS, giving a sensitivity of 66.7%, specificity of 100% and overall concordance of 93.5%. All the false-negative cases had low level gene amplification (MET:CEP7 or HER2:CEP17 FISH ratio of <3). The low sensitivity for HER2 amplification may be confounded by the small sample size and disproportionate number of cases with low level amplification. In summary, the NGS assay has good concordance with conventional testing methods but may be less sensitive in detecting low level gene amplification.

Molecular testing in non-small cell lung cancer: A consensus recommendation.

Introduction: Lung cancer remains an important cause of cancer-related mortality in Singapore, with a greater proportion of non-smokers diagnosed with non-small cell lung cancer (NSCLC) in the past 2 decades. The higher prevalence of targetable genomic alterations in lung cancer diagnosed in Singapore compared with countries in the West, as well as the expanding therapeutic landscape for NSCLC in the era of precision medicine, are both factors that underscore the importance of efficient and effective molecular profiling. Method: This article provides consensus recommendations for biomarker testing for early-stage to advanced NSCLC. These recommendations are made from a multidisciplinary group of lung cancer experts in Singapore with the aim of improving patient care and long-term outcomes. Results: The recommendations address the considerations in both the advanced and early-stage settings, and take into account challenges in the implementation of biomarker testing as well as the limitations of available data. Biomarker testing for both tumour tissue and liquid biopsy are discussed. Conclusion: This consensus statement discusses the approaches and challenges of integrating molecular testing into clinical practice for patients with early- to late-stage NSCLC, and provides practical recommendations for biomarker testing for NSCLC patients in Singapore.