AI and Cancer Research ── 2026-10-15
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（1） · Breast（2） · Lung（2） · Pancreatic（0） · Prostate（0） · ACC（0） · Brain（2） · Ovarian（0） · Endometrial（0） · Gastric（0） · Liver（1） · Kidney（0） · Bladder（0）
Cancer molecular biology and AI
- Abstract
Accurate prediction of postoperative recurrence is essential for individualized management and follow-up planning in patients with upper tract urothelial carcinoma (UTUC). However, reliable risk stratification remains challenging due to the heterogeneous nature of imaging characteristics and clinical information. In this study, we propose a multimodal clinical decision support framework that integrates contrast-enhanced computed tomography (CT) images with routinely available clinical variables for postoperative recurrence prediction. The proposed framework adopts an image-clinical integrated learning strategy to enhance semantic alignment between visual representations and patient-specific clinical context. Imaging features are guided by clinically informed semantic prompts, while a dynamic fusion mechanism adaptively balances the contributions of different modalities. This design enables robust multimodal interaction and improves the individualized risk estimation. The framework is evaluated using a retrospective UTUC cohort of 160 patients treated between 2016 and 2023, including 59 recurrence cases and 101 nonrecurrence cases. Experimental results demonstrate that the proposed method achieves an area under the receiver operating characteristic curve (AUC) of 0.87, demonstrating superior performance compared with conventional convolutional neural network-based models and representative multimodal baselines. Qualitative analyses further indicate improved alignment between imaging patterns and clinical factors, providing interpretable insights through attention-based visualization. These findings suggest that the proposed multimodal framework provides a potential approach for postoperative UTUC recurrence risk stratification and has the potential to support clinical decision-making and risk-adapted postoperative management.
Journal IF-equivalent: 3.9 (OpenAlex 2-year mean citedness, value as of 2026-10-13, retrieved 2026-10-15; not the official Clarivate IF)Reference: Liu D, Zhao T, Zhang S, Fang L. CLIP-CGPNet: A Multimodal Clinical Decision Support System for Postoperative UTUC Recurrence Prediction. J Digit Imaging Inform med. 2026 Oct 13 [Epub ahead of print]. doi:10.1007/s10278-026-02358-4.Checked: Abstract only
See all 1 Cancer biology papers →
Breast cancer: treatment, trials and AI
- Abstract
Preoperative molecular subtyping of breast cancer is essential for treatment selection and prognosis assessment, yet most deep learning approaches formulate subtype prediction as a conventional flat multi-class task without reflecting the sequential clinical decision process. We developed HCF-Net, a hierarchical cascade fusion network that decomposes subtype prediction into three clinically aligned binary decision nodes and integrates multiphase DCE-MRI with clinicoradiologic information. The model was retrospectively developed and validated using a dual-center cohort of 373 women who underwent preoperative 3.0 T multiphase DCE-MRI. On an independent test set (n = 75), HCF-Net achieved a Macro-AUC of 0.868 (95% CI, 0.806-0.923), accuracy of 73.3%, Macro-F1 of 0.732, and Cohen's κ of 0.631. The fusion model consistently achieved the highest AUC across all three hierarchical decision nodes, reaching 0.890 for luminal versus non-luminal tumors, 0.865 for Luminal A versus Luminal B tumors, and 0.974 for HER2-enriched versus triple-negative tumors. The same ordering of classification strategies was observed with a ConvNeXt-Tiny backbone. Compared with conventional flat classification strategies, hierarchical cascade decomposition and decision-level fusion provided substantial performance gains. These findings suggest that a hierarchical fusion framework aligned with clinical decision pathways may provide an effective and interpretable approach for preoperative breast cancer molecular subtype prediction.
