AI and Cancer Research ── 2026-11-01
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.
All cancers: Cancer biology（1）
Hematologic malignancies: AML（0） · CML（0） · ALL（0） · CLL（0） · Lymphoma（0） · Myeloma（0）
Solid tumors: Breast（2） · Lung（2） · Pancreatic（0） · Prostate（0） · Brain（2） · Ovarian（1） · Endometrial（1） · Gastric（0） · Liver（0） · Kidney（2） · Bladder（1）
Rare cancers: ACC（0）
Cancer molecular biology and AI
- Abstract
BACKGROUND: The aim of this research is to develop and evaluate a novel feature selection method based on a local search algorithm (LSFS) in combination with a genetic algorithm (GA) for cancer classification using high-dimensional gene expression data. METHODS: The study spanned a period between 2022 and 2024, using data from two medical research centers (Sofia, Bulgaria, and Moscow, Russia). More than 30,000 patient records were analyzed using six open datasets as source data. These datasets included information on blood, breast, colon, and other types of cancer from the GEO and TCGA databases. To prepare the data for analysis, the study employed techniques such as normalization, outlier elimination, and logarithmic transformation. Modern machine learning algorithms, such as random forests, support vector machines, and neural networks, were utilized to assess the effectiveness of the proposed method. RESULTS: The LSFS + GA method demonstrated the ability to maximize accuracy, sensitivity, and specificity, as well as other classification metrics. Specifically, classification accuracy improved by 8-15% depending on the dataset, sensitivity by 10-20%, and specificity by 5-10%. Additionally, there was a 12-18% reduction in noise in the data. The effectiveness of the model was demonstrated by a reduction in entropy, indicating an increase in classification confidence of 6-9%. Statistical analysis, including cross-validation and ANOVA, confirmed the statistical significance of the improvements achieved with the new method (p < 0.05). CONCLUSIONS: The developed algorithm enables a substantial reduction in computational complexity while maintaining, or even improving, classification accuracy. This is important for analyzing cancer data, as it helps to ensure more reliable results. The study's findings demonstrate the potential of combining local search methods with genetic algorithms to address high-dimensional classification problems in bioinformatics.
Journal IF-equivalent: 5.3 (OpenAlex 2-year mean citedness, value as of 2026-10-02, retrieved 2026-10-03; not the official Clarivate IF)Reference: Gu S, Savina T, Monov D, Gorozhanina E. New heuristic method for cancer classification using gene expression data. Cancer Imaging. 2026 Aug 19;26(1):151. doi:10.1186/s40644-026-01111-y. PMID: 42963784.Checked: Abstract only
See all 1 Cancer biology papers →
Hematologic malignancies
Acute myeloid leukemia (AML): treatment, trials and AI
No new qualifying paper for this issue.
Chronic myeloid leukemia (CML): treatment, trials and AI
No new qualifying paper for this issue.
Acute lymphoblastic leukemia (ALL): treatment, trials and AI
No new qualifying paper for this issue.
Chronic lymphocytic leukemia (CLL): treatment, trials and AI
No new qualifying paper for this issue.
Lymphoma: treatment, trials and AI
No new qualifying paper for this issue.
Multiple myeloma: treatment, trials and AI
No new qualifying paper for this issue.
Solid tumors
Breast cancer: treatment, trials and AI
- Abstract
Background: Breast cancer remains a leading cause of cancer-related mortality worldwide, with pronounced regional inequalities in middle-income countries such as Brazil. In Mato Grosso, structural disparities and limited access to specialized care pose additional challenges for accurate prognostic assessment. This study aimed to develop and internally validate Machine Learning (ML) models and prognostic nomograms to predict overall survival (OS) and breast cancer-specific survival (CSS), as well as to stratify patient risk in Mato Grosso, Brazil.
Methods: A retrospective population-based cohort study was performed using data from the Population-Based Cancer Registry (RCBP) (2001-2018), deterministically linked to the Mortality Information System (SIM) (2001-2022). Five survival prediction models were developed and internally validated, including four ML survival models, Random Survival Forest (RSF), Gradient Boosting Survival Analysis (GBS), Survival Support Vector Machine (SSVM), and ComponentWise Gradient Boosting (CWGB), and the conventional Cox proportional hazards (CPH) model. The dataset was split into training and test sets (80:20, stratified). Model performance was assessed using the concordance index (C-index), time-dependent area under the curve (AUCt), and integrated Brier score (IBS), with bootstrap confidence intervals. The highest-performing model was interpreted using SHAP values and permutation-based feature importance. Cox-based nomograms were then constructed and internally validated using 1,000 bootstrap resamples, followed by risk stratification and decision curve analysis to evaluate clinical utility.
