AI and Cancer Research ── 2026-10-17
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（1） · Lung（2） · Pancreatic（0） · Prostate（1） · ACC（0） · Brain（2） · Ovarian（0） · Endometrial（0） · Gastric（0） · Liver（2） · Kidney（2） · Bladder（0）
Cancer molecular biology and AI
- Abstract
Introduction: Lung cancer remains a major cause of cancer-related death; prompt detection and monitoring of pulmonary nodules through computed tomography (CT) is critical to prevent mortality. CT interpretation is time-intensive and can be prone to fatigue-related errors. The application of artificial intelligence (AI) may aid in the enhanced detection of pulmonary nodules when used in conjunction with radiologists. Thus, possibly decreasing interpretation time and enhancing diagnostic reliability. However, studies have reported uncertainty regarding the extent to which true positives are always diagnosed, as studies have indicated an increase in false positive rates with AI-assisted pulmonary nodule detection. This systematic review and meta-analysis focuses on the impact of AI assistance on sensitivity and false positive rates in comparison to unaided reading. Methodology: Adhering to the PRISMA guidelines, an intensive literature search was carried out on Cochrane, PubMed, Medline and Embase. Research composed of studies that compared AI-assisted reading to unaided radiologists in the context of nodule detection, which also provided additional outcomes that were utilised in the secondary outcome analysis. ROBINS-1 tool was used to assess risk of bias and data quality. Risk ratios and risk differences with 95% CI were reported for dichotomous outcomes, whereas mean differences with 95% CI were utilised for continuous outcomes. Sensitivity analyses were performed for the imputation of missing standard deviations.
Results: Seven studies reported mean sensitivity in either second reader (SR) mode or concurrent reader (CR) mode. Five of the included studies implemented second reader designs; AI-assisted sensitivity ranged from 38% to 85.66%, whereas unassisted reading sensitivity ranged from 20.9% to 73.46%. Additionally, three studies reported concurrent reading, with AI-assisted reading ranging from 80% to 84%, while unassisted reading varied from 64% to 72%. According to our research, AI-assisted reading had a significantly higher sensitivity (RR of 1.39; CI 95% 1.08–1.79; p = 0.01; I2 = 95%). Five studies reported false positives per scan. Four reported a numerical increase with AI assistance, but incomplete variance reporting and study heterogeneity precluded quantitative pooling. Reading time was increased under AI assistance as a second reader (MD 77.54; CI 95% −57.50 to 212.6, p = 0.132; I2 = 64.9%) but did not yield significance. Additionally, AI-assisted reading under concurrent reading did not yield statistical significance for reading time (MD –11.39; 95% CI −498.7 to 476.0, p = 0.816; I2 = 41.3%).
Conclusions: AI-assisted reading significantly improves sensitivity for pulmonary nodule detection compared to unaided reading, but the trade-offs with false positives and workflow disruption remain uncertain. Substantial heterogeneity and the limited number of studies preclude definitive clinical recommendations. These findings should be considered exploratory, and the implementation of AI in lung cancer screening requires prospective validation.
Journal IF-equivalent: 4.3 (OpenAlex 2-year mean citedness, value as of 2026-10-15, retrieved 2026-10-16; not the official Clarivate IF)Reference: Singh V, Gunda S, Shah A, Mathew J, Ravendran K. Impact of Artificial Intelligence Assistance on Radiologist Performance in CT-Based Pulmonary Nodule Detection: A Systematic Review and Meta-Analysis of Detection Accuracy Studies. J Imaging. 2026 Oct 14;12(10):509. doi:10.3390/jimaging12100509.Checked: Abstract only - Abstract
Background: Brain imaging is central to the structural, functional, metabolic, and neurophysiological characterization of neurological disease, yet interpretation remains constrained by heterogeneity in acquisition, annotation, expertise, and clinical context.
Objective: This systematic literature review evaluates recent artificial intelligence approaches for brain imaging and computer-aided diagnosis, with emphasis on methods, modalities, neurological diseases, diagnostic tasks, datasets, validation practices, and translational limitations.
