AI and Cancer Research ── 2026-11-09
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（4）
Hematologic malignancies: AML（0） · CML（0） · ALL（0） · CLL（0） · Lymphoma（0） · Myeloma（0）
Solid tumors: Breast（2） · Lung（4） · Colorectal（3） · Pancreatic（2） · Prostate（0） · Brain（2） · Ovarian（1） · Endometrial（1） · Gastric（1） · Liver（1） · Kidney（0） · Bladder（1）
Rare cancers: ACC（0）
Cancer molecular biology and AI
- Abstract
OBJECTIVES: Chemotherapy-associated steatohepatitis (CASH) increases the risk of postoperative liver failure and mortality in patients undergoing liver surgery. However, non-invasive diagnosis remains an unmet need. Radiomics has potential for characterizing liver parenchyma. This study evaluated the performance of a virtual liver biopsy for CASH prediction, comparing it with whole-liver radiomic analysis. MATERIALS AND METHODS: Two retrospective series of patients undergoing hepatectomy for colorectal liver metastases were analyzed: the public "Colorectal-Liver-Metastases" dataset (training and internal validation) and a monocenter series from Humanitas Research Hospital (external validation). Inclusion criteria were preoperative chemotherapy (≥ 2 months) and post-chemotherapy CT (thickness ≤ 5 mm). IBSI-compliant radiomic features were extracted from whole-liver parenchyma and from a virtual biopsy (manually segmented 2-mL cylinder of non-tumoral liver parenchyma). Estimated liver volume (eLV) was computed using three orthogonal diameters. Four XGBoost models were developed (70/30 split, 5-fold cross-validation): clinical; clinical + VB-radiomics (ViB); clinical + VB-radiomics + eLV (ViBE+); clinical + whole-liver radiomics (WholeLiver). RESULTS: One hundred eighty patients were included: 105 internal (63 males, mean age 58.9 years, 38% CASH+) and 75 external (44 males, mean age 62.4 years, 19% CASH+). WholeLiver and ViBE+ models achieved excellent and comparable performance in internal validation (WholeLiver: AUC = 0.857 (95% BS-CI: 0.676-0.954), accuracy = 0.774 (95% BS-CI: 0.613-0.903); ViBE + : AUC = 0.831 (95% BS-CI: 0.549-0.956), accuracy = 0.839 (95% BS-CI: 0.710-0.935); p = 0.814), outperforming ViB model (AUC = 0.724 (95% BS-CI: 0.483-0.896), accuracy = 0.774 (95% BS-CI: 0.613-0.903)). SHAP analysis confirmed liver volume metrics as key predictors. In external validation, the ViBE+ model achieved AUC = 0.745 (95% BS-CI: 0.604-0.886) and accuracy = 0.680 (95% BS-CI: 0.562-0.783). CONCLUSION: Virtual biopsy provides a reproducible, non-invasive radiomic sampling strategy for CASH prediction. Combined with liver volume metrics, it achieves performance comparable to whole-liver analysis, supporting its potential clinical application. KEY POINTS: Question Despite its association with postoperative morbidity, the non-invasive preoperative assessment of CASH remains challenging in patients undergoing liver surgery.
Findings: Radiomic analysis based on a virtual liver biopsy, combined with volumetric measurements, showed excellent performance in predicting CASH, comparable to whole-liver analysis, with liver volume emerging as a key predictor. Critical Relevance Statement A standardized virtual biopsy-based radiomic analysis represents a promising non-invasive approach for evaluating liver parenchymal injury, as demonstrated in preoperative assessment of CASH and identification of high-risk surgical patients.