Results: GBS demonstrated the highest overall performance for both OS and breast CSS, with strong discrimination and good calibration. For OS, the C-index reached 0.781 (95% CI 0.776-0.786), with an AUCt of 0.843 and an IBS of 0.129; for CSS, the C-index reached 0.790 (0.784-0.796), with an AUCt of 0.852 and an IBS of 0.120. CPH showed comparable discrimination but weaker calibration overall. The nomograms maintained stable discrimination at 1-, 3-, 5-, and 10-year time points and demonstrated good agreement between predicted and observed outcomes. Both ML models and Cox-derived nomograms achieved significant risk stratification (log-rank P< 0.001). SHAP analyses identified diagnostic method, tumor morphology, marital status, education level, and age as key predictors.
Conclusions: In this study, ML models, particularly GBS, and Cox-based nomograms demonstrated individualized prognostic capability for OS and breast CSS. These approaches may support effective risk stratification, facilitating the identification of patients at higher mortality risk and providing a scalable framework for risk-adapted management in real-world public health settings.
Journal IF-equivalent: 6.6 (OpenAlex 2-year mean citedness, value as of 2026-10-04, retrieved 2026-10-05; not the official Clarivate IF)Reference: Xavier SP, Victor A, Gotine AREM, das Neves MAB, Cardoso LB, de Albuquerque Maia FH, et al. Predicting overall and breast cancer-specific survival: machine learning models and prognostic nomograms from a population-based registry. BMC Med Inform Decis Mak. 2026 Oct 30 [Epub ahead of print]. doi:10.1186/s12911-026-03931-1.Checked: Abstract only - Abstract
Objective: Accurate and robust survival prediction is essential for personalised breast cancer prognosis and treatment decision-making. However, existing machine learning–based survival models often lack stability under cohort heterogeneity and distribution shift, while tabular foundation models typically do not support censored time-to-event data. This study aims to develop a foundation-model-based survival framework that explicitly handles right censoring and enables stable deployment across heterogeneous cohorts without task-specific retraining.
Methods: We propose TabSurv, a foundation-model-based framework for survival analysis that adapts pretrained tabular foundation models to censored time-to-event prediction. Built on TabPFN, TabSurv operates via in-context learning without gradient-based training or hyperparameter tuning. To address censoring, TabSurv introduces a two-stage, censoring-aware strategy. In the first stage, the model learns from patients with observed events and generates multiple plausible survival times for each censored patient, with all imputed times occurring after the observed censoring time. In the second stage, the model uses each imputed dataset as context and makes predictions through in-context learning. These predictions are then combined to produce the final result while accounting for uncertainty in the imputed survival times. For treatment recommendation, TabSurv fits a TabPFN regressor in context to risk scores from a random survival forest, which handles censoring, and estimates each patient’s predicted risk under hypothetical treatment reassignment.
Results: TabSurv was evaluated on twelve breast cancer gene expression cohorts under in-distribution and out-of-distribution settings. It achieved competitive or superior prognostic performance compared with eight established survival models and demonstrated the highest predictive stability under cohort heterogeneity. In exploratory treatment-recommendation experiments on METABRIC, patients whose treatment matched TabSurv’s recommendation showed the largest average restricted mean survival time advantage among the compared methods.
Conclusion: TabSurv provides an efficient and stable foundation-model-based approach to censored survival analysis, supporting robust prognosis and personalised treatment recommendation in heterogeneous breast cancer cohorts.