Methods: The review followed PRISMA 2020 and covered peer-reviewed English-language studies published from January 2020 through June 2026. Eight information sources were searched using database-specific terms for artificial intelligence, neuroimaging, neurological disease, and diagnostic analysis. The search identified 1,078 records; 236 duplicates were removed, 842 unique records were screened, 258 full texts were assessed, and 123 studies were included after a record-level eligibility re-audit. Heterogeneous evidence was synthesized narratively and by descriptive mapping rather than meta-analysis.
Results: MRI was frequently represented in the included studies and auxiliary mapping data; CT was commonly used in acute stroke and intracranial hemorrhage; PET supported selected molecular and differential-diagnosis studies; fMRI and diffusion imaging were used for network and white-matter analysis; and EEG extended the scope to neurophysiological diagnosis. CNN and three-dimensional networks were commonly reported, while attention, Transformer, graph, self-supervised, generative, multimodal, and foundation-model approaches appeared in selected recent studies. Stroke, dementia, and brain tumors were frequently represented, but heterogeneous populations, outcomes, and incomplete validation extraction precluded ranking diseases, modalities, architectures, or validation strategies.
Conclusion: The evidence suggests movement from task-specific pattern recognition toward multimodal and context-rich decision support in selected settings, but it does not establish uniform methodological superiority or clinical maturity. Dependable translation requires patient-level data governance, transparent reporting, uncertainty estimation, independent multicenter testing, prospective workflow evaluation, and clinically meaningful endpoints.
Journal IF-equivalent: 3.6 (OpenAlex 2-year mean citedness, value as of 2026-10-15, retrieved 2026-10-16; not the official Clarivate IF)Reference: Omarov B. Advances in artificial intelligence for brain imaging and computer-aided diagnosis of neurological diseases: a systematic literature review. Front Hum Neurosci. 2026 Oct 14;20:1963855. doi:10.3389/fnhum.2026.1963855.Checked: Abstract only
See all 2 Cancer biology papers →
Breast cancer: treatment, trials and AI
- Abstract
Objectives: C-X-C motif chemokine ligand 9 (CXCL9) is a critical mediator of tumor-infiltrating lymphocyte recruitment and a potential biomarker in breast cancer (BC). This study aimed to develop a machine learning-based handcrafted pathomics model to forecast survival outcomes by characterizing CXCL9-related morphological signatures from routine hematoxylin and eosin (H&E) slides. The biological relevance and clinical utility of the derived pathomics score (PS) were subsequently evaluated to provide an objective framework for risk stratification. Material and Methods: We developed a pathomics model integrating quantitative H&E image features with machine learning in 791 Cancer Genome Atlas-BC patients. Feature selection using minimum redundancy maximum relevance and recursive feature elimination was performed exclusively within the training set, and a gradient boosting machine model was constructed to output a PS representing the predicted probability of CXCL9 expression. Model performance was assessed in the training, testing, and external validation cohorts. Associations of PS with survival, immune infiltration, cancer-immunity cycle (CI cycle) activity, tumor mutational burden, and molecular subtypes were investigated through integrated bioinformatics.
Results: CXCL9 expression was confirmed as a significant prognostic factor for overall survival ( P = 0.037). The pathomics model demonstrated stable performance for predicting CXCL9 status in training, testing, and external cohorts (area under the curves: 0.741, 0.729, and 0.704, respectively). The PS significantly correlated with CXCL9 expression, stratified patients into distinct prognostic groups ( P = 0.012), and remained a significant protective factor in multivariate analysis (hazard ratio = 0.66, P = 0.048). Mechanistically, high PS was associated with immune-inflamed features, characterized by increased natural killer cells and CD8+ T-cell infiltration, enhanced CI cycle activity, and elevated TMB. Furthermore, the PS effectively reflected clinical heterogeneity, with triple-negative BC exhibiting the highest scores compared to other molecular subtypes ( P <0.001).
