AI and Cancer Research ── 2026-10-26
New papers on cancer and AI, collected from journal feeds, PubMed (searched across all journals) and OpenAlex (a public index used instead of Google Scholar), judged by Jev (an AI that makes language judgements): original research, AI central, which of 13 themes, treatment or trials, and then ranked by importance up to a daily limit. Journals are not filtered by impact factor; each paper shows its journal's IF-equivalent (OpenAlex two-year mean citedness) and the date of that value. Each entry shows the full original abstract.
Read by cancer type: Cancer biology（2） · Breast（2） · Lung（1） · Pancreatic（0） · Prostate（1） · ACC（0） · Brain（2） · Ovarian（0） · Endometrial（0） · Gastric（1） · Liver（2） · Kidney（0） · Bladder（1）
Cancer molecular biology and AI
- Abstract
Single-cell glycan and RNA sequencing (scGR-seq) enables characterization of cellular glycan heterogeneity. Here, we present scGlycoAI, an interpretable machine learning framework that integrates scGR-seq data for glycan-centered biological discovery. Using lectin-binding profiles as input, scGlycoAI employs hierarchical machine learning to accurately classify cell types and subtypes within complex tumor microenvironments. Applied to pancreatic ductal adenocarcinoma (PDAC) datasets, scGlycoAI achieved an overall eight-class classification accuracy of 90.3% under leave-one-patient-out validation using glycan features alone. These results demonstrate that glycan signatures, despite their lower dimensionality compared with transcriptomic profiles, are sufficient for robust cell-type annotation and represent cell-type-specific molecular signatures. Feature importance analysis identified PVL lectin binding, which reflects recognition of sialylated and/or GlcNAc-containing glycans, as a key feature of aggressive cancer states. A neural-network model combined with SHAP-based interpretation further revealed that elevated PVL binding was associated with transcriptional programs linked to epithelial-mesenchymal transition, KRAS signaling, extracellular matrix remodeling, and inflammatory responses. Higher expression of the PVL-associated gene signature was associated with poorer overall survival in the TCGA pancreatic adenocarcinoma cohort. Collectively, these findings suggest that glycan-based machine learning enables accurate cell classification while providing biological insights into malignancy-associated glycan states at single-cell resolution. This framework provides a foundation for glycan-centered biomarker discovery and glycan-targeted therapeutic development.
Journal IF-equivalent: 2.3 (OpenAlex 2-year mean citedness, value as of 2026-10-25, retrieved 2026-10-26; not the official Clarivate IF)Reference: Anh DXT, Tateno H. scGlycoAI: Machine learning analysis of single-cell glycan and RNA sequencing data for cell-type annotation and malignancy-associated glycan discovery. Glycobiology. 2026 Oct 24 [Epub ahead of print]. doi:10.1093/glycob/cwag100. PMID: 42925266.Checked: Abstract only - Abstract
In clinical liver MRI, diffusion-weighted imaging (DWI) and dynamic contrast-enhanced (DCE) imaging are commonly used and complementary sequences, particularly for liver tumor diagnosis and assessment. Accurate registration between the two modalities facilitates subsequent quantitative analysis and multi-modal image-based evaluation. Although deep learning has achieved remarkable progress in image registration, considerable challenges remain in multi-parametric liver imaging, mainly due to substantial contrast differences, pronounced respiratory motion, limited single-center training data, and inter-center heterogeneity. This study proposes a cross-modal registration framework for liver DWI and DCE across multi-center datasets. First, a multi-task synthesis-registration network (SynReg) is introduced, which integrates image synthesis and registration within a unified architecture to reduce cross-modal appearance discrepancy and facilitate deformable registration. To further improve personalized learning under cross-center heterogeneity, we propose a personalized decentralized distribution matching (PDDM) framework with SynReg as the backbone. PDDM performs compatibility-aware selective collaboration by identifying compatible external training cases and constructing client-specific collaboration relationships. Signal-to-noise ratio (SNR) distributions are used as a lightweight compatibility descriptor, while the synthesis components remain local and the registration network is selectively aggregated among compatible clients. The framework was evaluated on six datasets collected from five medical centers and acquired on MRI systems from three vendors under both low- and high-b-value settings. PDDM consistently achieved more favorable registration performance than single-center training and representative personalized federated learning methods, while remaining closely competitive with centralized pooled-data training. In comparisons with alternative matching strategies, PDDM showed the most consistently favorable overall performance across centers, b-value settings, and registration metrics. These findings support compatibility-aware selective collaboration as an effective strategy for personalized multi-center liver image registration. Code will be available at https://github.com/ZIC-skyzrc/PDDM-SynReg.