Journal IF-equivalent: 5.4 (OpenAlex 2-year mean citedness, value as of 2026-11-03, retrieved 2026-11-05; not the official Clarivate IF)Reference: Ammirabile A, Mastroleo F, De Martino R, Pugliese N, Waddle M, Laghi A, et al. Virtual liver biopsy for detecting steatohepatitis in chemotherapy-treated patients: comparison with whole-liver radiomics and external validation. Eur Radiol. 2026 Nov 7 [Epub ahead of print]. doi:10.1007/s00330-026-13004-6.Checked: Abstract only - Abstract
Objectives: Brain metastasis (BM) frequently occurs in advanced cancer patients, and accurate identification of the primary origin is essential for personalized treatment. Conventional imaging often lacks sensitivity and specificity for BM source prediction. This study aimed to develop and validate a multiparametric MRI-based radiomics model emphasizing brain–tumor interface (BTI) features to improve noninvasive BM origin identification. Materials and methods The primary cohort included 429 patients (740 BMs) from two centers, non-small cell lung cancer (NSCLC), small cell lung cancer (SCLC), breast cancer (BC), and gastrointestinal cancer (GIC), and an independent validation cohort of 33 patients (84 BMs) from a third center. All underwent pre-treatment 3.0 T MRI with T1-weighted contrast-enhanced (T1CE) and T2-weighted (T2W) sequences. Radiomic features were extracted from tumor core and BTI regions (2, 4, 6, 8 mm). Least absolute shrinkage and selection operator (LASSO) regression was used for feature selection, and radiomics signatures (RS) were evaluated using receiver operating characteristic (ROC) analysis.
Results: The constructed RS-BTI4 based on the 4-mm BTI region generated the best overall performance, with area under the ROC curve (AUCs) in the training cohort were 0.855 (LC/NLC), 0.910 (SCLC/NSCLC), and 0.890 (BC/GIC); in validation cohort, 0.726, 0.856, and 0.809; and in external validation cohort, 0.739, 0.750, and 0.792, respectively. RS-BTI4 consistently outperformed models based on other BTI radial widths and the whole tumor region in identifying the primary origin of BM.
Conclusion: BTI-derived radiomic features demonstrate strong potential for noninvasive identification of BM origin, with the 4-mm BTI region showing optimal predictive performance. Key Points Question Conventional MRI cannot reliably identify the primary origin of brain metastases, particularly when the primary tumor remains unknown at diagnosis.
Findings: The 4-mm brain–tumor interface model showed the most favorable overall performance, measured by area under the curve, across three binary classification tasks and validation cohorts. Critical relevance statement Integrating brain–tumor interface radiomics with multiparametric MRI may improve noninvasive estimation of BM origin and support more targeted diagnostic evaluation in clinical radiology.
Journal IF-equivalent: 6.5 (OpenAlex 2-year mean citedness, value as of 2026-11-03, retrieved 2026-11-05; not the official Clarivate IF)Reference: Jiang M, Han B, Huang Y, Rong X, Zhao W, Ge X, et al. Radiomics analysis of brain–tumor interface on multiparametric MRI for prediction of brain metastasis primary site. Insights Imaging. 2026 Nov 6;17(1):286. doi:10.1186/s13244-026-02464-5.Checked: Abstract only
See all 4 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: Preoperative prediction of axillary lymph node (ALN) metastasis remains challenging. We developed and externally validated a DCE-MRI-based multimodal fusion model integrating clinical, radiomics, habitat, and deep learning features.
Methods: A total of 404 patients from two centers were included. Center A ( n = 284) was split into training ( n = 198) and validation ( n = 86) sets; Center B ( n = 120) served as an independent external test cohort. Four sub-models (random forest for clinical variables, ExtraTrees for whole-tumor and habitat radiomics, ResNet50) were combined by weighted late fusion. Progressive fusion, a sequential ablation introducing modalities one at a time, tested whether each stream contributed non-redundant information; all 15 combinations were additionally evaluated. SHAP was applied to the feature-based sub-models and Grad-CAM to the CNN.
Results: On external testing, the fusion model achieved an AUC of 0.847 (95% CI 0.771–0.921), significantly higher than the clinical model (0.754; DeLong P = 0.017). Differences versus the radiomics (0.797), deep learning (0.784), and habitat (0.817) sub-models were numerical rather than statistically significant ( P = 0.074, 0.066, and 0.248). Progressive fusion showed stepwise gains (0.754, 0.807, 0.812, 0.847), and exhaustive combination analysis indicated that each modality contributed non-redundant information. SHAP identified T stage as the dominant clinical predictor, and the most influential habitat features originated from three different subregions. Grad-CAM showed tumor-focused attention.
Conclusion: This multimodal fusion model incorporating habitat radiomics achieved good discrimination for preoperative ALN prediction with external validation, and ablation confirmed each feature stream contributed non-redundant information.