Conclusion: This pathomics framework provides an imaging-derived indicator of CXCL9 expression and may support prognostic stratification in BC. Its association with immune-inflamed characteristics suggests potential relevance for immune phenotype assessment, but its value for predicting immunotherapy response requires validation in immunotherapy-treated cohorts.
Journal IF-equivalent: 2.2 (OpenAlex 2-year mean citedness, value as of 2026-10-15, retrieved 2026-10-16; not the official Clarivate IF)Reference: Huang W, Zhan M, Yu J, Ren L, Du J, Hou Y, et al. Machine learning-based pathomics signature as a novel digital marker for C-X-C motif chemokine ligand 9 expression and prognostic assessment in breast cancer. Cytojournal. 2026 Oct 13;23:63. doi:10.25259/cytojournal_67_2026.Checked: Abstract only
Lung cancer: treatment, trials and AI
- Abstract
Background: Chronic inflammation and metabolic dysregulation are increasingly recognized as interconnected drivers of tumorigenesis and immune evasion, yet their combined prognostic and mechanistic relevance in lung adenocarcinoma (LUAD) remains poorly defined.
Methods: A curated 117-gene set representing systemic inflammation-metabolism dysregulation was obtained from MSigDB. Core prognostic genes were identified through differential expression analysis and univariate Cox regression. Using TCGA-LUAD as the training cohort and six independent GEO cohorts for external validation, 101 machine learning algorithm combinations were systematically evaluated to construct a robust prognostic model. Model performance was assessed by C-index, time-dependent ROC, and PCA. Immune characteristics were analyzed using TCIA, ESTIMATE, and TIMER-based deconvolution. ATP2A2, identified as the gene most strongly correlated with risk score, underwent multi-cohort transcriptomic and immunohistochemical validation, in vitro functional characterization, and mechanistic investigation via IOBR-integrated immune profiling. Single-cell RNA sequencing and multiplex immunofluorescence provided cellular-resolution verification of microenvironmental associations.
Results: The RSF + SuperPC model achieved optimal performance and effectively stratified patients into high- and low-risk groups with significantly divergent survival across all seven cohorts. High-risk tumors showed reduced immune/stromal infiltration and elevated tumor purity. ATP2A2 was consistently overexpressed in tumor tissue, correlated with poor differentiation, advanced stage, and shorter survival, and predicted immunotherapy resistance. Mechanistically, high ATP2A2 expression was associated with suppressed immune cell infiltration, attenuated chemokine signaling, impaired cancer-immunity cycle activity, and an “immune-desert” phenotype confirmed by single-cell and spatial analyses.
Conclusion: This study establishes a validated inflammation-metabolism-based prognostic signature in LUAD and identifies ATP2A2 as a key driver linking tumor aggressiveness to immunosuppressive microenvironment remodeling, positioning it as a promising prognostic biomarker and potential therapeutic target for overcoming immunotherapy resistance.