Journal IF-equivalent: 3.9 (OpenAlex 2-year mean citedness, value as of 2026-10-13, retrieved 2026-10-15; not the official Clarivate IF)Reference: Chen Y, Hu L, Hou J, Xie Y, Nie S, Jiang Y, et al. HCF-Net: a Hierarchical Cascade Fusion Network Aligned with Clinical Treatment Pathways for Preoperative Molecular Subtyping of Breast Cancer on Dynamic Contrast-Enhanced MRI. J Digit Imaging Inform med. 2026 Oct 13 [Epub ahead of print]. doi:10.1007/s10278-026-02331-1.Checked: Abstract only - Abstract
Habitat radiomics characterizes texture within tumor subregions but discards the spatial relationships between them. We developed a landscape-ecology-inspired framework quantifying inter-habitat spatial structure on DCE-MRI, evaluated its complementary value alongside within-habitat radiomics, and compared early versus late fusion, using axillary lymph node metastasis (ALNM) prediction as the evaluation task. In this multicenter retrospective study, 284 patients from one center were randomly split into training (n = 198) and validation (n = 86) cohorts, with 120 patients from an independent institution as the external test set. Tumors were partitioned into six habitats by k-means clustering of 19 voxel-wise texture descriptors, with centroids derived exclusively from the training cohort. Three feature domains were constructed: 8 clinical parameters, 642 within-habitat radiomics features, and 94 inter-habitat spatial structure features spanning fragmentation (n = 30), morphology (n = 24), inter-habitat contact (n = 15), inter-habitat distance (n = 15), area ratio (n = 6), and diversity (n = 4). In the external test set, progressive fusion yielded incremental gains in AUC: clinical alone 0.754, plus within-habitat radiomics 0.843, plus inter-habitat spatial structure 0.863 (95% CI 0.792-0.934). The full early fusion model achieved higher AUC than the clinical-only (DeLong P = 0.011) and spatial-structure-only models (P = 0.044); early fusion yielded a numerically higher AUC than late fusion without reaching significance (0.863 vs 0.851, P = 0.636). The two single-domain imaging models were statistically indistinguishable (0.817 vs 0.784, P = 0.512). Inter-habitat spatial structure captures tumor organization overlooked by conventional habitat radiomics and provides complementary information for preoperative ALNM prediction.
Journal IF-equivalent: 3.9 (OpenAlex 2-year mean citedness, value as of 2026-10-13, retrieved 2026-10-15; not the official Clarivate IF)Reference: Liu P, Wang P, Zou X, Zhang Q, Wang W. From Intra- to Inter-habitat Analysis: Spatial Structure Features for Axillary Lymph Node Metastasis Prediction on Breast DCE-MRI. J Digit Imaging Inform med. 2026 Oct 13 [Epub ahead of print]. doi:10.1007/s10278-026-02384-2.Checked: Abstract only
Lung cancer: treatment, trials and AI
- Abstract
BACKGROUND: Pulmonary mucinous adenocarcinoma (PMA) represents a rare lung adenocarcinoma subtype, characterized by a lack of comprehensive pathological classification and prognostic factors. In this study, we propose a multimodal machine learning (ML) framework that integrates multiple data modalities to enhance PMA subtype classification and prognostic prediction. METHODS: This retrospective study enrolled 175 primary PMA cases with details of demographic, histopathological, computed tomography (CT) imaging, and epithelial growth factor receptor ( EGFR ) mutation data. Least absolute shrinkage and selection operator (LASSO) regularized logistic regression model was utilized for histological classification, and Cox proportional hazards model was employed for survival prediction with internal validation. RESULTS: Pure mucinous adenocarcinoma presented a higher prevalence of smaller radiographic or pathological tumor size, lower lobe localization, lower rates of lymph node metastasis and spread through air spaces (STAS), early pathological stage, carcinoembryonic antigen (CEA) ≤5 ng/mL, spiculated margin, Ki-67 low expression and lower frequency of EGFR exon 19 deletion (P=0.002, 0.003, EGFR exon 19 deletion as independent prognostic factors in PMA (P=0.04, 0.049, respectively). Moreover, Kaplan-Meier curves revealed significantly different outcomes between low- and high-risk groups stratified by the nomogram score (P<0.001). CONCLUSIONS: Pulmonary pure mucinous adenocarcinoma exhibited lower malignancy compared to the mixed mucinous and mucin-secreting type. The nomogram model developed and validated in this study exhibited promising efficacy in predicting histological subtype preoperatively and survival in patients with PMA, offering guidance for clinicians in diagnosis and prognosis prediction.