Journal IF-equivalent: 12.5 (OpenAlex 2-year mean citedness, value as of 2026-10-25, retrieved 2026-10-26; not the official Clarivate IF)Reference: Zheng R, Yu H, Wu X, Xia X, Li R, Wang Q, et al. Distribution matching based personalized federated learning for multi-center, cross-modal liver image registration. Medical Image Analysis. 2027 Feb;116:104365. doi:10.1016/j.media.2026.104365.Checked: Abstract only
See all 2 Cancer biology papers →
Breast cancer: treatment, trials and AI
- Abstract
Background: Accurate breast cancer mortality prediction is constrained by severe class imbalance and the sensitivity-specificity trade-off, which frequently induces high false-positive rates in clinical settings. To address this limitation, we propose a rigorously calibrated Static Stacking Ensemble framework.Methods: The model was developed from the METABRIC cohort (N=1816) using 5-fold stratified cross-validation, while the SEER dataset (N=4024) was reserved for independent external validation. The architecture combines out-of-fold (OOF) predictions from deep neural network, XGBoost, and random forest base learners. To replace the standard fixed decision threshold (default τ=0.5), we used a data-driven threshold based on Youden’s J statistic.Results: Baseline models had important limitations, including a specificity of 0.1997 in standalone deep learning and weight collapse in evolutionary ensembles. At the optimized decision threshold (τ=0.7378), the proposed model balanced sensitivity and specificity. Evaluated on the independent cohort, the model yielded a specificity of 0.6996, a sensitivity of 0.7298, an accuracy of 0.7212, and an F1 score of 0.7894. The framework achieved a ROC-AUC of 0.6925, an area under the precision-recall curve (PR-AUC) of 0.8914, and a Brier score of 0.1563.Conclusion: Combining OOF prediction stacking with an optimized decision threshold provides a calibrated clinical decision support system (CDSS). This framework minimizes prognostic false alarms and robustly stratifies high-risk patients across heterogeneous cohorts, significantly outperforming isolated baseline architectures.
Journal IF-equivalent: 0.5 (OpenAlex 2-year mean citedness, value as of 2026-10-25, retrieved 2026-10-26; not the official Clarivate IF)Reference: Abdollahi J, Gardaneh M. Calibrated Stacking Ensemble Framework for High-Fidelity Breast Cancer Mortality Prediction. Arch Breast Cancer. 2026 Oct 23;13(4):474-85. doi:10.32768/abc.7294618352-074.Checked: Abstract only - Abstract
BACKGROUND: Breast cancer is the most frequently diagnosed malignancy in women globally, accounting for approximately 2.30 million new cases and 666,103 deaths in 2022. Artificial intelligence technologies including machine learning, deep learning, radiomics, and natural language processing have been widely applied across the breast cancer care continuum. However, no systematic review restricted to primary studies with patient-level or image-level data has synthesized evidence spanning all clinical domains simultaneously. OBJECTIVES: To evaluate the performance, methodological quality, and clinical relevance of artificial intelligence primary studies across screening and diagnostic imaging, digital pathology, radiomics, perioperative management, prognostic prediction, and natural language processing in breast cancer. METHODS: PubMed/MEDLINE, Scopus, Web of Science, Embase, and the Cochrane Library were searched from January 2015 to May 2026. Eligibility was restricted to original primary research reporting patient-level or image-level data; secondary syntheses were explicitly excluded. Risk of bias was assessed using QUADAS-2 and PROBAST. Reporting followed PRISMA 2020 guidelines. RESULTS: Of 5,275 identified records, 17 primary studies met eligibility criteria. In screening mammography (seven studies; n = 7,540 to 144,231 examinations), deep learning achieved area under the receiver operating characteristic curve (AUC) values of 0.876 to 0.939; a randomised trial in 80,033 women demonstrated non-inferiority to double reading with a 44.3% reduction in radiologist workload. In digital pathology (five studies; 270 to 44,732 whole-slide images), deep learning achieved AUC 0.985 to 0.994, exceeding unassisted pathologist performance in lymph node metastasis detection. Magnetic resonance imaging radiomics predicted pathological complete response in HER2-positive breast cancer with AUC 0.80. No breast cancer-specific perioperative primary study met the eligibility criteria. Deep survival networks achieved concordance index 0.626 versus 0.612 for Cox regression in breast cancer cohorts. Natural language processing identified metastatic recurrence in breast cancer clinical records with sensitivity 83% and specificity 73%. Risk of bias was low to moderate for imaging and pathology studies and high for small sample radiomics studies. Density-stratified performance was reported by only two imaging studies, and receptor status prediction from haematoxylin and eosin staining had not been validated as a safe alternative to immunohistochemistry. CONCLUSIONS: Artificial intelligence demonstrated clinically meaningful performance across the five domains with eligible primary studies. Breast cancer-specific perioperative and intensive care primary studies were absent, representing the largest evidence gap. External validation, demographic diversity, and prospective clinical integration evidence remained the most consistently identified limitations. Prediction of molecular receptor status without immunohistochemistry requires rigorous prospective safety validation before it can complement standard testing.