Journal IF-equivalent: 4.8 (OpenAlex 2-year mean citedness, value as of 2026-10-15, retrieved 2026-10-16; not the official Clarivate IF)Reference: Hu X, Zhang G, Zhang Y, Zhao Y, Zhou F, Li G. An AI-derived inflammation-metabolism ecosystem signature reveals ATP2A2 as a microenvironment-remodeling driver of immune evasion in lung adenocarcinoma. Front Cell Dev Biol. 2026 Oct 14;14:1971779. doi:10.3389/fcell.2026.1971779.Checked: Abstract only - Abstract
BACKGROUND: Distinct treatment strategies for small-cell lung cancer (SCLC) and non-small-cell lung cancer (NSCLC) brain metastases require accurate noninvasive subtyping. PURPOSE: To develop and externally validate a biparametric MRI-based 2.5D multi-instance learning (MIL) deep learning (DL) model for discriminating SCLC from NSCLC brain metastases, with performance compared against clinical, radiomics, and 3D-DL models. STUDY TYPE: Retrospective. POPULATION: This study included 366 patients from four institutions. Center 1 provided the training set (n = 199; mean age, 63.88 ± 10.79 years; 72.36% male) and an internal tuning set (n = 85; mean age, 64.73 ± 9.53 years; 67.06% male). Centers 2-4 were pooled into a single external test set (n = 82; mean age, 62.26 ± 10.60 years; 63.41% male). FIELD STRENGTH/SEQUENCE: 1.5 T and 3.0 T; contrast-enhanced T1-weighted imaging and fluid-attenuated inversion-recovery imaging. ASSESSMENT: The 2.5D-MIL model was benchmarked against clinical, radiomics, and 3D-DL models and evaluated on internal tuning and pooled external test sets. STATISTICAL TESTS: Shapiro-Wilk, Student's t-test, Mann-Whitney U, chi-square, univariable and multivariable logistic regression, and DeLong tests were used. Performance measures included the area under the receiver operating characteristic curve (AUC) with 95% confidence intervals and classification and calibration metrics. Statistical significance was defined as two-sided p < 0.05. RESULTS: In the internal tuning set, AUCs were 0.842 (2.5D-MIL), 0.740 (clinical), 0.710 (radiomics), and 0.747 (3D-DL). In the external test set, AUCs were 0.826 (2.5D-MIL), 0.826 (clinical), 0.696 (radiomics), and 0.664 (3D-DL). Differences between 2.5D-MIL and the clinical (p = 1.000), radiomics (p = 0.139), and 3D-DL (p = 0.119) models were not significant. DATA CONCLUSION: The MRI-based 2.5D-MIL model showed potential for noninvasive differentiation of SCLC from NSCLC brain metastases. Larger prospective studies are needed before clinical use. EVIDENCE LEVEL: 3. TECHNICAL EFFICACY: Stage 2.
Journal IF-equivalent: 2.4 (OpenAlex 2-year mean citedness, value as of 2026-10-15, retrieved 2026-10-16; not the official Clarivate IF)Reference: Zhu J, Liu C, Zou L, Xu R, Xie X, Tian Y, et al. MRI‐Based 2.5D Multi‐Instance Deep Learning for Differentiating Pathological Subtypes of Brain Metastases From Lung Cancer. Magnetic Resonance Imaging. 2026 Oct 13 [Epub ahead of print]. doi:10.1002/jmri.70588.Checked: Abstract only
Pancreatic cancer: treatment, trials and AI
No new qualifying paper for this issue.
Prostate cancer: treatment, trials and AI
- Abstract
Background: Treatment intensification with androgen deprivation therapy (ADT) combined with docetaxel, an androgen receptor pathway inhibitor, or selected triplet regimens is recommended for eligible patients with metastatic castration-sensitive prostate cancer (mCSPC). Despite increasing adoption, implementation remains variable in routine clinical practice.
Objective: To characterize temporal trends in first-line systemic treatment for mCSPC and identify factors associated with receipt of guideline-concordant treatment intensification using exploratory explainable machine learning.
Methods: National treatment patterns were evaluated using the Pfizer Oncology Quality Care Insight Tool derived from IQVIA Anonymized Patient Longitudinal Data, and institutional patterns were evaluated within Avera Health. The exploratory cohort included 42 patients with documented mCSPC treated between 2018 and 2023. Guideline-concordant treatment intensification was defined as ADT combined with docetaxel or a novel hormonal therapy within 90 days of ADT initiation. Potential outcome-derived variables were excluded before modeling. Six predictive approaches were evaluated using repeated nested stratified cross-validation, with 5-fold outer cross-validation repeated 20 times and 5-fold inner cross-validation repeated three times. Recursive feature elimination was performed within outer training folds, and class imbalance was addressed using SMOTE within resampling.