Journal IF-equivalent: 5.7 (OpenAlex 2-year mean citedness, value as of 2026-11-04, retrieved 2026-11-05; not the official Clarivate IF)Reference: Wang W, Li Y, Zou X, Ji G, Peng J. A multicenter clinicopathologic and MRI-based multimodal fusion model for predicting axillary lymph node metastasis in breast cancer. Cancer Imaging. 2026 Nov 6 [Epub ahead of print]. doi:10.1186/s40644-026-01152-3.Checked: Abstract only - Abstract
BACKGROUND: Invasive ductal carcinoma (IDC) shows marked heterogeneity in clinical outcomes, often not fully captured by standard molecular subtypes. Tumor mutational burden (TMB) has limited prognostic utility in IDC due to low mutation rates and failure to account for structural genomic alterations. Fraction genome altered (FGA), reflecting copy number changes, may better represent genomic instability and disease aggressiveness. METHODS: We analyzed 3396 IDC patients from the AACR GENIE cohort, focusing on four key gene mutations (TP53, PIK3CA, GATA3, MAP3K1). Machine learning models (logistic regression and support vector machine) were trained using FGA or TMB as the main predictors, adjusted for clinical variables, to predict mortality. RESULTS: Fraction genome altered consistently outperformed TMB in mortality prediction across all gene subtypes. In TP53-mutated patients, FGA improved the area under the receiver operating characteristic curve (AUROC; 0.70 vs. 0.69) and accuracy (67% vs. 64%) compared to TMB. In MAP3K1, FGA achieved a significant AUROC increase (0.75 vs. 0.49), indicating a shift from poor to strong discriminative capacity. High negative predictive values were observed with FGA, reaching 85% in GATA3 and 83.3% in MAP3K1, indicating strong reliability in identifying survivors. CONCLUSION: Fraction genome altered is a more robust and interpretable predictor of mortality than TMB in IDC. Its consistent performance across diverse genomic subtypes highlights its potential as a clinically actionable biomarker for risk stratification and personalized patient management in breast cancer. ZUSAMMENFASSUNG: HINTERGRUND: Das invasive duktale Karzinom (IDC) weist eine deutliche Heterogenität bei den klinischen Ergebnissen auf, die oftmals nicht vollständig durch die molekularen Standardsubtypen erfasst werden. Die Tumormutationslast (TMB) hat beim IDC nur begrenzten prognostischen Nutzen aufgrund niedriger Mutationsraten und fehlender Berücksichtigung struktureller genomischer Alterationen. Der Anteil des veränderten Genoms („fraction genome altered“, FGA) spiegelt die Kopienzahlveränderungen wider und könnte genomische Instabilität und Krankheitsaggressivität besser darstellen. METHODEN: Aus der AACR-GENIE-Kohorte wurden die Daten von 3396 IDC-Patienten ausgewertet, mit Fokus auf 4 entscheidenden Genmutationen (TP53, PIK3CA, GATA3, MAP3K1). Modelle des maschinellen Lernens (logistische Regression und Support Vector Machine) wurden anhand von FGA oder TMB als den wesentlichen Prädiktoren unter Berücksichtigung klinischer Variablen trainiert, um die Mortalität vorherzusagen. ERGEBNISSE: Dabei war FGS über alle Gensubtypen hinweg durchgehend aussagekräftiger als TMB bei der Mortalitätsvorhersage. Bei Patienten mit TP53-Mutation verbesserten sich mit FGA die Fläche unter der Receiver-Operating-Kurve (AUROC; 0,70 vs. 0,69) und die Genauigkeit (67% vs. 64%) im Vergleich zu TMB. Bei MAP3K1 erzielte FGA einen signifikanten AUROC-Anstieg (0,75 vs. 0,49), was auf eine Verlagerung von einer schwachen zu einer starken diskriminativen Leistung hinweist. Für FGA wurden hohe negative prädiktive Werte festgestellt, sie erreichten 85% bei GATA3 und 83,3% bei MAP3K1, was auf eine starke Reliabilität in Bezug auf die Erkennung von Überlebenden hinweist. SCHLUSSFOLGERUNG: Die FGA ist ein robusterer und besser interpretierbarer Prädiktor der Mortalität als TMB bei IDC. Ihre durchgehende Leistung über verschiedene genomische Subtypen hinweg betont ihr Potenzial als klinisch nutzbarer Biomarker für die Risikostratifizierung und die personalisierte Patientenversorgung bei Brustkrebs.