Journal IF-equivalent: 6.3 (OpenAlex 2-year mean citedness, value as of 2026-10-31, retrieved 2026-11-01; not the official Clarivate IF)Reference: Vu T, Tran HX, Li X, Pinero S, Liu L, Li J, et al. TabSurv: Tabular foundation model for breast cancer prognosis using gene expression data. Comput Methods Programs Biomed. 2027 Jan;288:109693. doi:10.1016/j.cmpb.2026.109693. PMID: 42962386.Checked: Abstract only
Lung cancer: treatment, trials and AI
- Abstract
Histologic transformation from lung adenocarcinoma (LUAD) to small cell lung cancer (SCLC) is a clinically important mechanism of acquired resistance to EGFR tyrosine kinase inhibitors, but the regulatory programs associated with this lineage transition remain incompletely characterized. We reanalyzed mouse and human single-cell and bulk transcriptomic datasets to define a 13-regulon Histologic Transformation Regulon Signature (HTRS) and developed TransRiskML, a machine-learning framework that stratifies LUAD samples into low-, medium-, and high-HTRS molecular states. Across independent cohorts, high-HTRS tumors showed poorer survival, stronger SCLC-like transcriptional features, distinct genomic features, and transcriptome-inferred drug-response patterns. HTRS captured transformation-associated molecular states that were largely independent of general proliferative activity across cohorts, although proliferation contributed substantially to the prognostic signal in advanced-stage NSCLC, where adjustment attenuated the association. A simplified 15-gene surrogate score was developed for downstream analyses, and exploratory pathology suggested a trend toward higher tumor-cell nuclear HDAC2 staining in pre-transformation LUAD and transformed SCLC specimens. These findings provide a systems-level framework for transformation-associated molecular-state stratification and prioritize candidate regulatory features for prospective investigation of LUAD-to-SCLC lineage plasticity. The framework is intended for hypothesis generation; prospective studies with documented transformation outcomes are required to determine its clinical utility.
Journal IF-equivalent: 5.1 (OpenAlex 2-year mean citedness, value as of 2026-10-31, retrieved 2026-11-01; not the official Clarivate IF)Reference: Tang M, Yang J, Zhang X, Zhang B, Jiang L, Bao J, et al. Machine learning stratification of LUAD-to-SCLC transformation states and drug-response signatures. npj Syst Biol Appl. 2026 Oct 30 [Epub ahead of print]. doi:10.1038/s41540-026-00845-6.Checked: Abstract only - Abstract
Objective: To develop a deep learning (DL) based probabilistic 3D deformable image registration framework for uncertainty-aware dose accumulation in magnetic resonance imaging-guided radiotherapy (MRgRT) of lung cancer. Approach: We propose TransMorph-prob (TM-prob), a variational Bayesian model that predicts the voxel-wise mean and variance of dense displacement fields (DDFs). Two TM-prob models were trained on an internal CT dataset (725 patients) and a low-field MR-linac dataset (102 patients), and benchmarked against Monte Carlo dropout TransMorph (TM-MCD) and DIRUncertainty with B-spline initialization (ASDIR) on the DIRLAB 4DCT dataset (10 patients, 3000 landmarks), and an annotated MR-linac dataset (16 patients, 107 image pairs, 227 landmarks) with target and seven organ-at-risk (OAR) contours. Both datasets contained an additional 1239/13,289 algorithm-generated landmarks. Performance was evaluated using target registration error (TRE), Dice similarity coefficient (DSC), landmark- and voxel-wise expected calibration errors (LECE/ECE), and dose distributions derived from 2000 DDF samples per patient. Main results: On the DIRLAB dataset, TM-prob achieved a median TRE of \qty{1.8}{\mm}/\qty{2.8}{\mm} on manual/algorithm-generated landmarks, versus \qty{1.3}{\mm}/\qty{2.4}{\mm} for ASDIR and \qty{2.1}{\mm}/\qty{3.0}{\mm} for TM-MCD. On the MRI dataset, TM-prob achieved the median TRE of \qty{3.9}{\mm}/\qty{2.6}{\mm} and a mean DSC of 0.87, matching ASDIR (\qty{3.3}{\mm}/\qty{2.7}{\mm}, and DSC of 0.87) while outperforming TM-MCD (\qty{4.4}{\mm}/\qty{2.9}{\mm}, and 0.84). In uncertainty calibration, TM-prob achieved a LECE of \qty{1.74}{\mm}/\qty{0.30}{\mm} on MRI manual/algorithm-generated landmarks versus \qty{2.41}{\mm}/\qty{0.56}{\mm} for ASDIR and \qty{6.65}{\mm}/\qty{3.92}{\mm} for TM-MCD, and an average contour ECE of 5.8% versus 7.0% and 21.2%. Two patients with indistinct GTV boundaries exhibited substantially wider target D95 distributions, demonstrating that calibrated DDF uncertainty translates into clinically relevant dose-coverage uncertainty.