Journal IF-equivalent: 1.4 (OpenAlex 2-year mean citedness, value as of 2026-10-13, retrieved 2026-10-15; not the official Clarivate IF)Reference: Yang W, Chen C, Li L, Chen Z, Chen Z, Le H, et al. Integrating multimodal data for precise subtyping and prognostication in patients with pulmonary mucinous adenocarcinoma. Transl Cancer Res. 2026 Sep;15(9):708-8. doi:10.21037/tcr-2026-1241.Checked: Abstract only - Abstract
BACKGROUND: Brain metastasis remains an important clinical concern in patients with small cell lung cancer (SCLC), even after prophylactic cranial irradiation (PCI). Accurate identification of patients at high risk of brain metastasis after PCI may facilitate individualized surveillance and management. This study developed a fusion model based on two-and-a-half-dimensional (2.5D) multi-channel deep learning features, clinical features, and radiomics features to predict whether patients with SCLC will develop brain metastases following PCI. METHODS: This retrospective study included 185 patients with SCLC who underwent PCI and randomly divided them into a training set (N=148) and a testing set (N=37). A 2.5D multi-channel convolutional neural network (CNN) model was constructed based on multi-planar regions of interest (ROI) derived from CT images to extract 2.5D deep learning features. Based on the largest cross-section and three-dimensional (3D) volume of the tumor ROI, two-dimensional (2D) and 3D deep learning features were extracted, respectively. Subsequently, features from different dimensions were fused with clinical features and traditional omics features to construct the 2D_clinic_Rad, 2.5D_clinic_Rad, and 3D_clinic_Rad models, respectively. The performance differences between the 3D models and the clinical and traditional radiomics models were then compared. RESULTS: The 2.5D_clinic_Rad fusion model demonstrated the best performance in predicting brain metastases, achieving an area under the curve (AUC) of 0.841 on the test set, outperforming clinical models, traditional radiomics models, and 2D and 3D deep learning fusion models. Analysis of decision curves and calibration curves indicated that the 2.5D_clinic_Rad model demonstrated the highest clinical net benefit and the best calibration consistency compared to other models. CONCLUSIONS: The fusion model based on 2.5D_clinic_Rad can effectively predict the risk of brain metastasis in patients with SCLC following whole-brain prophylactic irradiation.
Journal IF-equivalent: 2.5 (OpenAlex 2-year mean citedness, value as of 2026-10-13, retrieved 2026-10-15; not the official Clarivate IF)Reference: Zhang X, Zhao L, Wang J, Zhang X, Liang X, Cao W, et al. Interpretable deep learning and radiomics for predicting the occurrence of brain metastases following prophylactic brain irradiation in small cell lung cancer. Transl Lung Cancer Res. 2026 Sep;15(9):281-1. doi:10.21037/tlcr-2026-0708.Checked: Abstract only
Pancreatic cancer: treatment, trials and AI
No new qualifying paper for this issue.
Prostate cancer: treatment, trials and AI
No new qualifying paper for this issue.
Adenoid cystic carcinoma: treatment, trials and AI
No new qualifying paper for this issue.