Results: Thirty-two (32) of forty-two (42) patients (76.2%) received guideline-concordant treatment intensification. Treatment-pattern analysis showed increasing use of first-line novel hormonal therapy and declining ADT monotherapy over time. Under repeated nested validation, discrimination was modest and variable across models. The Decision Tree achieved the highest patient-level AUC (0.675; 95% CI, 0.421–0.929), whereas Random Forest achieved an AUC of 0.650 (95% CI, 0.383–0.917), accuracy of 85.7%, precision of 88.2%, recall of 93.8%, and F1 score of 0.909. Feature-selection stability identified insurance coverage for novel hormonal therapy as the most consistently selected predictor, followed by positive core proportion and smoking history. These three variables were retained in the final explanatory Random Forest model, and global SHAP and Random Forest importance analysis showed broadly concordant rankings.
Conclusions: Treatment intensification for mCSPC increased substantially in routine practice. Repeated nested validation produced more conservative and variable performance estimates than the original single-split analysis, underscoring the exploratory nature of this small cohort. Healthcare access and selected clinical factors warrant further evaluation in larger, multicenter datasets.
Journal IF-equivalent: 2.7 (OpenAlex 2-year mean citedness, value as of 2026-10-02, retrieved 2026-10-03; not the official Clarivate IF)Reference: Barton Odro E, Bychinski J, Van Alstyne T, Corsini C, Owen P, Jones CP, et al. Predictors of guideline-concordant treatment intensification in metastatic castration-sensitive prostate cancer: an explainable machine learning study. Front Oncol. 2026 Oct 13;16:1835503. doi:10.3389/fonc.2026.1835503.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: The objective of this study was to develop and externally validate complementary magnetic resonance imaging (MRI)-based models and their stacked combinations for preoperative World Health Organization (WHO) grading of intracranial meningioma. METHODS: This retrospective multicenter study included 455 histopathologically confirmed meningiomas: a four-center development cohort (n = 346) with leave-one-center-out cross-validation and an external cohort (n = 109). Four base models used contrast-enhanced T1-weighted MRI: tumor + peritumoral radiomics, an nnU-Net segmentation-based classifier, frozen DINOv3 transfer-learning features, and clinical variables. All 15 combinations were prespecified and stacked using a linear meta-learner trained on development out-of-fold predictions. Frozen models were externally evaluated without modification. RESULTS: WHO 2-3 tumors comprised 24.6% overall (112/455; development 20.5%; external 37.6%). External AUCs were 0.732 for nnU-Net, 0.703 for DINOv3, 0.645 for clinical, 0.628 for radiomics. The multimodal ensemble (nnU-Net+DINOv3+Clinical) achieved the highest external AUC (0.742), exceeding radiomics (ΔAUC +0.114, p = 0.008) but not nnU-Net (ΔAUC +0.011, p = 0.737). Compared with the clinical model, discrimination was higher but nonsignificant at the prespecified threshold (ΔAUC +0.098, p = 0.050), while reclassification improved (IDI +0.109, p < 0.001). Radiomics-containing combinations performed strongly in development but lost most discrimination externally. The multimodal ensemble had an external calibration slope of 1.32 (Brier 0.190) and net benefit above default strategies at thresholds ≥ 0.23. CONCLUSION: The multimodal ensemble achieved the highest external AUC but did not significantly exceed nnU-Net, which was the most transportable single predictor of meningioma grade. Clinical variables did not improve discrimination but enabled interpretable feature-level attribution. Handcrafted radiomics lacked external transportability.
Journal IF-equivalent: 3.2 (OpenAlex 2-year mean citedness, value as of 2026-10-15, retrieved 2026-10-16; not the official Clarivate IF)Reference: Huryol C, Sulaimanov U, Yuce M, Sanlier N, Ozturk F, Ozturk O, et al. MRI-based preoperative WHO grade prediction in meningioma: development and comparison of deep learning, radiomics, clinical, and combined models in multicenter data. J Neurooncol. 2026 Oct 14;180(1):18. doi:10.1007/s11060-026-05827-6.Checked: Abstract only - Abstract
Purpose: To systematically review the integration of generative artificial intelligence (GenAI) in MRI-based brain tumor management and evaluate its impact on detection, segmentation, diagnosis, treatment planning, and outcome prediction. The review addresses the research question like How effectively can GenAI enhance MRI-based brain tumor management, and what challenges limit its clinical translation.