Journal IF-equivalent: 1.2 (OpenAlex 2-year mean citedness, value as of 2026-11-07, retrieved 2026-11-08; not the official Clarivate IF)Reference: Kumari B, Lahariya R, Anand G. Fraction genome altered outperforms tumor mutational burden for machine learning-based mortality prediction across TP53, PIK3CA, GATA3, and MAP3K1 subtypes in invasive ductal carcinoma. Wien Med Wochenschr. 2026 Nov 6 [Epub ahead of print]. doi:10.1007/s10354-026-01202-2.Checked: Abstract only
Lung cancer: treatment, trials and AI
- Abstract
Background: Intratumor heterogeneity in lung adenocarcinoma (LUAD) profoundly influences tumor progression and immune evasion. However, current prognostic models largely fail to capture the complex cellular dynamics of the tumor microenvironment (TME) at single-cell resolution.
Methods: We integrated single-cell RNA sequencing with bulk transcriptomics to derive cell-type-specific signatures. A systematic evaluation of 101 machine learning algorithm combinations was performed across multiple independent cohorts to construct a robust prognostic model. Immune landscape, mutational features, intercellular communication, and immunotherapy responsiveness were comprehensively evaluated. The biological functions of the identified hub gene, transmembrane 4 L six family member 1 (TM4SF1), were rigorously validated in vitro .
Results: The optimal StepCox[forward]-Ridge model showed strong prognostic stratification in five cohorts. Low-risk tumors exhibited an immune-inflamed phenotype, suggesting greater predicted good responses to immune checkpoint blockade. In contrast, high-risk tumors had an immunosuppressive TME with overactive cell communication driven by fibroblasts and myeloid cells. TM4SF1 was a key driver in this high-risk signature. TM4SF1 silencing significantly inhibited LUAD cell proliferation, migration, and invasion, and strongly induced apoptosis. TM4SF1 depletion reversed tumor immune evasion by reducing PD-L1, increasing MHC-I, and lowering the secretion of CCL5.
Conclusions: This single-cell-guided machine-learning framework provides strong prognostic stratification in LUAD and captures immune phenotypes associated with potential immunotherapy responsiveness. TM4SF1 emerged as a candidate mediator associated with malignant progression and immune-related phenotypes in LUAD, warranting further mechanistic and in vivo investigation. This suggests it could be a useful therapeutic target.
Journal IF-equivalent: 2.8 (OpenAlex 2-year mean citedness, value as of 2026-11-03, retrieved 2026-11-04; not the official Clarivate IF)Reference: Li J, Liu T, Li L, Lu W, Huang J, Li X, et al. A single-cell transcriptomics-based prognostic model identifies TM4SF1 as a key promoter of malignant progression in lung adenocarcinoma. Front Oncol. 2026 Nov 6;16:1948068. doi:10.3389/fonc.2026.1948068.Checked: Abstract only - Abstract
Real-time detection of rare cancer cells holds potential for guiding more informed treatment decisions at the bedside. However, conventional enrichment methods are limited by low sensitivity, a high risk of cell damage, and prolonged processing times. To address these challenges, this study developed an intelligent micro-total analysis platform toward H1299 cells (a metastatic non-small cell lung cancer cell line). The system integrates a cascaded dual-microfluidic chip architecture with a high-resolution microscope driven by a deep learning-based detection framework. Finite element simulations were performed to optimize droplet generation conditions for the cross-junction microfluidic chip. A dataset of 749 high-resolution droplet images (1536 × 1024 pixels) was constructed, comprising 2619 live H1299 lung cancer cells distributed across 5127 droplets. Among the algorithms evaluated, the YOLOv7 model was selected and optimized, achieving a detection accuracy above 98% and a real-time inference speed exceeding 55 frames per second. As a proof of concept, the platform was applied to quantitatively analyze single-cell level responses to anticancer drugs in undiluted whole blood and processed biopsy samples within 30-40 min, yielding results consistent with those of the standard Cell Counting Kit-8 (CCK-8) assay. The minimal sample requirement, label-free operation, and stable performance of the system underscore its potential for treatment monitoring. Moreover, its capacity for continuous image acquisition and autonomous analysis may facilitate dynamic monitoring in future cancer research.
