The study addresses one of the most persistent challenges in gastric cancer immunotherapy. Nivolumab can produce long-lasting responses in some patients, but many others gain little benefit despite receiving the same treatment. Gastric cancer is biologically diverse, meaning that two tumours appearing similar under conventional examination may behave very differently once exposed to immune-based therapy. Clinicians therefore need reliable biomarkers that can distinguish patients more likely to respond from those who may require another strategy. The researchers’ model is intended to provide an additional layer of evidence by extracting predictive information directly from tumour morphology.

At present, the best-known clinical marker for selecting patients for some immunotherapy regimens is the programmed death ligand 1, or PD-L1, combined positive score. The CPS estimates the proportion of tumour cells and immune cells within a tissue sample that express PD-L1, a protein capable of suppressing immune activity. A higher score can indicate a greater likelihood of benefit from drugs such as nivolumab, which block the interaction between PD-1 on immune cells and PD-L1 on tumour or immune cells. Yet PD-L1 is not a perfect predictor. Some patients with low or negative scores respond, while some patients with high scores do not. This limitation has encouraged researchers to look for more comprehensive biological signals.

Digital pathology offers a way to examine those signals at a scale that is difficult to achieve manually. In a typical workflow, a glass pathology slide is scanned to create a whole-slide image containing millions or even billions of pixels. Deep-learning algorithms can then evaluate the architecture of the tumour, the arrangement of malignant cells, the density and distribution of immune cells, connective tissue patterns, necrotic regions and other visual features. Many of these characteristics are subtle, spatially complex or too numerous to be consistently integrated during routine assessment. A model can process them collectively and convert the resulting information into a numerical risk score.

The researchers describe a model developed from digital pathology to forecast outcomes among patients with gastric carcinoma treated with nivolumab. Rather than depending exclusively on a single molecular marker, the system is designed to learn associations between tissue appearance and clinical course. Its output is a risk estimate that could potentially help identify patients more likely to experience a favourable outcome and those at higher risk of limited benefit. The central concept is not that artificial intelligence replaces the pathologist, but that it acts as a computational assistant capable of uncovering patterns hidden within standard diagnostic material.

This distinction is important because digital pathology uses specimens already collected as part of ordinary cancer care. In principle, a predictive model based on routine slides could be easier to implement than a test requiring a new biopsy, specialised sequencing or an expensive laboratory platform. It could also be updated to combine image-derived information with clinical variables, treatment history and established biomarkers such as PD-L1 CPS. Such integration may eventually produce a more nuanced picture of a patient’s likely response than any individual measurement can provide.

However, the promise of an AI-derived score does not automatically make it ready for clinical decisions. Deep-learning systems can learn unwanted features from the data used to train them, including differences in staining protocols, scanner hardware, hospital workflows or patient selection. A model that performs well in one institution may lose accuracy when applied to slides produced elsewhere. Researchers must therefore test these systems across independent cohorts, institutions and populations, while also examining whether the model remains reliable when tissue samples are small, damaged or contain limited tumour material. Transparent reporting and rigorous validation are essential before such tools can influence treatment choices.

The study is particularly significant because nivolumab outcomes are difficult to predict using conventional clinical information alone. Immunotherapy depends on an interaction between the cancer and the patient’s immune system, and that interaction may be reflected in the organisation of cells within the tumour microenvironment. A slide can reveal not only whether immune cells are present, but also where they are located and how they relate to malignant cells. Deep learning may be able to quantify these spatial relationships, potentially identifying an “immune context” linked to treatment sensitivity. The resulting score could complement PD-L1 testing rather than compete with it.

If validated in future studies, the model could support a more precise form of treatment planning for gastric cancer. Patients predicted to have a higher probability of benefit might proceed with nivolumab-based therapy with greater confidence, while those at higher predicted risk could be considered for clinical trials, combination approaches or alternative treatments. Such a system could also help researchers design trials by identifying biologically similar patient groups and investigating why some tumours resist immune checkpoint blockade. Nevertheless, the score should be interpreted as a probability, not a verdict. Treatment decisions would still need to account for overall health, tumour stage, previous therapies, toxicity risks and patient preferences.

The work reflects a broader transformation in oncology, in which pathology images are becoming quantitative sources of biological information rather than static illustrations attached to a diagnosis. By applying deep learning to routine tissue, the researchers aim to move gastric cancer care closer to predictive medicine, where the question is not simply what a tumour looks like, but what it is likely to do when challenged by a specific therapy. The model described by Hong and colleagues does not eliminate the uncertainty surrounding nivolumab, but it offers a potentially scalable route toward reducing it. Its ultimate value will depend on independent validation, clinical integration and proof that the predictions improve outcomes for real patients.