Methods: A systematic literature review was conducted following PRISMA guidelines across PubMed, IEEE Xplore, ScienceDirect, SpringerLink, and Web of Science. Studies published between 2015 and 2025 that applied generative models—including Generative Adversarial Networks (GANs), Variational Autoencoders (VAEs), diffusion models, and transformer-based methods to brain tumor MRI analysis were included. Data were extracted from 55 peer-reviewed studies for qualitative synthesis.
Results: Hybrid architectures combining GANs with CNNs or transformers achieved classification accuracies up to 99.53%. Attention-based segmentation models on multi-modal MRI data attained Dice scores exceeding 0.89. GenAI demonstrated significant contributions to tumor detection, cross-modal synthesis, data augmentation, treatment personalization, and survival prediction. Key challenges included data scarcity, model explainability, algorithmic bias, and the need for prospective clinical validation.
Conclusions: GenAI offers transformative potential for neuro-oncological care by addressing data limitations and enabling personalized treatment strategies. However, resolving ethical concerns, ensuring regulatory compliance, and advancing multi-modal integration remain essential for successful clinical translation
Journal IF: unknown (could not be matched)Reference: [No authors listed]. Advancing Brain Tumor Management Using Generative AI: A Comprehensive Review of MRI-Based Applications. Zenodo (CERN European Organization for Nuclear Research). [Epub ahead of print]. doi:10.5281/zenodo.23337543.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 and purpose Transcatheter arterial chemoembolization (TACE) is the primary treatment for intermediate-stage hepatocellular carcinoma (HCC). However, significant heterogeneity in patient response to TACE necessitates non-invasive and precise methods for evaluating treatment efficacy. This study aims to explore the predictive ability of combined intratumoral habitat imaging and peritumoral radiomics features for TACE response. Materials and methods We retrospectively enrolled HCC patients who underwent TACE treatment at four centers between January 2015 and December 2023. All patients underwent contrast-enhanced MRI. Patients from centers A and B formed the training cohort, while those from centers C and D comprised external validation cohorts. Using three-phase enhanced MRI (arterial, portal venous, and delayed phase), K-Means clustering divided intratumoral regions into three habitat subregions (Habitat 1, 2, and 3), and peritumoral features were extracted. Clinical variables were also collected. Key radiomics features were selected by LASSO regression, and clinical indicators were identified through univariable and multivariable logistic regression. The XGBoost algorithm constructed intratumoral, peritumoral, clinical, and combined models. Performance was evaluated using ROC curves, calibration curves, decision curve analysis (DCA), and DeLong tests.
Results: A total of 174 HCC patients who underwent initial TACE treatment were enrolled, including 104 in training and 70 in validation cohorts. Fifteen key intratumoral features from the habitat subregions and 24 radiomics features from the peritumoral region were identified, primarily derived from wavelet transforms and texture analysis. The wavelet-LLL_glszm_ZoneVariance_ PVP feature from Cluster 2 contributed significantly to the model and had a positive impact (highest SHAP value). Alpha-fetoprotein (AFP) (P = 0.015) and Tumor size (P = 0.016) remained significantly associated with TACE treatment response in multivariable analysis. The combined model based on clinical, intratumoral habitat and peritumoral radiomics showed superior predictive performance, with AUCs of 0.950 (95% CI: 0.89-1.00), 0.850 (0.79-0.91) and 0.830 (0.77-0.89) in training and validation cohorts, outperforming single models (Clinic: AUC = 0.700, Tumor_Habitat: AUC = 0.880, Peritumor_Radiomics: AUC = 0.870, P<0.05). Calibration and DCA demonstrated good agreement between predicted and observed outcomes and favorable net benefit across the evaluated threshold probabilities.