Significance: TM-prob is an end-to-end DL model, achieving fast, well-calibrated, uncertainty-aware registration for lung cancer patients, enabling reliable DDF uncertainty propagation into dose accumulation for clinical decision-making in online adaptive radiotherapy.
Journal IF-equivalent: 2.9 (OpenAlex 2-year mean citedness, value as of 2026-10-28, retrieved 2026-10-29; not the official Clarivate IF)Reference: Wei C, Radonic D, Klaar R, Hohmann N, Marschner S, Eze C, et al. An uncertainty-aware deep learning-based registration model for adaptive lung cancer radiotherapy. Phys Med Biol. 2026 Oct 30 [Epub ahead of print]. doi:10.1088/1361-6560/aebc09. PMID: 42962374.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.
Brain tumours: treatment, trials and AI
- Abstract
Background: Therapy-induced tissue alterations complicate intraoperative diagnosis of recurrent CNS tumors. We evaluated stimulated Raman histology (SRH) combined with convolutional neural networks (CNNs) for rapid tumor detection and classification.
Methods: In this bicentric observational study, fresh tissue from patients undergoing resection or stereotactic biopsy for suspected recurrent CNS tumors was imaged with fiber-laser-based SRH. CNN1 performed binary tumor/non-tumor prediction and CNN2 histotype classification. CNN1 was evaluated against blinded neuropathologist SRH consensus and CNN2 against the final integrated histopathological diagnosis.
Results: Of 382 acquired SRH images, 262 images from 143 patients were included. CNN1 achieved an AUC of 0.975 (95% CI, 0.95–1.00) for tumor detection. An exploratory cohort-derived tumor probability threshold of ≥ 59 increased specificity from 70.7% to 92.0% while maintaining 95.2% sensitivity and identifying 71.4% of radiation necrosis samples. Among 212 images in treatment subgroup analysis, CNN1 accuracy did not differ significantly across prior-treatment groups (overall 90.1%; p = 0.080). CNN2 accuracy declined from 61.8% after surgery alone to 39.0% after surgery, radiotherapy, and medical treatment (χ²=6.04, p = 0.049). Multimodal therapy was independently associated with lower odds of correct CNN2 prediction (adjusted OR, 0.10 [95% CI, 0.02–0.39]; p = 0.001 and 0.04 [95% CI, 0.01–0.20]; p < 0.001). 120/382 images (31.5%) were of insufficient diagnostic quality; application of the quality control threshold would have rejected 84/120 (70.0%).
Conclusions: CNN1 maintained high tumor/non-tumor discrimination across treatment subgroups when image quality was sufficient, whereas CNN2 entity-classification performance declined with increasing treatment intensity. Reliable SRH-based diagnosis in recurrent tumors requires validated image-quality control measures and model adaptation to recurrent disease.
Journal IF-equivalent: 1.2 (OpenAlex 2-year mean citedness, value as of 2026-10-31, retrieved 2026-11-01; not the official Clarivate IF)Reference: Fürtjes G, Al Shughri A, Stehle T, Reinecke D, Meißner AK, Jung N, et al. Performance of intraoperative AI-assisted Label-Free Stimulated Raman Histology in Recurrent Brain Tumors. Neuro-Oncology Advances. 2026 Oct 29 [Epub ahead of print]. doi:10.1093/noajnl/vdag267.Checked: Abstract only - Abstract
Background: Distinguishing true progression (TP) from pseudoprogression (PsP) in glioblastoma (GBM) remains a clinical challenge as both often manifest as indeterminate contrast-enhancing lesions on post-treatment MRIs. However, integrating dynamic contrast-enhanced (DCE)-MRI with analytical methods such as clustering and machine learning offers a promising approach for distinguishing TP from PsP.
Methods: Quantitative analysis of DCE-MRI data from 82 patients with TP (n = 53) and PsP (n = 29) was performed using five pharmacokinetic models. Subsequently, a parsimonious selection method was used to identify the best fit for each voxel. In next step, clustering analysis using K-means ++ was performed to classify pixels into low, medium, and high-intensity regions. Tumors were segmented into enhancing, non-enhancing, and edema regions using automated nnU-Net algorithm and clusters were extracted from these regions. Significant features derived from clustering analysis and descriptive statistics (mean, median, and skewness) of DCE-MRI parameters and tumor volume were incorporated as input variables for classifier development. Finally, five machine learning classifiers were employed to differentiate between TP and PsP.
