AI and Cancer Research ── 2026-09-30


New papers on cancer and AI from 26 medical, oncology and general journals with an impact factor of 10 or more, collected from the journals' own websites and selected by Jev (an AI that makes language judgements): is it original research, is AI central, which of 13 themes, and does it concern treatment or trials. Each entry shows the full original abstract.
Read by cancer type: Cancer biology(12) · Breast(3) · Lung(3) · Pancreatic(2) · Prostate(2) · ACC(0) · Brain(0) · Ovarian(0) · Endometrial(0) · Gastric(0) · Liver(0) · Kidney(0) · Bladder(0)
Cancer molecular biology and AI
- Abstract
Tissues are complex ecosystems organised in space, and alterations in this organisation underpin multiple diseases. Spatial omics enables molecular profiling of tissue organisation, but linking these patterns to clinical outcomes remains challenging. We present SpaCEy (Spatial Clinical Explainability), an explainable graph neural network that identifies tissue patterns predictive of clinical outcomes in spatial proteomics datasets. SpaCEy models tissues as spatial graphs from molecular marker expression, without using predefined cell-type labels or anatomical regions as model inputs. Its embeddings capture intercellular relationships and molecular dependencies for predicting overall survival and disease progression. An integrated explainer identifies recurring spatial patterns and coordinated marker expression relevant to model predictions. Applied to a spatial proteomic lung cancer cohort, SpaCEy identifies spatial and protein-expression patterns associated with disease progression. Across multiple breast cancer proteomic datasets, it stratifies patients by overall survival, both across and within established clinical subtypes, and highlights protein markers underlying this stratification.
Reference: Rifaioglu AS, Ervin EH, Sarigun A, Germen D, Bodenmiller B, Tanevski J, et al. SpaCEy links spatial tissue patterns to clinical outcomes using explainable graph neural networks. Nat Commun. 2026 Sep 26;17(1):10232. doi:10.1038/s41467-026-77924-z. PMID: 42800816; PMCID: PMC13615965.Checked: Full text checked - Abstract
Predicting drug efficacy across diverse patient contexts remains a major challenge in oncology, as models trained on cancer cell lines often fail to capture patient-specific biology. Emerging biological foundation models and patient-derived technologies offer a promising solution. Here, we present UniCure, a multi-modal model that combines biological and chemical foundation models to predict drug-induced transcriptomic responses across diverse cell and tissue contexts, enabling individualized drug ranking. Trained on 1.9 million transcriptomic perturbation profiles spanning >22,000 compounds, 166 cell types, and 24 tissues, UniCure accurately predicts dose-dependent and combination responses and generalizes across bulk and single-cell data. We further fine-tune UniCure on 345 patient-derived tumor-like cluster (PTC) transcriptomic profiles and validate performance on 396 real-world clinical profiles, demonstrating effective patient-level prediction. The model supports response-based patient stratification and is experimentally validated in cell line and patient-derived models. Overall, UniCure provides a practical framework for translating preclinical data into personalized therapeutic strategies.
Reference: Chen Z, Tian S, Pei J, Gu R, Li Y, Ding S, et al. UniCure: A multi-modal model for predicting personalized cancer therapy response. Cancer Cell. 2026 Sep [Epub ahead of print]. doi:10.1016/j.ccell.2026.07.010. PMID: 42716007.Checked: Abstract only
See all 12 Cancer biology papers →
Breast cancer: treatment, trials and AI
- Abstract
Background: Tumour-infiltrating lymphocytes (TILs) are a robust prognostic marker in patients with triple-negative breast cancer. Artificial intelligence (AI)-derived computational tools assessing TILs could improve efficiency, but require independent validation against clinical outcomes. We aimed to compare the prognostic performance of AI-derived TIL scores with pathologist-scored TILs in a large, prospectively collected dataset pooled from randomised controlled trials.
Methods: CATALINA was an independent, external validation study using prospectively collected long-term clinical outcome data pooled from seven randomised clinical trials conducted at multiple sites. We independently evaluated two previously validated AI pipelines that generate five computationally assessed tumour-infiltrating lymphocyte (cTIL) scores by masked, independent deployment of locked models. cTIL scores were correlated with the mean of the pathologist-scored stromal TILs (sTILs) in 220 digitised haematoxylin and eosin whole slide images in a cohort of patients with early-stage triple-negative or HER-2 positive breast cancer, previously scored by trained pathologists in a TIL-reproducibility study. Prognostic performance was assessed in a separate cohort of patients with early triple-negative breast cancer pooled from seven prospective, randomised adjuvant trials. Multivariable Cox regression models adjusted for clinicopathological factors and study heterogeneity assessed associations of cTIL score and sTIL score with invasive disease-free survival, distant disease-free survival, and overall survival. 5-year discrimination was estimated using time-dependent area under the receiver operating characteristic curve (AUC).