Conclusion: The combined model integrating AFP, Tumor size, intratumoral habitat imaging, and peritumoral radiomics could accurately predict initial TACE response in HCC patients. Cluster 2-derived features showed relatively greater contributions among the intratumoral habitat subregions. This non-invasive prediction tool may provide complementary information for pretreatment risk stratification. Future prospective multicenter studies are needed to verify the clinical applicability of the model.
Journal IF-equivalent: 2.7 (OpenAlex 2-year mean citedness, value as of 2026-10-02, retrieved 2026-10-03; not the official Clarivate IF)Reference: Wang Z, Yin N, Su R, Zhou M, Sun Z, Li J, et al. Intratumoral habitat combined with peritumoral radiomics to improve the predictive performance of initial TACE efficacy: a multicenter retrospective study. Front Oncol. 2026 Oct 14;16:1772206. doi:10.3389/fonc.2026.1772206.Checked: Abstract only - Abstract
Background: This study developed and validated an machine-learning-based radiomics model integrating tumor habitat radiomics, peritumoral radiomics, and clinical features to predict progression-free survival (PFS) following repeat transarterial chemoembolization (TACE) in patients with hepatocellular carcinoma (HCC).
Methods: This retrospective multicenter study included 270 patients with HCC. Patients from Center 1 were assigned to training (n = 94) and internal validation (n = 41) cohorts, while Centers 2 (n = 82) and 3 (n = 53) served as external validation cohorts. Tumor habitats and 5-mm peritumoral regions were generated from contrast-enhanced CT images. Radiomics features were selected using univariate Cox and LASSO-Cox regression. A fusion model and HPC risk score were constructed by integrating selected radiomics signatures and clinical variables. Performance was assessed using time-dependent ROC, C-index, calibration, decision curve analysis, and Kaplan–Meier analyses.
Results: The optimal habitat cluster number was K = 2. Eleven habitat features, three peritumoral features, and alpha-fetoprotein were retained in the fusion model. The model achieved AUCs of 0.923, 0.921, and 0.897 for 3-, 6-, and 9-month progression-free survival in the training cohort, and 0.932, 0.863, and 0.916 in the internal validation cohort, respectively; all external AUCs exceeded 0.82. The fusion model showed higher C-index values than the clinical model across cohorts. High-risk patients had significantly shorter PFS than low-risk patients (all P < 0.001). Calibration and decision curve analyses demonstrated good agreement and clinical utility.
Conclusion: The CT-based fusion model and HPC risk score effectively predicted progression risk in HCC.
Journal IF-equivalent: 5.2 (OpenAlex 2-year mean citedness, value as of 2026-10-15, retrieved 2026-10-16; not the official Clarivate IF)Reference: Wang F, Hu Y, Shi ZX, He XY, Sui YH, Wen FK, et al. CT habitat and peritumoral radiomics for predicting progression after repeat TACE in hepatocellular carcinoma: a multicenter study. Front Pharmacol. 2026 Oct 14;17:1942002. doi:10.3389/fphar.2026.1942002.Checked: Abstract only
Kidney cancer: treatment, trials and AI
- Abstract
Objective: To develop and validate an interpretable machine learning (ML) model that integrates extracellular volume fraction (ECV) derived from contrast-enhanced CT with clinical and imaging features for preoperative prediction of World Health Organization/International Society of Urological Pathology (WHO/ISUP) grade in clear cell renal cell carcinoma (ccRCC). Materials and methods A retrospective cohort of 263 patients with pathologically confirmed ccRCC from two institutions was analyzed. Patients from Hospital A (n=184) were randomly divided into training (n=128) and internal validation (n=56) cohorts, while patients from Hospital B (n=79) served as an independent external validation cohort. CT-derived ECV, arterial enhancement fraction (AEF), and conventional imaging features were extracted. Six machine learning models (Logistic Regression [LR], eXtreme Gradient Boosting [XGBoost], Gaussian Naive Bayes [GNB], Support Vector Machine [SVM], K-Nearest Neighbors [KNN], Light Gradient Boosting Machine [LightGBM]) were constructed, and the best-performing model was identified based on bootstrap resampling. Model interpretability was assessed using SHapley Additive exPlanations (SHAP).