Results: Univariable clustering analysis of DCE-MRI data identified Ktrans, Ve, Vp, τi and tumor volumes as significant parameters for distinguishing TP from PsP. Multivariable clustering revealed that combined high-Ktrans–high-Ve is a key distinctive variable. Among machine learning classifiers tested using these parameters, Random Forest demonstrated the best diagnostic performance, achieving an accuracy of 83% and an AUC of 0.85.
Conclusion: Parsimonious analysis of DCE-MRI data in conjunction with clustering and machine learning could serve as a valuable method for accurately distinguishing TP from PsP in GBMs.
Journal IF-equivalent: 1.2 (OpenAlex 2-year mean citedness, value as of 2026-10-31, retrieved 2026-11-01; not the official Clarivate IF)Reference: Basak S, Bera S, Misra SN, Rajan A, Poptani H, Chawla S, et al. Differentiating True Progression from Pseudoprogression in Glioblastomas: Dynamic Contrast Enhanced-MRI Habitat Analysis with Parsimonious Pharmacokinetic Model. Neuro-Oncology Advances. 2026 Oct 29 [Epub ahead of print]. doi:10.1093/noajnl/vdag254.Checked: Abstract only
Ovarian cancer: treatment, trials and AI
- Abstract
Background: Platinum sensitivity is a key predictive and prognostic factor in epithelial tubo-ovarian carcinoma, however early prognostic estimation at multidisciplinary tumour boards remains challenging. Large language models can process unstructured clinical narratives, but their prognostic utility in gynaecological oncology remains unclear. We compared the performance of contemporary large language models with that of gynaecological oncologists in predicting platinum sensitivity and overall survival from baseline tumour board data.
Methods: In this retrospective cohort study, 69 patients with epithelial tubo-ovarian carcinoma were included. Standardized vignettes were independently assessed by five models using identical prompts and by three gynaecological oncologists from different institutions. Both models and experts classified platinum sensitivity (recurrence ≤6 months vs >6 months after first-line platinum-based therapy), overall survival ( < 2, 2–5, >5 years), and confidence (low, moderate, high). Exploratory analyses assessed performance by confidence level, neoadjuvant chemotherapy, case difficulty, and repeated assessment of LLM predictions.
Results: 86% of patients were platinum-sensitive. Platinum sensitivity accuracy ranged from 50.7% to 85.5% among large language models and from 49.3 % to 76.8% among experts, with no significant difference between groups ( P = 0.304). Large language models showed high sensitivity (52.5–100%) but low specificity (0–40%). Survival prediction accuracy was moderate (40.6–52.2% for large language models; 44.8–49.3% for experts), with no significant difference between groups ( P = 0.671). Accuracy increased with higher confidence but declined in neoadjuvant-treated patients and complex cases. In repeated assessments, mean model accuracy decreased for platinum sensitivity (71.5% to 62.6%) and overall survival (45.2% to 40.0%).
Conclusion: Large language models achieved similar overall accuracy to gynaecological oncologists when predicting platinum sensitivity and overall survival. However, limited specificity for platinum resistance, lower performance in complex cases, and temporal variability highlight important limitations. Large language models may serve as adjunctive decision-support tools but require prospective validation before clinical implementation.