Findings: Individual data were collated from 1759 patients, of whom 1356 had complete clinicopathological data, pathologist sTIL scores, and cTIL scores available. Modest correlation (r 0·375-0·473) was observed between cTIL scores and the mean pathologist sTIL score. Both sTIL and cTIL were independently associated with 5-year invasive disease-free survival, distant disease-free survival, and overall survival after adjustment for clinicopathological factors (hazard ratio for invasive disease-free survival was 0·73 [95% CI 0·66-0·82]; q<0·0001, distant disease-free survival was 0·70 [0·61-0·79]; q<0·0001, and overall survival was 0·72 [0·63-0·82]; q<0·0001 for sTIL scores and 0·80 [0·73-0·89]; q<0·0001, 0·77 [0·69-0·86]; q<0·0001, and 0·79 [0·70-0·88]; q=0·0002, respectively, for percentage_lymphocyte scores). In models adjusted for clinicopathological variables and sTIL score, cTIL score did not maintain a statistically significant prognostic association. Both sTIL and cTIL scores improved the 5-year AUC over clinicopathological variables alone, while cTIL score did not significantly further improve AUC when combined with clinicopathological variables and sTIL score.
Interpretation: Two cTIL models deployed entirely without retraining or modification provided statistically significant prognostic information and improved risk discrimination compared with clinicopathological variables alone in this large, platform-based, independent validation study. Although cTIL score did not incrementally improve prognostication compared with models combining clinicopathological variables with sTIL score, these findings support the application of cTILs as a reproducible prognostic biomarker, particularly in settings where routine or widespread pathologist assessment is unavailable.
Funding: Breast Cancer Research Foundation (USA).
Reference: Dixon-Douglas JR, Drubay D, Salgado R, Acs B, van der Laak J, Yuan Y, et al. Artificial intelligence-based tumour infiltrating lymphocyte quantification in patients with triple-negative breast cancer: an independent validation study. Lancet Oncol. 2026 Sep;27(9):1181-92. doi:10.1016/s1470-2045(26)00339-6. PMID: 42636839.Checked: Abstract only - Abstract
Background: Stromal tumour-infiltrating lymphocytes (sTILs) are prognostic in early-stage HER2-positive breast cancer, but their role in the context of dual HER2 blockade remains undefined. We evaluated manual, digital, and artificial intelligence (AI)-based sTIL quantification, together with AI-derived spatial metrics, for prognostic and treatment-benefit stratification using tumour samples from the phase 3 APHINITY trial.
Methods: In the APHINITY trial, 4805 patients were randomly assigned to receive chemotherapy plus trastuzumab with pertuzumab or chemotherapy plus trastuzumab with placebo. Median follow-up was 74·1 months (IQR 68·3-75·4). We analysed 4262 haematoxylin and eosin-stained images using manual assessment, an automated digital approach, AI-based lymphocyte quantification (AI percentage lymphocytes), and two AI-derived spatial features (AI-TIL and immune hotspot). Interobserver reproducibility was assessed in 262 randomly chosen tumour samples scored independently by five pathologists. Multivariable Cox models were used to assess associations between TIL levels and invasive disease-free survival (primary outcome in APHINITY), distant recurrence-free interval, and overall survival. The heterogeneity of pertuzumab benefit was evaluated using subgroup analyses, subpopulation treatment effect pattern plot analyses, and nested Cox models with treatment-by-biomarker interaction terms.
Findings: Manual scoring showed high interobserver reproducibility (intraclass correlation coefficient 0·84 [95% CI 0·79-0·88]). Concordance between manual and automated methods was modest. AI-based scoring (AI percentage lymphocytes) reclassified 120 (11·6%) of 1035 node-positive tumours from immune-low (by manual scoring) to immune-high; this subgroup of patients showed greater separation of 5-year invasive disease-free survival curves between pertuzumab and placebo groups compared with patients whose tumours were concordantly classified as immune-low by both manual and AI-based approaches. Higher levels of TILs were associated with improved invasive disease-free survival for all sTIL measurement approaches and spatial measurements (hazard ratios [HRs] 0·41-0·93). Pertuzumab was associated with improved invasive disease-free survival at higher sTIL levels across all measurement approaches (HRs 0·36-0·48), but was not associated with higher values of spatial measures. The largest 6-year absolute improvements with pertuzumab were observed in patients with node-positive disease whose tumours scored in the highest level of immune infiltration of manual sTIL scoring (≥70·0%; mean absolute improvement 12·1 percentage points [SD 2·8]). In nested prognostic and predictive models, AI-based immune hotspot scores provided the most consistent additional information when combined with any sTIL measurement (all p<0·010).