Results: Tumor size (low-grade: 4.99 ± 1.98 cm; high-grade: 6.20 ± 2.72 cm, P = 0.002), ECV (low-grade: 0.46 ± 0.09; high-grade: 0.57 ± 0.12, P<0.001), and AEF (low-grade: 1.37 ± 0.24; high-grade: 1.56 ± 0.25, P<0.001) were significantly higher in high-grade ccRCC, while hematocrit (HCT, low-grade: 0.41 ± 0.05; high-grade: 0.38 ± 0.06, P<0.001) was lower. The optimal LR model achieved robust performance: training cohort AUC = 0.995 (95% CI: 0.990–0.999), internal validation AUC = 0.903 (95% CI: 0.818–0.988), external test AUC = 0.857 (95% CI: 0.756–0.958). SHAP analysis showed ECV, tumor diameter, and AEF were the top 3 predictors.
Conclusion: An interpretable ML model incorporating CT-derived ECV and imaging features effectively predicts preoperative WHO/ISUP grade of ccRCC, providing a noninvasive tool for individualized risk stratification and clinical decision-making.
Journal IF-equivalent: 2.7 (OpenAlex 2-year mean citedness, value as of 2026-10-02, retrieved 2026-10-03; not the official Clarivate IF)Reference: Wang Y, Wang Y, Bai G, Huang W, Huang M, Chen W. Interpretable machine learning for preoperative prediction of WHO/ISUP grade in clear cell renal cell carcinoma using contrast-enhanced CT–derived extracellular volume fraction. Front Oncol. 2026 Oct 13;16:1851636. doi:10.3389/fonc.2026.1851636.Checked: Abstract only - Abstract
In the healthcare industry, Renal Cell carcinoma (RCC) is the most common form of kidney cancer, and it is heterogeneous with intrinsic histopathological features. Moreover, grading RCC from the histopathology slides is essential for prognosis and determination of treatment strategy, but manual grading is labor intensive, time consuming and requires addressing inherent observer variability. Recently, Deep Learning (DL) approaches have shown significant advantages in medical image analysis, However, applying DL approaches to RCC grading still faces several challenge, which include small, annotated datasets and algorithms that can adequately represent intricate histopathological features. Besides, the proposed study provides datasets of digitalized histopathology scans of RCC slides, which are annotated by expert pathologists that are sufficient for training and testing models. Therefore, the proposed Dual Attention-Gated Dilated MobileNetV2 (DAG-DMobileNetV2) is employed for automated RCC grading. The model addresses these challenges by using dilated convolutions to increase the receptive field and generate a larger context without a reduction in resolution, hence allowing the model to extract both fine-grained and global features effectively. In addition, the dual attention mechanism, composed of channel and spatial attention mechanisms that enables the model to dynamically emphasize important areas and feature channels while suppressing irrelevant noise and concentrating on diagnostically important regions. Thus, the MobileNet backbone enables the model to operate efficiently, allowing for its suitability for deployment in real-time clinical settings. Hence, the contributions of the proposed model are the distinct attention modules coupled with dilated convolutions, allowing for accurate discrimination of the 4 different grades of RCC. Thus, the proposed DAG-DMobileNetV2 achieves improved classification performance, improved feature representation, and decreased computational complexity resulting in faster inference. Moreover, the attention mechanisms for DAG-DMobileNetV2 should automatically accommodate and adapt to variability in histopathological image quality.
Journal IF-equivalent: 2.4 (OpenAlex 2-year mean citedness, value as of 2026-10-15, retrieved 2026-10-16; not the official Clarivate IF)Reference: Harinath Y, Sureshbabu A. Automated grading of renal cell carcinoma using an efficient deep learning approach on histopathology images. Discov Computing. 2026 Oct 13;29(1):748. doi:10.1007/s10791-026-10616-w.Checked: Abstract only
Bladder cancer: treatment, trials and AI
No new qualifying paper for this issue.