Journal IF-equivalent: 11.9 (OpenAlex 2-year mean citedness, value as of 2026-11-07, retrieved 2026-11-08; not the official Clarivate IF)Reference: Zhang S, Bo B, Gu H, Chen M, Wu D, Li Y, et al. A deep monitoring microfluidic platform for label-free identification and nanodrug evaluation in lung cancer. Biosensors and Bioelectronics. 2027 Feb;318:119395. doi:10.1016/j.bios.2026.119395.Checked: Abstract only
Colorectal cancer: screening, treatment, trials and AI
- Abstract
Tumor-associated macrophages (TAMs) are key regulators of the tumor microenvironment in colorectal cancer (CRC), yet their functional heterogeneity remains poorly understood, especially regarding the interplay between cellular senescence and lipid metabolism. We integrated multi-omics and single-cell transcriptomic data to characterize a novel macrophage subpopulation termed senescence-associated lipid-metabolic (SALM) macrophages. Using eight machine learning algorithms, a prognostic model based on SALM signatures was developed and internally evaluated via nested cross-validation in a combined TCGA–GSE39582 cohort. Spatial multiplex immunofluorescence and qPCR were employed for experimental validation. SALM macrophages exhibit elevated IL-10/STAT3 signaling, terminal differentiation, and a core gene module enriched in senescence and lipid metabolism pathways. They interact strongly with T cells via immunosuppressive ligands IL-10 and MIF. Spatial analysis confirmed p16 + CD68 + IL-10 + cell enrichment at the tumor front. The SALM-based prognostic model achieved high accuracy (AUC = 0.972), and a corresponding nomogram showed potential for personalized prognosis prediction. SALM macrophages drive immunosuppression in CRC through a senescence-lipid metabolism axis, serving as a novel prognostic biomarker and potential therapeutic target.
Journal IF-equivalent: 5.9 (OpenAlex 2-year mean citedness, value as of 2026-11-04, retrieved 2026-11-05; not the official Clarivate IF)Reference: Zhao B, Liao Y, Ye S, Jiang N, Lu W, Chen Y, et al. Multi-omics and machine learning reveal a senescence-associated lipid-metabolic macrophage phenotype driving immunosuppression and poor prognosis in colorectal cancer. Sci Rep. 2026 Nov 7 [Epub ahead of print]. doi:10.1038/s41598-026-80104-0.Checked: Abstract only - Abstract
Colorectal cancer (CRC) remains a leading cause of cancer-related mortality in the UK. Early detection and removal of adenomatous polyps are essential to improving outcomes. Artificial intelligence-assisted colonoscopy tools, such as GI Genius (GIG), may enhance adenoma detection rates (ADR) and reduce the likelihood of missed lesions. A patient-level simulation cost-effectiveness model was developed to estimate the economic and clinical impact of GIG-assisted colonoscopy compared with standard colonoscopy alone in a symptomatic for suspected CRC population in England. The model adopted a National Health Service and Personal Social Services perspective, with a lifetime time horizon. Key model inputs were informed by the NAIAD trial, which evaluated the impact of GIG-assisted colonoscopy on ADR, compared with standard colonoscopy. Base case and probabilistic sensitivity analysis (PSA) were conducted to estimate the incremental cost-effectiveness ratio and the probability of cost effectiveness. Base case results suggest that GIG is a cost-effective intervention, associated with per-person cost savings of £69 and quality-adjusted life year (QALY) gains of 0.046. This was primarily due to increased ADR and subsequent reduced CRC incidence. Scenario analyses testing uncertainty around the sensitivity of colonoscopy, clinical outcomes for those initially undiagnosed, differences in outcomes across experienced and non-experienced endoscopists, and the total costs of GIG produced findings that were consistent with the base case and did not materially change the estimated costs or QALYs. PSA results indicate that GIG is cost effective in 53% of simulations at the £20,000 per QALY gained threshold. This uncertainty is attributable to the marginal change in QALY outcomes between arms of the model, meaning that minor fluctuations in QALY outcomes between PSA iterations lead to large variations in the ICER. The results highlight that GIG is a cost-saving intervention that can improve health outcomes by increasing ADRs. Scenario analyses broadly support the base case findings, suggesting that the conclusions were generally consistent across the alternative assumptions explored. PSA results highlighted considerable decision uncertainty, driven by the small incremental differences in QALYs. PSA results highlight considerable decision uncertainty, driven by the small incremental differences in QALYs.