Subject of Research: Deep learning and digital pathology for predicting nivolumab outcomes in gastric carcinoma

Article Title: A deep learning-derived risk score model from digital pathology to forecast nivolumab outcomes in gastric carcinoma

Article References: Hong, Y., Hwang, I., Kim, MJ. et al. A deep learning-derived risk score model from digital pathology to forecast nivolumab outcomes in gastric carcinoma. Br J Cancer (2026). https://doi.org/10.1038/s41416-026-03590-z

Image Credits: AI Generated

DOI: 10.1038/s41416-026-03590-z

Keywords: gastric cancer, gastric carcinoma, nivolumab, immunotherapy, PD-L1, combined positive score, digital pathology, deep learning, artificial intelligence, biomarkers, precision oncology

Gastric cancer remains one of the most prevalent and deadly cancers globally, ranking fifth in incidence and fourth in cancer-related deaths. Particularly burdensome in China, which accounts for nearly half of the global cases, the disease poses immense challenges despite advances in therapeutic modalities. Immune checkpoint inhibitors (ICIs) have emerged as a beacon of hope, offering durable responses in select patient populations. However, the variability in therapeutic outcomes necessitates reliable predictive biomarkers to optimize patient selection and avoid ineffective treatment exposure.

Historically, the expression of programmed death-ligand 1 (PD-L1) has served as a conventional biomarker to guide immunotherapy, yet its clinical utility is hampered by technical complexities and inconsistent interpretative concordance among pathologists. In a novel and comprehensive study leveraging single-cell transcriptome sequencing, the investigative team mapped the intricate tumor microenvironment of 46 LAGC patients undergoing combined neoadjuvant chemotherapy and ICI treatment. The analysis unveiled a distinctive upregulation of tumor-specific Major Histocompatibility Complex class II molecules (tsMHC-II) exclusively in tumors from patients who displayed treatment sensitivity.

This differential tsMHC-II expression underscores a robust mechanistic link between enhanced antigen presentation within tumor cells and augmented immune-mediated tumor eradication. Crucially, patients harboring tsMHC-II-positive tumors demonstrated a remarkable pathological complete response (pCR) rate of 36.84%, significantly surpassing the 11.11% observed in tsMHC-II-negative counterparts. Similarly, major pathological response (MPR) rates were markedly elevated at 63.16% versus 25.93%, further solidifying the biomarker’s predictive power.

To validate these transformative findings, a prospective clinical trial encompassing 30 patients specifically selected for tsMHC-II positivity was conducted. The outcomes were profound: 36.67% achieved pCR while 66.67% attained MPR, rates dramatically higher than historical averages in unselected LAGC populations. These results compellingly advocate for the integration of tsMHC-II assessment into clinical workflows to enhance treatment stratification.

Importantly, the tsMHC-II biomarker is amenable to detection via standard immunohistochemistry (IHC), a technique ubiquitously available in pathology laboratories worldwide. This pragmatic advantage addresses the critical issue of accessibility and reproducibility that plagues existing biomarker assays, particularly PD-L1. The tsMHC-II IHC evaluation provides unequivocal and reproducible results, thus enabling straightforward implementation across diverse clinical settings.

On a molecular level, mechanistic investigations revealed that interferon-gamma (IFN-γ) signaling dynamically upregulates MHC-II expression within tumor cells, thereby enhancing antigen presentation and potentiating immune surveillance. This insight not only elucidates the biomarker’s biological underpinnings but also opens avenues for therapeutic strategies aiming to amplify tsMHC-II expression, potentially converting non-responders into responders.

The clinical implications of this discovery are profound. By reliably identifying patients predisposed to benefit from neoadjuvant immunotherapy, oncologists can tailor treatments with greater precision, minimizing unnecessary exposure to toxic therapies in non-responders and maximizing clinical benefit in responsive populations. This precision medicine approach is poised to significantly improve survival outcomes and quality of life for patients afflicted with LAGC.

Professor Xiangdong Cheng, a corresponding author of the study, emphasized the transformative potential of this biomarker, stating that tsMHC-II evaluation could revolutionize patient selection for immunotherapy. The ability to predict treatment responsiveness with high fidelity stands to refine clinical decision-making and optimize resource utilization in oncology care.

Building upon this foundational work, the researchers are initiating larger multicenter clinical trials to further validate the tsMHC-II biomarker and assess its applicability across other cancer types. Such studies will be instrumental in confirming its broad utility and integrating this biomarker into global oncological practice.

Established in 1963, Zhejiang Cancer Hospital has long been at the forefront of cancer research and care in China, consistently recognized for excellence with the highest national rating in hospital performance assessments. Its collaboration with Peking University, another leading institution in biomedical research, underscores the study’s scientific rigor and potential impact.

This landmark discovery exemplifies the power of cutting-edge single-cell sequencing technologies combined with translational clinical research to unveil actionable biomarkers that will shape the future landscape of cancer immunotherapy. As gastric cancer continues to impose a heavy toll worldwide, innovations such as tsMHC-II-guided therapy offer new hope for precision oncology and improved patient outcomes.

Subject of Research: Identification of tumor-specific MHC-II (tsMHC-II) as a predictive biomarker for neoadjuvant immunotherapy response in locally advanced gastric cancer.

Article Title: Tumor-specific MHC-II Expression Predicts Response to Neoadjuvant Immune Checkpoint Inhibition in Locally Advanced Gastric Cancer

News Publication Date: Not specified

Web References: Not specified

References: DOI 10.1016/j.scib.2026.01.004

Image Credits: ©Science China Press

Keywords: gastric cancer, immunotherapy, immune checkpoint inhibitors, neoadjuvant therapy, biomarker, tumor-specific MHC-II, tsMHC-II, single-cell transcriptome sequencing, pathological complete response, major pathological response, interferon-gamma, precision oncology