Journal IF-equivalent: 0.0 (OpenAlex 2-year mean citedness, value as of 2026-10-25, retrieved 2026-10-26; not the official Clarivate IF)Reference: [No authors listed]. Artificial Intelligence in Breast Cancer Diagnosis, Treatment, and Perioperative Management: A Systematic Review of Current Applications and Future Perspectives. Clin Ter. [Epub ahead of print]. doi:10.7417/CT.2026.2172. PMID: 42922241.Checked: Abstract only
Lung cancer: treatment, trials and AI
- Abstract
Small cell lung cancer (SCLC) is among the most lethal thoracic malignancies, and timely and accurate histopathological classification is critical for guiding treatment decisions. Existing deep learning approaches face difficulty simultaneously capturing the high-frequency nuclear texture features characteristic of SCLC—such as hyperchromatic salt-and-pepper chromatin and dense nuclear moulding—and the long-range spatial dependencies of tissue organisation, limiting classification reliability. To address these challenges, this study proposes SCLC-SBT, a hierarchical Spectral-Bilinear Transformer for automated SCLC histopathological image classification. The network deploys re-parameterizable Hybrid-Conv Blocks (HCB) with frequency-domain Spectral-Channel Attention (SCA) in the first three stages to extract fine-grained multi-scale local features, and employs a novel Dual-Branch Conv Linear Integration Transformer (DBCLIT) in the deepest stage to jointly model local morphology and long-range dependencies via bilinear selective state space modelling. Evaluated on a 1,974-image binary classification benchmark comprising Normal and SCLC tissue patches, SCLC-SBT achieves 0.9697 accuracy (95% CI 0.9495 to 0.9865), 0.9728 F1-score, and 0.9971 AUC, attaining the best point estimate among eleven compared architectures including DeiT, MLP-Mixer, DaViT, and CAFormer on five of the seven reported metrics. Bootstrap confidence intervals and pairwise McNemar’s tests indicate that this advantage is statistically significant relative to five of the eleven baselines. Relative to the six strongest baselines, DeiT, MLP-Mixer, CAFormer, Swin-T, and the tied PoolFormer and DaViT pair, the difference is not statistically significant at $$\alpha =0.05$$ on the 297-sample test set, so SCLC-SBT is best interpreted as achieving competitive to superior accuracy at a substantially better accuracy-efficiency trade-off while maintaining competitive model efficiency with approximately 17 M parameters and 7.0 G FLOPs. The results demonstrate that integrating spectral-domain channel recalibration with bilinear state space modelling provides an effective inductive bias for SCLC histopathological feature learning.
Journal IF-equivalent: 5.2 (OpenAlex 2-year mean citedness, value as of 2026-10-04, retrieved 2026-10-05; not the official Clarivate IF)Reference: Liang S, Liang Y, Zheng Q, Yang J. SCLC-SBT: a spectral-bilinear transformer for small cell lung cancer histopathology image classification. Sci Rep. 2026 Oct 24 [Epub ahead of print]. doi:10.1038/s41598-026-76898-8.Checked: Abstract only
Pancreatic cancer: treatment, trials and AI
No new qualifying paper for this issue.