Journal IF-equivalent: 3.9 (OpenAlex 2-year mean citedness, value as of 2026-10-09, retrieved 2026-10-10; not the official Clarivate IF)Reference: Galera A, Psilopatis I, Heidinger M, Schmid S, Siegenthaler F, Klar M, et al. Platinum sensitivity and overall survival stratification in epithelial tubo-ovarian carcinoma: a comparative evaluation of large language models and gynaecological oncologists. BMC Cancer. 2026 Oct 30 [Epub ahead of print]. doi:10.1186/s12885-026-17237-y.Checked: Abstract only
Endometrial cancer: treatment, trials and AI
- Abstract
Endometrial carcinoma (EC) is a highly prevalent malignant tumor of the female reproductive system, with a continuously rising global incidence and an increasing trend toward younger age at onset. Lymphovascular space invasion (LVSI) is an important independent prognostic risk factor for endometrial cancer and is closely associated with lymph node metastasis, distant recurrence, and poor overall survival. It is a core indicator for clinical risk stratification, selection of surgical extent, and formulation of postoperative adjuvant therapy. However, LVSI is a microscopic pathological change that can only be definitively diagnosed using postoperative pathological specimens. Subjective imaging interpretation of routine preoperative pelvic MRI cannot directly detect LVSI, and therefore cannot meet the clinical need for accurate preoperative risk assessment. MRI-based radiomics can mine high-throughput quantitative features that are invisible to the naked eye within tumor images, and deep learning can automatically learn hierarchical image features. Together, they provide a new avenue for noninvasive preoperative prediction of LVSI status in endometrial cancer. This article systematically reviews the research progress of MRI-based radiomics and deep learning in the field of LVSI prediction in endometrial cancer, elaborates on the standard radiomics workflow, traditional radiomics models, deep learning models, and the diagnostic performance of combined clinical-imaging prediction models, summarizes key issues in current research such as limited sample size, cross-center domain shift, insufficient reproducibility, and lack of prospective validation, and provides an outlook on future directions including clinical translation, multi-omics integration, and explainable artificial intelligence.
Journal IF-equivalent: 0.2 (OpenAlex 2-year mean citedness, value as of 2026-10-31, retrieved 2026-11-01; not the official Clarivate IF)Reference: Mo W, Tang W, Huang J, Zhao R, Wu Q. Research Progress of MRI-based Radiomics and Deep Learning in Lymphovascular Space Invasion of Endometrial Carcinoma. IJBLS. 2026 Oct 30;17(1):24-30. doi:10.54097/4tgers42.Checked: Abstract only
See all 1 Endometrial papers →
Gastric cancer: treatment, trials and AI
No new qualifying paper for this issue.
Liver cancer: treatment, trials and AI
No new qualifying paper for this issue.
Kidney cancer: treatment, trials and AI
- Abstract
Introduction: To develop and validate a multimodal CT-based model integrating intra-peritumoral radiomics, 2.5D deep learning (DL), and clinical-radiological features for preoperative prediction of World Health Organization/International Society of Urological Pathology (WHO/ISUP) grade in older patients with clear cell renal cell carcinoma (ccRCC).
Methods: This multicenter retrospective study included 1,103 patients older than 60 years with pathologically confirmed ccRCC from four hospitals. Patients were allocated to a training cohort (n=459), an internal validation cohort (n=198), and two independent external test cohorts (test1, n=227; test2, n=219). WHO/ISUP grades I–II were classified as low grade and grades III–IV as high grade. Radiomics features were extracted from corticomedullary-phase CT images using intratumoral and progressively expanded intra-peritumoral regions of 1, 2, and 3 mm. In parallel, 2D and 2.5D DL features were extracted using ImageNet-pretrained ResNet34 networks, with the 2.5D approach integrating axial, coronal, and sagittal tumor views. After feature selection, five machine learning classifiers were evaluated. The optimal radiomics model, DL model, and clinical model were integrated using stacking-based decision-level fusion. Model performance was assessed using receiver operating characteristic analysis, calibration curves, decision curve analysis (DCA), and SHapley Additive exPlanations (SHAP).
Results: The random forest (RF) model based on intra-peritumoral 3-mm radiomics features achieved areas under the receiver operating characteristic curve (AUCs) of 0.754 (95% CI, 0.683–0.825) and 0.725 (95% CI, 0.655–0.794) in the test1 and test2 cohorts, respectively. The RF model based on 2.5D DL features achieved corresponding AUCs of 0.756 (95% CI, 0.682–0.830) and 0.713 (95% CI, 0.643–0.783). The multimodal combined model achieved numerically higher external AUCs than the selected single-modality models, reaching 0.775 (95% CI, 0.705–0.845) in test1 and 0.732 (95% CI, 0.664–0.800) in test2. DCA demonstrated favorable clinical net benefit for the combined model, while SHAP analysis identified the 2.5D DL component as the largest contributor to model predictions. Discussion A multimodal CT-based framework integrating intra-peritumoral radiomics, 2.5D DL, and clinical-radiological information enabled noninvasive preoperative prediction of WHO/ISUP grade in older patients with ccRCC and maintained predictive performance across independent external cohorts. This approach may provide complementary imaging and clinical information for preoperative risk stratification and individualized treatment planning.