Interpretation: Standardised manual sTIL scoring was reproducible, and digital and AI-based methods showed consistent prognostic stratification and potential for treatment-benefit stratification despite only modest correlation between platforms. AI spatial metrics provided complementary information beyond sTIL density and could support more scalable immune assessment. Future studies are needed to validate these approaches in independent cohorts and to clarify their clinical utility for stratifying contemporary HER2-directed therapies.
Funding: None.
Reference: Lara González LE, Giudici F, Salgado R, Yan H, Rojo F, Comerma L, et al. Manual, digital, and AI tumour-infiltrating lymphocyte scoring: a secondary analysis of the APHINITY randomised trial. Lancet Oncol. 2026 Sep;27(9):1168-80. doi:10.1016/s1470-2045(26)00247-0. PMID: 42636838.Checked: Abstract only
Lung cancer: treatment, trials and AI
- Abstract
Despite a decade in, immunotherapy (IO) treatment selection in non-small cell lung cancer (NSCLC) remains largely guided by subgroup analyses and imperfect programmed death ligand 1 (PD-L1) and clinical scores. To our knowledge, I 3 LUNG ( NCT05537922 ) is currently the largest international, real-world, multimodal, artificial intelligence (AI)-based study, enrolling 2,396 patients. We integrated real-world clinical and blood (CB) data, computed tomography (CT) images, digital pathology (DP), and genomics into machine learning early fusion (MLEF) and deep learning intermediate fusion (DLIF) models. Machine learning (ML) and deep learning (DL) CB-only models achieved consistent performance across outcomes with area under the curve (AUC) up to 0.77 in the test (TEST) set. Performance drop in external validation (EXVAL) likely reflects population differences (AUC range: 0.55-0.72). AI models significantly surpassed PD-L1, Eastern Cooperative Oncology Group performance status (ECOG PS), neutrophil-to-lymphocyte ratio (NLR), lactate dehydrogenase (LDH) and Lung Immune Prognostic Index (LIPI) score in the independent TEST set. The clinical usability study showed that lung expert and nonexpert physicians improved their prediction with the explainable AI (XAI) ML CB-only based tool. Although multimodal integration with MLEF (CB+CT+DP) was associated with higher performance, its incremental benefit remains uncertain, not translated in TEST and EXVAL. The I 3 LUNG project is a pioneering framework showing the clinical usefulness of AI tools. A prospective validation of the decision support system (both CB and multimodal) is currently undergoing in more than 2,000 patients.
Reference: Prelaj A, Miskovic V, Sacco M, Ferrarin A, Licciardello CM, Provenzano L, et al. Clinical usability of an explainable AI decision support tool and evaluation of multimodal models in NSCLC. Nat Med. 2026 Sep 13;32(9):3235-47. doi:10.1038/s41591-026-04488-2. PMID: 42733093; PMCID: PMC13577906.Checked: Full text checked - Abstract
Multi-task DL for predicting EGFR mutation status Epidermal growth factor receptor (EGFR) mutation status is a critical biomarker in the management of non-small cell lung cancer (NSCLC), playing an essential role in selecting patients for EGFR-targeted treatment. With advancements in deep learning (DL), there is a growing interest in developing non-invasive methods for predicting EGFR mutation status. In this study, we present a multi-task deep learning (MTDL) model that utilizes CT images to predict EGFR mutation status (ChiCTR2400083082 in the WHO International Clinical Trials Registry). Our MTDL model achieved promising performance in accurately predicting EGFR mutation status. Additionally, the MTDL score was significantly associated with survival in patients receiving EGFR-targeted treatment, as well as relevant gene expression patterns and tumor microenvironment. These findings suggest that our method has the potential to serve as an accurate and non-invasive biomarker for predicting EGFR mutation status, thereby facilitating personalized treatment decisions for NSCLC patients.