Prostate cancer: treatment, trials and AI
- Abstract
Intraoperative digital guidance is increasingly being integrated into robot-assisted radical prostatectomy and robot-assisted partial nephrectomy to improve oncological precision while preserving functional outcomes. The supporting clinical evidence remains limited and heterogeneous. This systematic review, conducted in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) 2020 guidelines and prospectively registered in PROSPERO (CRD420261400733), searched PubMed, Ovid Embase, and the Cochrane Library for English-language studies published between 1 January 2025 and 20 May 2026. Eligible studies were prospective investigations involving adults undergoing robot-assisted radical prostatectomy or robot-assisted partial nephrectomy for primary urological malignancy, evaluating intraoperative augmented reality, mixed reality, artificial intelligence (AI)-assisted pathology, and related image-guided technologies with at least one patient-level clinical or diagnostic endpoint. Narrative synthesis was performed because of substantial heterogeneity, and risk of bias was assessed using design-specific tools. Of the 131 records screened, 93 were excluded at the title and abstract screening stage, 22 reports underwent full-text eligibility assessment after removal of duplicates, 16 reports were excluded at the full-text eligibility assessment stage, and six studies were included in the narrative synthesis. In radical prostatectomy, 3D AI-augmented reality guidance and AI-enhanced stimulated Raman histopathology showed promising signals for surgical margin control, adjuvant treatment, continence, and intraoperative margin assessment. In partial nephrectomy, mixed reality improved warm ischaemia time and clamping strategy, while 3D image-guided surgery demonstrated acceptable medium-term oncological and functional outcomes. Overall, prospective evidence suggests that intraoperative digital guidance may improve selected oncological, functional, technical, and diagnostic outcomes in robotic urological surgery, but larger multicentre comparative trials with standardised endpoints and longer follow-up are required.
Journal IF-equivalent: 1.2 (OpenAlex 2-year mean citedness, value as of 2026-10-25, retrieved 2026-10-26; not the official Clarivate IF)Reference: Harrison G. Prospective Clinical Evidence on Artificial Intelligence-Enabled Augmented and Mixed Reality in Robot-Assisted Prostate and Kidney Cancer Surgery: A Systematic Review. Cureus. 2026 Sep 23 [Epub ahead of print]. doi:10.7759/cureus.116810.Checked: Abstract only
Adenoid cystic carcinoma: treatment, trials and AI
No new qualifying paper for this issue.
Brain tumours: treatment, trials and AI
- Abstract
Purpose: Artificial intelligence(AI)-based feature extraction from whole slide images (WSIs) shows significant promise for glioma prognosis. However, while foundation pathology models have potential, their features typically lack biological interpretability and clear links to disease mechanisms, limiting their clinical translational value.
Methods: We propose a clustering Vision Transformer (ViT)–based framework for pathological image analysis. Tens of thousands of image patches extracted from each WSI were first clustered into 100 groups. The foundation-model features of the 100 cluster centroids, together with the proportional representation of each cluster across the whole slide, were then integrated and input into the ViT model for prognostic prediction. The image-derived risk scores were further integrated with matched RNA-seq data to identify risk-associated genes and biological pathways through differential expression and pathway enrichment analyses. Prognostic prediction was developed and evaluated in a total of 2552 cases, including 559 cases from Huashan Hospital for training and internal testing, 309 cases from Shanghai International Hospital as external validation cohort 1, and 1684 cases from TCGA as external validation cohort 2. Pathogenomic analyses were performed in 567 TCGA cases with matched WSI and RNA-seq data and further validated in 657 CGGA cases.
Results: Risk scores produced by the prognostic model showed a significant correlation with patient survival (log-rank P < 0.001). When integrated into existing risk stratification frameworks, these risk scores enhanced survival predictions via a nomogram based on clinical information and risk score compared to a traditional clinical-molecular nomogram, achieving a C-index of 0.90, superior calibration and classification accuracy (net reclassification improvement = 0.99, P < 0.001). Specific genes and pathways demonstrated significant associations with risk scores, and the mean expression levels of these key genes exhibited strong prognostic value across both the pathogenomics cohort and the CGGA dataset (log-rank P < 0.001).