Journal IF-equivalent: 4.9 (OpenAlex 2-year mean citedness, value as of 2026-11-07, retrieved 2026-11-08; not the official Clarivate IF)Reference: Curtis-Gretton L, Varghese AA, Watts K, Green M, Holmes H. The economic and clinical impact of an AI-assisted tool for colonoscopy to support diagnosis of colorectal cancer in symptomatic patients in England. BMC Digit Health. 2026 Nov 6;4(1):79. doi:10.1186/s44247-026-00314-4.Checked: Abstract only
Pancreatic cancer: treatment, trials and AI
- Abstract
BACKGROUND: Pancreatic ductal adenocarcinoma (PDAC) frequently exhibits lymph node (LN) metastasis, making early identification of high-risk patients crucial for optimizing treatment strategies. However, robust predictive models and external validation remain limited. This study aimed to develop and validate an artificial intelligence (AI) model for preoperative detection of LN status in PDAC patients. METHODS: We retrospectively enrolled 233 pathologically confirmed PDAC patients from two high-volume pancreatic surgery centers between July 2015 and July 2022. All patients underwent contrast-enhanced computed tomography (CT) scans and met strict inclusion and exclusion criteria. Two experienced radiologists independently reviewed imaging. Radiomics analysis was performed using MATLAB and Python-based PyRadiomics. Following feature selection, 14 radiomic features were retained to construct a radiomics score. Three predictive models were developed and compared. RESULTS: From 1,652 extracted radiomic features, 14 were selected to build a radiomics score significantly associated with LN metastasis (P<0.001). Multivariate logistic regression identified tumor location, vascular invasion, white blood cell (WBC) count, platelet count, and radiomics score as independent predictors of LN metastasis, and a nomogram was generated. Various machine learning algorithms were evaluated to identify the optimal model combining radiomic and clinical data. Decision curve analysis demonstrated that the extreme gradient boosting (XGBoost) model achieved superior accuracy and stability, with an area under the curve (AUC) of 0.86 in the training set and 0.81 in the validation set. CONCLUSIONS: We successfully developed a LN metastasis prediction model integrating preoperative CT radiomics and clinical variables. The XGBoost-based model exhibited excellent accuracy, robustness, and generalizability. Future studies should focus on constructing more reliable models through standardized pathological sampling and prospective multicenter trials, alongside advancing imaging techniques to improve identification of small LNs.
Journal IF-equivalent: 1.8 (OpenAlex 2-year mean citedness, value as of 2026-11-08, retrieved 2026-11-09; not the official Clarivate IF)Reference: Li Y, Wu S, Qiu J, Meng L, Zhang M, Cai H, et al. Deep learning radiomics model for lymph node metastases prediction: a diagnostic study. Gland Surg. 2026 Oct;15(10):276-6. doi:10.21037/gs-2026-0378.Checked: Abstract only - Abstract
BACKGROUND: Tertiary lymphoid structures (TLS) are emerging prognostic biomarkers in pancreatic ductal adenocarcinoma (PDAC), yet no reliable non-invasive tool exists for their preoperative assessment. This study aimed to develop and validate a contrast-enhanced computed tomography (CECT)-based habitat radiomics model for preoperative prediction of intratumoral TLS status in PDAC. METHODS: In this retrospective study, 204 surgically resected PDAC patients were enrolled and allocated into training (n=142) and validation (n=62) cohorts. TLS status was determined by fluorescent multiplex immunohistochemistry (mIHC), with positive cases subclassified as primary or secondary follicle-like TLS. K-means clustering partitioned the tumor volume of interest (VOI) into spatially distinct subregions; radiomics features were extracted from each subregion and selected via least absolute shrinkage and selection operator (LASSO) regression. Five machine learning classifiers were evaluated. Independent clinical predictors were identified by multivariate logistic regression (LR) and integrated with the optimal imaging model to construct a combined model. RESULTS: TLS positivity was observed in 32.84% of patients. The LR-based habitat model achieved area under the curve (AUC) of 0.939 and 0.873 in the training and validation cohorts, substantially outperforming the conventional radiomics model (AUCs: 0.815 and 0.701). Tumor differentiation and neural invasion were identified as independent clinical predictors. The combined model yielded the highest AUCs of 0.956 and 0.881, with favorable calibration and superior net clinical benefit on decision curve analysis (DCA). CONCLUSIONS: CECT-based habitat radiomics enables robust, non-invasive preoperative prediction of intratumoral TLS in PDAC, offering a practical tool for individualized risk stratification and treatment planning; incorporation of clinical variables yielded numerically higher AUCs but without statistically significant improvement.