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, Liang Z, Lv D, Hu S, Zhou H, Li J, et al. Multimodal CT radiomics and 2.5D deep learning for preoperative grading of clear cell renal cell carcinoma in older patients: a multicenter study. Front Oncol. 2026 Oct 30;16:1982970. doi:10.3389/fonc.2026.1982970.Checked: Abstract only - Abstract
Background: Sarcomatoid renal cell carcinoma (sRCC) is a rare and aggressive subtype of renal cell carcinoma with a poor prognosis. Accurate prognostic stratification is critical for individualized treatment planning. This study aimed to develop and validate a machine learning-based prognostic model integrating multiphase CT radiomics and clinicopathological factors to predict overall survival (OS) in patients with pathology-confirmed sRCC.
Methods: A total of 113 patients with pathologically confirmed sRCC who underwent nephrectomy were retrospectively enrolled. Radiomic features were extracted from arterial phase (AP) and venous phase (VP) CT images. After feature selection using intraclass correlation coefficient (ICC > 0.75) and univariate Cox regression, a radiomics signature was constructed using least absolute shrinkage and selection operator (Lasso) regression and random survival forest (RSF) algorithms. A combined model was developed by integrating the radiomics score with independent clinical predictors identified through multivariate Cox regression. Model performance was evaluated using the concordance index (C-index), time-dependent receiver operating characteristic (ROC) curves, calibration curves, and decision curve analysis (DCA). Internal validation was performed using bootstrap resampling and repeated cross-validation.
Results: The combined model, incorporating the AP+VP radiomics score, N stage, M stage, and Ki-67 index, showed numerically improved predictive performance compared with the clinical model. In the held-out test set, it achieved a C-index of 0.737 (95% CI: 0.612–0.846), which was comparable to the AP+VP radiomics model alone (C-index: 0.735) and numerically higher than the clinical model (C-index: 0.615); however, the improvement over the clinical model was not statistically significant (P = 0.115). AUCs for 1-, 2-, and 3-year OS were 0.833, 0.780, and 0.749, respectively. The model showed good calibration and clinical utility across a range of threshold probabilities. Significant survival stratification was achieved between high- and low-risk groups (log-rank P < 0.05).
Conclusions: The proposed machine learning model combining multiphase CT radiomics and clinicopathological factors may provide a noninvasive tool for predicting OS in sRCC patients. It showed numerically improved performance compared with conventional clinical models; however, this incremental benefit was not statistically significant, and its performance was comparable to the radiomics-only model. Further multicenter validation is warranted to confirm its generalizability.
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: Liu T, Yao Y, Zhou Z, Hu Y, Sun L, Zhang G. Development and validation of a multiphase CT radiomics-based machine learning model for prognostic prediction in sarcomatoid renal cell carcinoma. Front Oncol. 2026 Oct 30;16:1982796. doi:10.3389/fonc.2026.1982796.Checked: Abstract only
Bladder cancer: treatment, trials and AI
- Abstract
This study aims to predict the expression of NRG1 in bladder cancer using pathomic techniques. We obtained transcriptomic data, pathological images, and clinical data of bladder cancer patients from TCGA. OTSU algorithm was used to segment images. The features obtained by mRMR_RFE screening were modeled by GBM algorithm. Further, the correlation between the Pathomics score and immune genes was analyzed. A total of 20 features were obtained by mRMR_RFE screening, and a prediction model of NRG1 was constructed. The AUC of the ROC curve in the training set and the validation set are 0.789 and 0.702 respectively. Pathomics score was positively correlated with immune-related genes ( p < 0.05). Silencing NRG1 could suppress BLCA cell proliferation, migration, invasion, whereas its overexpression exhibited contrasting effects. The pathomics model showed moderate discriminatory ability, and pathomics score is positively correlated with immune-related genes.
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: Zhang C, Wu F, Zhou Q, Duan Q, Zhu L, Huang W. Predicting NRG1 expression and its molecular-pathological features of bladder cancer through a machine learning-based pathomics model. Discov Onc. 2026 Oct 30 [Epub ahead of print]. doi:10.1007/s12672-026-06230-3.Checked: Abstract only
Rare cancers
Adenoid cystic carcinoma: treatment, trials and AI
No new qualifying paper for this issue.