Conclusion: These results demonstrate that risk scores derived from pathological imaging can effectively identify key genes and biological pathways critical for stratifying glioma patients into high- and low-risk subgroups. Consequently, therapeutic strategies that modulate the tumor immune microenvironment may be particularly beneficial for high-risk patients identified by this approach.
Journal IF-equivalent: 5.4 (OpenAlex 2-year mean citedness, value as of 2026-10-25, retrieved 2026-10-26; not the official Clarivate IF)Reference: Pan T, Shi Z, Chen J, Yu J, Wu G. Prognostic risk stratification in glioma based on the foundation pathology model with identification of key genes and biological pathways associated with prognosis: a multicenter study. acta neuropathol commun. 2026 Oct 24 [Epub ahead of print]. doi:10.1186/s40478-026-02456-y.Checked: Abstract only - Abstract
BACKGROUND: Optimal surgical management of adult-type diffuse gliomas (ADGs) varies substantially by subtype, making accurate preoperative subtyping crucial for individualized surgical planning. This study aimed to develop a radiomics-based model for preoperative subtyping of ADG in accordance with the 2021 World Health Organization (WHO) Classification of Central Nervous System Tumors. METHODS: A total of 382 patients with ADGs were enrolled and randomly assigned to a training set (n = 267) and an independent test set (n = 115). Tumor masks were automatically segmented and refined by experienced neurosurgeons. Radiomics features were extracted from MRI after standardized preprocessing and dimensionality reduction. Fourteen machine learning classifiers were evaluated, and the best-performing model was optimized and validated on the independent test set. Model performance was assessed using AUC, accuracy, recall, precision, F1 score, Kappa coefficient, and Matthews correlation coefficient. RESULTS: After LASSO (Least Absolute Shrinkage and Selection Operator) regression, 50 key features were retained. Random Forest showed the best preliminary performance and was selected for optimization. On the independent test set, the optimized model achieved a macro-average AUC of 0.9084, with favorable results across other metrics. Texture features contributed most strongly to prediction. CONCLUSION: This radiomics model enables robust preoperative ADG subtyping under the 2021 WHO classification and may support individualized surgical planning using routine MRI features. Owing to its retrospective single-center design, multicenter prospective external validation is required prior to widespread clinical application.
Journal IF-equivalent: 6.3 (OpenAlex 2-year mean citedness, value as of 2026-10-25, retrieved 2026-10-26; not the official Clarivate IF)Reference: Liang Y, Shi J, Zhao C, Liu J, Li K, Yang J, et al. Radiomics‐Assisted Preoperative Subtyping of Adult‐Type Diffuse Gliomas: A Retrospective Study Aligned With the WHO 2021 Classification. CNS Neurosci Ther. 2026 Oct 23;32(10):e71225. doi:10.1002/cns.71225. PMID: 42924459.Checked: Abstract only
Ovarian cancer: treatment, trials and AI
No new qualifying paper for this issue.
Endometrial cancer: treatment, trials and AI
No new qualifying paper for this issue.
Gastric cancer: treatment, trials and AI
- Abstract
BACKGROUND: Visceral adipose tissue (VAT) is associated with tumor progression in gastric cancer (GC), but its added value for predicting lymph node metastasis (LNM) remains unclear. PURPOSE: This study aimed to construct a DR-DLR model that incorporates CT-based features from both VAT and tumor, with the goal of predicting LNM in GC patients, while investigating its biological relevance. METHODS: 855 GC patients were retrospectively collected across three clinical centers, divided into a primary cohort, one internal test cohort, and two independent external validation cohorts. An Attention Residual Transformation Network (ARTNet) extracted imaging representations from CT images. Feature representations and clinical variables were integrated using a multilayer perceptron (MLP) to build the DR-DLR model. Model performance, generalizability, prognostic value, and biological relevance were evaluated using internal/external testing, radiologist comparison, survival analysis, and radiogenomics analysis. RESULTS: Incorporation of VAT-derived features improved predictive performance compared with tumor-only models. The DR-DLR model achieved areas under the receiver operating characteristic curve (AUC) of 0.898 (95 % CI: 0.817-0.946), 0.834 (95 % CI: 0.743-0.897), and 0.848 (95 % CI: 0.775-0.901) in the internal and two external test cohorts, respectively. It outperformed junior and senior radiologists in LNM assessment. Overall survival was shorter in high-risk patients than in low-risk. Radiogenomics analysis revealed that the high-risk phenotype was associated with activation of immune-related pathways and increased infiltration of CD4 + T cells, plasma cells, dendritic cells, and mast cells. CONCLUSION: The DR-DLR model improved LNM prediction, with its high-risk phenotype linked to immune-related molecular alterations, supporting its value for preoperative risk stratification.