Brain tumours: treatment, trials and AI
- Abstract
Glioblastoma (GBM) treatment response is highly heterogeneous. Predicting outcomes from pre-treatment MRI is a critical unmet need, yet the clinical adoption of "black box" deep learning (DL) models is hindered by a lack of transparency. Robust and holistic validation frameworks still need to be developed to allow clinical trust. A multi-layered eXplainable AI (XAI) pipeline was employed to dissect a previously developed deep learning model trained to predict GBM overall survival. First, the model's visual focus was qualitatively and quantitatively analysed. Second, the model's feature dependence was quantified using input ablation studies. Third, the depth at which class information becomes decodable was traced by linear probing of the internal representations. Finally, the clinical impact of the AI and its explanations was assessed in a multi-reader, multi-case study (37 patients, 4 readers, 3 phases, 444 observations) using Generalised Estimating Equations (GEE) and clustered bootstrapping. Analysis revealed a high-intensity heuristic: hyper-intense pixels at the skull periphery anchored "Long-Term" predictions, while the model defaulted to "Short-Term" based on tumour enhancement in its absence. The ablation study established this dependence, and linear probing pointed in the same direction. In the clinical study, AI assistance significantly improved expert accuracy (OR 1.598, p < 0.01) without artificially boosting confidence (p = 0.561). Importantly, the addition of XAI heatmaps was associated with a change in how experts used the AI score (interaction p < 0.01), and with fewer patients wrongly called long-term survivors. High predictive accuracy can mask reliance on low-level intensity heuristics. While superficial interpretation of saliency maps is perilous, multi-layered audits expose these shortcuts. Clinically, spatial heatmaps were associated with improved expert diagnostic accuracy and a shift in decision-making strategy.
Journal IF-equivalent: 3.9 (OpenAlex 2-year mean citedness, value as of 2026-10-13, retrieved 2026-10-15; not the official Clarivate IF)Reference: Andres R, Moreau NN, Dessoude L, Le Henaff L, Missohou F, Stefan D, et al. Explainability and Clinical Trust of Deep Learning in Glioblastoma Treatment Efficacy Prediction: A Comprehensive Framework. J Digit Imaging Inform med. 2026 Oct 13 [Epub ahead of print]. doi:10.1007/s10278-026-02381-5.Checked: Abstract only - Abstract
BACKGROUND: High CD9 expression is significantly associated with shorter overall survival (OS) in patients with adult-type diffuse gliomas (ADGs). Concurrently, drug screening analyses have identified emetine as a potential targeted therapeutic agent for gliomas exhibiting high CD9 expression, indicating that CD9 may serve as a novel biomarker with the potential to transform glioma diagnosis and treatment. This study aimed to develop an artificial intelligence prediction model based on preoperative magnetic resonance imaging (MRI) images to facilitate the early identification of high CD9 expression in patients with ADGs. METHODS: We retrospectively collected CD9 expression data from 262 patients with ADGs in The Cancer Genome Atlas (TCGA) and Chinese Glioma Genome Atlas (CGGA) cohorts. Using preoperative MRI sequences [contrast-enhanced T1-weighted imaging (CET1) and T2-weighted imaging (T2WI)], Habitat features were extracted, using K-means clustering algorithm, together with radiomic features. Additionally, multi-channel 2.5-dimensional deep learning (2.5D_DL) data were constructed, based on neural network architectures, including ResNet101, DenseNet121, and SimpleViT, and DL features were extracted. Seven classifiers were utilized to construct individual Radiomics, Habitat, and 2.5D_DL predictive models. Subsequently, a Stacking model was developed via an ensemble fusion strategy to predict high CD9 expression. Model performance was evaluated using receiver operating characteristic (ROC) curves, and clinical efficacy was assessed by decision curve analysis (DCA). Shapley Additive Explanations (SHAP) analysis was performed to explore the interpretation of the models, enhancing the transparency of the machine learning predictions. In addition, Patients were stratified into high- and low-risk groups based on Stacking model scores, and survival differences were compared using the Kaplan-Meier analysis and the log-rank test. RESULTS: The Habitat model exhibited superior ROC curve [area under the ROC (AUC)] values than the Radiomics model. Among the multi-channel 2.5D_DL models, the SimpleViT model achieved slightly better performance than the convolutional neural network (CNN)-based models (ResnNet101 and DenseNet121). The final Stacking model, which integrated the outputs from Habitat, Radiomics, and 2.5D_DL models exhibited superior AUC values. The AUC reached 0.999, 0.822, and 0.728 in the training, validation, and test sets, respectively. DeLong testing confirmed the statistically significant differences in the AUC values of each model in the training set, but no statistically significant differences were observed among the other sets. In addition, enhanced net clinical benefit across a more extensive range of risk thresholds for this integrated model was verified by DCA. Prognostic stratification by Stacking model revealed significant differences in survival outcomes between high-risk and low-risk groups. CONCLUSIONS: The preoperative MRI-based Stacking model effectively identifies patients with high CD9 expression among ADGs and stratifies patient risk, providing support for clinical therapeutic decision-making and individualized prognostic evaluation. Prospective multicenter data are still required to validate the prognostic performance and generalizability of this model.