Journal IF-equivalent: 1.8 (OpenAlex 2-year mean citedness, value as of 2026-11-08, retrieved 2026-11-09; not the official Clarivate IF)Reference: Li K, Guo R, Wang X, Li L, Yu F, Li Z, et al. Habitat radiomics combined with clinical features for predicting tertiary lymphoid structure status in pancreatic ductal adenocarcinoma: development and validation of a preoperative CECT-based model. Gland Surg. 2026 Oct;15(10):289-9. doi:10.21037/gs-2026-0439.Checked: Abstract only
Prostate cancer: treatment, trials and AI
No new qualifying paper for this issue.
Brain tumours: treatment, trials and AI
- Abstract
Background/Objectives: After chemoradiation for glioblastoma, residual or recurrent tumor (tumor-positive disease, TP) and treatment-related change (TRC), which includes pseudoprogression and radiation necrosis, look alike on conventional MRI. We tested whether radiomic features from dynamic susceptibility contrast (DSC) perfusion MRI alone can separate them.
Methods: We analyzed 224 post-treatment MRI examinations from 168 patients in the public UCSD-PTGBM collection. A machine-learning ensemble was trained on 1223 radiomic features from the leakage-corrected relative cerebral blood volume (rCBV) map, with training (109 patients, 143 examinations) and test (59 patients, 81 examinations) data separated at the patient level and the model fixed before testing. The analysis was repeated on the cerebral blood flow (CBF) map from the same scans, and DSC was compared with arterial spin labeling (ASL) in patients who had both.
Results: On the independent test set (patient-level analysis), the model distinguished TP from TRC with an area under the receiver operating characteristic curve (AUC) of 0.79 (95% CI 0.67–0.89). It detected 31 of 49 patients with tumor (sensitivity 63%) and correctly identified all 10 patients with TRC (specificity 100%); at a predefined higher-sensitivity cut-off, sensitivity was 69% and specificity 80%. With the CBF map, the AUC did not differ significantly (0.78; p = 0.89), but there was a different balance of sensitivity and specificity. In an exploratory subset of 36 patients, DSC and ASL did not differ significantly (AUC 0.82 vs. 0.71; p = 0.52).
Conclusions: DSC perfusion radiomics alone identified tumor with high specificity but missed about one-third of tumors: a positive result may support a diagnosis of tumor, whereas a negative result cannot exclude it. External, multicenter validation is needed before clinical use.
Journal IF-equivalent: 6.1 (OpenAlex 2-year mean citedness, value as of 2026-11-07, retrieved 2026-11-08; not the official Clarivate IF)Reference: Christodoulou RC, Christofi G, Vamvouras G, Esmeraldo MA, Papageorgiou PS, Vassiliou E, et al. Explainable DSC Perfusion Radiomics for Post-Treatment Glioblastoma Assessment Using a Soft-Voting Machine-Learning Ensemble. Cancers. 2026 Nov 6;18(21):3567. doi:10.3390/cancers18213567.Checked: Abstract only - Abstract
Early brain tumor staging is critical to the success of currently available treatment planning and modalities. Magnetic Resonance Imaging (MRI) is a necessary method for treatment planning and early diagnosis. Most current classification methods do not achieve a high level of classification accuracy, which may result in some tumor cases being misclassified or classified as suspicious. In our proposed work, we leverage the DenseNet201 deep learning architecture as the foundation for classifying brain tumors. A dataset in this methodology consisted of MRI scans, which included four unique types of tumors: meningioma, pituitary tumor, no tumor, and glioma. To improve classification precision, improve generalization, and reduce overfitting, we employed three strategies (a1, a2, and a3) during the classification process. When our model was evaluated on unseen test data, it achieved an impressive 99.77\% accuracy. The proposed technique effectively classifies malignant brain tumors, despite the similarities within classes and the varying tumor morphologies. There are four state-of-the-art techniques of deep learning that we compared our results with: ResNetRS50, ResNet50, VGG19, and EfficientNetV2, which achieved accuracies of 99.77\%, 98.71\%, 96.88\%, and 96.58\%, respectively. In the field of brain tumor classification, our approach has outperformed others in terms of performance, highlighting its potential for clinical applications.