Journal IF-equivalent: 3.6 (OpenAlex 2-year mean citedness, value as of 2026-10-11, retrieved 2026-10-12; not the official Clarivate IF)Reference: Miao S, Xiong Z, Yang H, Zhang L, Qi H, Liu Z, et al. Incorporating visceral adipose tissue into dual-region deep learning radiomics on CT improves preoperative lymph node metastasis prediction in gastric cancer: A multicenter study. European Journal of Radiology. 2027 Jan;206:113309. doi:10.1016/j.ejrad.2026.113309.Checked: Abstract only
Liver cancer: treatment, trials and AI
- Abstract
PURPOSE: To develop a Magnetic resonance imaging (MRI) -based radiomics-clinical model for noninvasive prediction of fibroblast activation protein (FAP) expression in hepatocellular carcinoma (HCC), and to explore its association with tumor microenvironment (TME) characteristics and potential immunotherapy response. PATIENTS AND METHODS: This retrospective study included 104 patients with HCC from the Fourth Hospital of Hebei Medical University, 31 external MRI cases from The Cancer Imaging Archive (TCIA), and 363 transcriptomic profiles from The Cancer Genome Atlas (TCGA). Immunohistochemistry (IHC) assessed FAP expression. Tumor regions were manually segmented, and radiomics features were extracted using PyRadiomics. Multiple machine learning classifiers were used to construct and validate models for predicting FAP expression. Logistic regression was selected for its balanced performance between the training and validation cohorts, with the smallest area under the curve (AUC) difference among the five machine-learning algorithms. A radiomics-clinical combined model was further developed by integrating the radscore with clinical indicators. Radiogenomic analysis explored radscore-related transcriptomic features and immune infiltration characteristics. RESULTS: In the validation cohort, the AUC values of the intratumoral, peritumoral, and intratumoral + peritumoral radiomics models were 0.757, 0.502, and 0.784, respectively. The intratumoral + peritumoral model also achieved a sensitivity of 0.692 and a specificity of 0.788, indicating the best overall discriminatory performance among the three models. The radiomics-clinical combined model integrating the systemic immune-inflammation index (SII), prognostic nutritional index (PNI), and radscore achieved an AUC of 0.816 in the validation cohort. Radscore-related transcriptomic modules identified 10 hub genes for risk stratification. Patients in the high-risk group exhibited a more pronounced immunosuppressive TME and poorer predicted benefit from immunotherapy. CONCLUSION: The MRI-based radiomics-clinical model effectively predicted FAP expression in HCC. Radscore reflected FAP-related immunosuppressive TME remodeling and may provide insights into potential immunotherapy response stratification, which requires further validation in independent immunotherapy-treated cohorts.
Journal IF-equivalent: 2.9 (OpenAlex 2-year mean citedness, value as of 2026-10-02, retrieved 2026-10-03; not the official Clarivate IF)Reference: Gao R, Han G, Wang Q, Zhang M, Yin F. MRI-Based Radiomics Predicts FAP Expression and Immunosuppressive Tumor Microenvironment in Hepatocellular Carcinoma. J Hepatocell Carcinoma. 2026 Oct;Volume 13:1-18. doi:10.2147/jhc.s641948. PMID: 42924263.Checked: Abstract only - Abstract
BACKGROUND: Although combining systemic and locoregional therapies has improved outcomes for hepatocellular carcinoma (HCC), identifying appropriate candidates remains challenging because no reliable tool predicts response. METHODS: This retrospective multicenter study enrolled 334 HCC patients who received first-line locoregional-systemic therapy from nine centers in China. Following automated tumor segmentation using nnU-Net on pretreatment contrast-enhanced magnetic resonance imaging, predefined radiomics features were computationally extracted, and deep learning features were obtained via a ResNet convolutional neural network. Three types of predictive models for tumor response (radiomics, deep learning, and combined) were developed and validated on the training cohort ( n = 213), internal validation cohort (IVC, n = 53), and external validation cohort (EVC, n = 68). Performance was assessed using area under the receiver operating characteristic curve (AUC) and net reclassification improvement (NRI). Associations of model with progression-free survival (PFS) and overall survival (OS) were evaluated. RESULTS: Among the three models (multi-sequence radiomics, multi-sequence deep learning, and combined), the combined model showed the best predictive performance in both the training (AUC: 0.997, 95% CI: 0.994-1.000) and validation cohorts (AUC of IVC 0.900, 95% CI: 0.806-0.994; AUC of EVC: 0.871, 95% CI: 0.790-0.951). The combined model demonstrated significantly improved predictive performance compared with the multi-sequence radiomic model (training NRI = 43.9%, p p = 0.038; EVC NRI = 3.2%, p = 0.806) and multi-sequence deep learning model (training NRI = 80.8%, IVC NRI = 72.7%, EVC NRI = 50.4%; all p < 0.05). Specifically, the combined model was significantly associated with both PFS and OS. CONCLUSIONS: The combined radiomics-deep learning model outperformed both single-modality models in predicting objective response and stratifying survival outcomes in unresectable HCC patients receiving combined systemic and locoregional therapy.