Journal IF-equivalent: 1.4 (OpenAlex 2-year mean citedness, value as of 2026-10-13, retrieved 2026-10-15; not the official Clarivate IF)Reference: Pang B, Yuan M, Yan Y, Li J, Xue J, Jing L, et al. MRI-derived habitat radiomics integrated with transformer deep learning for preoperative prediction of high CD9 expression: a novel prognostic marker in adult-type diffuse gliomas. Transl Cancer Res. 2026 Sep;15(9):703-3. doi:10.21037/tcr-2026-1847.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
No new qualifying paper for this issue.
Liver cancer: treatment, trials and AI
- Abstract
BACKGROUND: Hepatocellular carcinoma (HCC) is one of the leading causes of cancer-related mortality worldwide, and TP53 mutation acts as a trunk mutation driving tumor progression. However, TP53 mutation status can currently be determined only by invasive liver biopsy. This study applies multiregional radiomics features from magnetic resonance imaging (MRI) to predict P53-mutated HCC and offers a non-invasive tool for identifying this invasive subtype. METHODS: In this retrospective study, data from 320 patients who underwent preoperative MRI were analyzed and divided into a training cohort (TC; n=224) and a validation cohort (VC; n=96). Clinical risk factors were identified using stepwise regression to construct predictive models. We evaluated three machine learningclassifiers across six MRI sequences, and the least absolute shrinkage and selection operator method was applied to select the best IntraPeri fusion model from four regions (whole tumor, IntraPeri_9mm, IntraPeri_11mm, and IntraPeri_13mm) to establish a radiomics model. The predictive nomogram for P53-mutated HCC integrated these clinical predictors with discriminative radiomics features, and its performance was assessed using receiver operating characteristic analysis, calibration, and decision curves. RESULTS: Among 320 patients (259 men and 61 women; mean age, 58.25±11.51 years), 183 had P53-mutated HCC and 137 had non-P53-mutated HCC. The largest tumor diameter (LTD), Edmondson-Steiner grade, and rim arterial phase hyperenhancement were identified as independent predictors of P53-mutated HCC. The ExtraTrees classifier based on radiomics features from the optimal MRI sequence [T1-weighted imaging-arterial phase (T1WI-AP)] within the IntraPeri_11mm region achieved strong predictive accuracy [area under the curve (AUC) TC =0.805; AUC VC =0.660]. Predictive nomogram integrating clinical and radiomics features demonstrated excellent performance in both the TC [AUC =0.815; 95% confidence interval (CI): 0.758-0.872] and VC (AUC =0.802; 95% CI: 0.713-0.890). Decision curve analysis further confirmed its clinical utility. CONCLUSIONS: Nomogram combining clinical model with IntraPeri_11mm radiomics may serve as effective predictors of preoperative P53 mutation status in HCC.
Journal IF-equivalent: 1.4 (OpenAlex 2-year mean citedness, value as of 2026-10-13, retrieved 2026-10-15; not the official Clarivate IF)Reference: Weng J, Yao D, Zeng Q, He Y, Yang C, Yang B. Magnetic resonance imaging-based radiomics for predicting P53-mutated hepatocellular carcinoma: intratumoral and peritumoral analysis. Transl Cancer Res. 2026 Sep;15(9):709-9. doi:10.21037/tcr-2026-1579.Checked: Abstract only
Kidney cancer: treatment, trials and AI
No new qualifying paper for this issue.
Bladder cancer: treatment, trials and AI
No new qualifying paper for this issue.