Reference: Song Q, Li X, Song B, Ye W, Zhang T, Hu X, et al. Multi-task deep learning model for predicting EGFR mutation status in NSCLC. NPJ Digit Med. 2026 Jul 20 [Epub ahead of print]. doi:10.1038/s41746-026-03007-4. PMID: 42477500.Checked: Abstract only
Pancreatic cancer: treatment, trials and AI
- Abstract
Purpose: The choice of adjuvant chemotherapy in pancreatic ductal adenocarcinoma (PDAC) is mainly guided by patients' general condition. We hypothesized that tumor morphology may predict differential treatment benefit and tested whether deep learning applied to histology images could derive a biomarker of relative benefit from gemcitabine (GEM) versus modified FOLFIRINOX (mFOLFIRINOX) in resected PDAC. Patients and methods Standard whole-slide images from a retrospective multicentric series of 231 patients who underwent curative-intent pancreatectomy and received adjuvant mFOLFIRINOX (n = 54) or GEM (n = 177) were used to train regimen-specific histology models on disease-free survival (DFS), which were then combined into PANCprAId, a biomarker estimating personalized relative benefit from adjuvant GEM versus mFOLFIRINOX. External validation was performed in the randomized PRODIGE-24/CCTG PA6 trial (n = 313).
Results: In PRODIGE-24/CCTG PA6, the treatment-specific histology scores used to construct PANCprAId stratified outcomes among patients treated with GEM (hazard ratio [HR], 1.69 [95% CI, 1.04 to 2.73]; P = .03) and mFOLFIRINOX (HR, 2.02 [95% CI, 1.4 to 3.0]; P < .001). When combined into PANCprAId, the biomarker identified subgroups with differential relative benefit from adjuvant GEM versus mFOLFIRINOX, with significant treatment interactions for DFS (interaction P = .003) and cancer-specific survival (interaction P = .001). Predicted sensitivity to each regimen was associated with distinct epithelial and stromal features.
Conclusion: Histology-based deep learning can derive a predictive biomarker of relative benefit from adjuvant GEM versus mFOLFIRINOX in resected PDAC.
Reference: Beaufils A, De Martino J, Jiang X, Blanchard T, Fraunhoffer N, Mendes D, et al. Developing a Histology-Based Artificial Intelligence Biomarker to Predict Adjuvant Chemotherapy Benefit in Pancreatic Cancer. J Clin Oncol. 2026 Sep 10;44(26):2507-16. doi:10.1200/jco-26-00327. PMID: 42507965; PMCID: PMC13557473.Checked: Full text checked - Abstract
Pancreatic ductal adenocarcinoma (PDAC) is one of the most lethal malignancies worldwide, and accurate prognostic prediction remains highly challenging due to its marked biological heterogeneity and complex tumor microenvironment. To address this challenge, a histopathomics-based survival prediction system (HPSurv) was developed using histopathological whole-slide images (WSIs) for individualized overall survival (OS) prediction. Within this framework, pathological tissue classification, quantitative characterization of tumor spatial heterogeneity, and a survival Transformer were integrated to enable multi-level representation learning from histopathological data. The system was developed and evaluated in 1020 patients across five independent cohorts. Compared with conventional clinicopathological indicators, significantly improved prognostic performance was achieved across multicenter cohorts (p < 0.05), with a mean C-index of 0.761 and time-dependent AUCs of 0.936, 0.877, and 0.772 for predicting 6-month, 2-year, and 3-year survival, respectively. Subgroup analyses further supported its role as an independent prognostic factor and suggested its potential utility in stratifying patients with respect to ACT-related outcomes. In addition, significant associations with key PDAC molecular pathways were observed, providing biological insights into the model predictions and supporting interpretability. In the study, an interpretable and high-performing artificial intelligence (AI) framework for quantitative modeling of PDAC was established. Objective characterization of tumor heterogeneity and accurate postoperative survival prediction are enabled, with potential value for personalized management in PDAC.
Reference: Shao L, Ke X, Wang Y, Li R, Yu K, Wu J, et al. AI-driven tumor heterogeneity quantification and survival prediction in pancreatic ductal adenocarcinoma. NPJ Digit Med. 2026 Jul 20 [Epub ahead of print]. doi:10.1038/s41746-026-02979-7. PMID: 42477155.Checked: Abstract only
Prostate cancer: treatment, trials and AI
- Abstract
Risk stratification in primary prostate cancer remains heavily reliant on clinicopathological criteria that frequently miss the heterogeneity underlying early aggressive disease. We present a novel machine learning non-linear prognostic framework encoding somatic copy-number alterations and biological information associated with gene products, along with an integrative multi-omics approach including epigenomics and transcriptomics into a patient-specific biological network. Applied to the TCGA-PRAD (n = 498), our weighted graph-based feature selection and LASSO-Cox model identified ZNF268 as a master regulator gene, in which the hypermethylation of its promoter region is linked to a distinct oncogenic transition exclusive to Low/Intermediate-risk disease. Post-hoc analysis of Low-ZNF268 tumors showed a distinct somatic landscape enriched for driver mutations and predicted sensitivity to MAPK, ATR, and PI3K/mTOR inhibitors, providing potential therapeutic vulnerabilities alongside the prognostic signal. Topological network analysis further revealed that ZNF268 loss impacts a co-expression rewiring gene network, quantified as a Rewiring Score: associated with Progression-Free Survival in the TCGA-PRAD (HR: 2.79, 95% CI: 1.36-5.71, p = 0.0049) and Biochemical Recurrence in two external cohorts. By capturing tumors at an active molecular transition state preceding systemic progression, this framework offers a prognostic tool to identify biologically aggressive prostate cancer disease within patients currently undertreated by standard risk criteria.