Journal IF-equivalent: 5.3 (OpenAlex 2-year mean citedness, value as of 2026-10-24, retrieved 2026-10-26; not the official Clarivate IF)Reference: Wang LN, Zhou SQ, Li F, Wu LF, Xu L, Wang K, et al. Integrating Magnetic Resonance Imaging-Based Deep Learning and Radiomics to Predict Treatment Response in Hepatocellular Carcinoma Receiving Combined Systemic and Locoregional Therapies: A Multicenter Study. Liver Cancer. 2026 Sep 7 [Epub ahead of print]. doi:10.1159/lic/admag009. PMID: 42924067.Checked: Abstract only
Kidney cancer: treatment, trials and AI
No new qualifying paper for this issue.
Bladder cancer: treatment, trials and AI
- Abstract
Bladder cancer (BCa) displays marked molecular heterogeneity and carries substantial risks of recurrence, progression and treatment resistance, highlighting the need for new biomarkers defined at the level of cellular states. Here, we integrated single-cell RNA sequencing (scRNA-seq), spatial transcriptomics (ST), bulk RNA sequencing (bulk RNA-seq), machine-learning (ML) models and immunotherapy cohorts to characterize highly stem-like malignant epithelial cells in BCa. Based on scRNA-seq data, malignant epithelial cells were identified using CopyKAT and then divided into LowStem, IMStem and HighStem groups according to within-patient CytoTRACE scores. Cell–cell communication and pathway analyses showed extensive inferred interactions between HighStem malignant epithelial cells and immune, fibroblast and endothelial cells. HighStem cells also showed higher scores for DNA repair, oxidative phosphorylation, MYC and E2F pathways, but lower scores for transforming growth factor-β (TGF-β), Notch and WNT/β-catenin pathways. By integrating high-dimensional weighted gene co-expression network analysis (hdWGCNA), differential-expression analysis, survival analysis, ST validation and ML modelling, we identified TXNL4A, APEX1, TIMM8B, MDH2, TRMT112, C1QBP, CYC1 and BANF1 as core risk genes. The Gaussian naïve Bayes (NB) model showed favorable overall classification performance in both cohorts. Shapley additive explanations (SHAP) indicated that all eight genes contributed to the identification of HighStem cells. Immunotherapy-cohort analyses suggested that TXNL4A, BANF1 and MDH2 may be associated with immunotherapy response. Virtual knockout analysis suggested that the BANF1-associated network involves protein synthesis, mitochondrial function and cell adhesion. These findings provide a potential molecular basis for understanding stemness heterogeneity in BCa and may inform the development of individualized treatment strategies.
Journal IF-equivalent: 2.4 (OpenAlex 2-year mean citedness, value as of 2026-10-12, retrieved 2026-10-13; not the official Clarivate IF)Reference: Liu X, Xiao Z, Wang Y, Huang L. Integrative single-cell and spatial transcriptomics combined with machine learning reveals molecular features and key risk genes of high-stemness malignant epithelial cells in bladder cancer. Discov Onc. 2026 Oct 23 [Epub ahead of print]. doi:10.1007/s12672-026-06196-2.Checked: Abstract only