Reference: Rafeletou A, Fathi F, Kiseļova T, Taheri G, Lundberg A. A novel multiomics machine learning signature identifies rapid progression in clinically low risk prostate cancer. NPJ Digit Med. 2026 Sep 14;9(1):702. doi:10.1038/s41746-026-03254-5. PMID: 42736338; PMCID: PMC13575102.Checked: Full text checked - Abstract
Background: Long-term androgen deprivation therapy (LT-ADT) with radiotherapy is standard-of-care for high-risk localized prostate cancer, with abiraterone added for clinically very high-risk disease. Given the potential toxicity and cost of abiraterone, a predictive biomarker to refine patient selection is needed. We evaluated a digital pathology multimodal artificial intelligence (MMAI) model, previously validated as a prognostic biomarker, for prediction of abiraterone benefit among nonmetastatic clinically very high-risk prostate cancer. Patients and methods MMAI scores were generated for patients enrolled in two sequential abiraterone trials (no shared controls) in the STAMPEDE (Systemic Therapy in Advancing or Metastatic Prostate Cancer: Evaluation of Drug Efficacy) platform protocol (NCT00268476) using digital pathology images, prostate-specific antigen, tumor stage, and age. We applied the previously established 75th percentile threshold to classify patients as MMAI very high-risk or standard high-risk. The primary endpoint was metastasis-free survival (MFS). Treatment effects and risk estimates were obtained using Cox regression and Kaplan-Meier method, respectively. Prediction was assessed using a treatment-by-biomarker interaction Cox model.
Results: In total, 1137 patients randomly assigned to LT-ADT (N = 583) or LT-ADT with abiraterone (N = 554) were included. The MMAI very high-risk group (N = 268) demonstrated significant MFS improvement from adding abiraterone [hazard ratio (HR) 0.47, 95% confidence interval (CI) 0.31-0.70], with 5-year MFS increasing from 62% (95% CI 54% to 70%) in LT-ADT to 81% (95% CI 74% to 88%) in LT-ADT with abiraterone. Limited abiraterone benefit was observed in the MMAI standard high-risk group (N = 869; HR 0.83, 95% CI 0.63-1.09), with a 5-year MFS of 82% (95% CI 78% to 85%) versus 84% (95% CI 80% to 87%, interaction P-value = 0.02). This differential effect was consistent in local node-negative and node-positive subgroups.
Conclusion: In this post hoc study of randomized clinical trial data, a locked digital pathology MMAI test displayed a strong prognostic association and predicted abiraterone efficacy in very high-risk, nonmetastatic prostate cancer. This biomarker could be implemented clinically to maximize benefit from treatment intensification while avoiding unnecessary toxicity.
Reference: Parker CTA, Huang HC, Grist E, Mendes L, Yamashita R, Croucher D, et al. Multimodal artificial intelligence prediction of abiraterone efficacy in two STAMPEDE phase III trials of nonmetastatic very high-risk prostate cancer. Ann Oncol. 2026 Oct;37(10):1334-44. doi:10.1016/j.annonc.2026.05.708. PMID: 42250604.Checked: Abstract only
Adenoid cystic carcinoma: treatment, trials and AI
No new qualifying paper in the covered journals for this issue.
Brain tumours: treatment, trials and AI
No new qualifying paper in the covered journals for this issue.
Ovarian cancer: treatment, trials and AI
No new qualifying paper in the covered journals for this issue.
Endometrial cancer: treatment, trials and AI
No new qualifying paper in the covered journals for this issue.
Gastric cancer: treatment, trials and AI
No new qualifying paper in the covered journals for this issue.
Liver cancer: treatment, trials and AI
No new qualifying paper in the covered journals for this issue.
Kidney cancer: treatment, trials and AI
No new qualifying paper in the covered journals for this issue.
Bladder cancer: treatment, trials and AI
No new qualifying paper in the covered journals for this issue.