Journal IF-equivalent: 1.2 (OpenAlex 2-year mean citedness, value as of 2026-11-07, retrieved 2026-11-08; not the official Clarivate IF)Reference: Thamer Z, Sagheer N, Ata O, Abdulmunem A, Thamer H. Brain Tumor Classification Accuracy Enhancement via DenseNet201 Compared to Four Alternative Models. ELCVIA. 2026 Nov 5;25(3):65-80. doi:10.5565/rev/elcvia.2305.Checked: Abstract only
Ovarian cancer: treatment, trials and AI
- Abstract
Borderline ovarian tumors (BOTs) are epithelial ovarian tumors with a favorable prognosis, particularly in younger patients. Fertility-sparing surgery (FSS) is often preferred for patients desiring to preserve fertility. This study aimed to develop a machine learning (ML)-based prediction model to identify patients at high risk of recurrence after FSS. A multi-center retrospective study was conducted, including 589 BOT patients who underwent FSS between 2010 and 2023. Clinical, pathological, and laboratory data were collected, and ten ML algorithms were evaluated for their predictive performance. The dataset was preprocessed, and feature selection was conducted using univariate analyses and feature importance scores derived from preliminary ML models. The dataset was randomly split into training and test sets, and hyperparameter tuning was performed using grid search and cross-validation. Model performance was assessed using metrics such as AUC, accuracy, sensitivity, and specificity. The Gradient Boosting model demonstrated the highest accuracy, with an AUC of 0.94, sensitivity of 91%, and specificity of 88%. Key predictors of recurrence included histological subtype, age at diagnosis, tumor size, and surgical approach. The model’s interpretability was enhanced using SHAP values, which highlighted the importance of these features. Additionally, a web-based tool was developed to facilitate clinical application of the model, allowing physicians to input patient data and obtain recurrence risk predictions. This study highlights the potential of ML-based models in improving personalized post-surgical management and optimizing oncological and reproductive outcomes for BOT patients undergoing FSS.
Journal IF-equivalent: 5.6 (OpenAlex 2-year mean citedness, value as of 2026-11-08, retrieved 2026-11-09; not the official Clarivate IF)Reference: Gao Y, Yan C, Li W, Gao M, Wang T, Huang C, et al. Machine learning based model to predict the recurrence after fertility sparing surgery in patients with borderline ovarian tumor. J Ovarian Res. 2026 Nov 7 [Epub ahead of print]. doi:10.1186/s13048-026-02300-w.Checked: Abstract only
Endometrial cancer: treatment, trials and AI
- Abstract
OBJECTIVES: Preoperative identification of FIGO 2023 stage I endometrial cancer (EC) is important for treatment planning. We aimed to develop and validate a deep-learning radiomics nomogram (DLRN) based on multiparametric MRI to distinguish stage I EC from stage II-IV disease. MATERIALS AND METHODS: This study retrospectively enrolled patients from three centers. Patients from Centers 1 and 2 were randomly split into a training set (n = 616), and an internal test set (n = 158), and Center 3 served as an external test set (n = 232). The DLRN integrated deep-learning features, intratumoral and peritumoral radiomics features, and clinical characteristics. The DLRN was compared with clinical, radiomics, and deep-learning models. Discrimination was evaluated using the area under the receiver operating characteristic curve (AUC), with AUCs compared using DeLong's test. RESULTS: A total of 1006 patients (mean age, 56.5 ± 9.7 years) were analyzed. In the internal test set, the DLRN achieved an AUC of 0.852, higher than the clinical (0.673; p = 0.001), original radiomics (0.765; p = 0.030), and combined radiomics (0.793; p = 0.050) models. In the external test set, the DLRN remained robust (AUC = 0.829) and outperformed the clinical, original radiomics, and combined radiomics models (AUC = 0.680, 0.681, and 0.743; all p < 0.005). With DLRN assistance, radiologists showed improved diagnostic performance. CONCLUSION: The MRI-based DLRN showed robust discrimination between FIGO 2023 stage I and stage II-IV EC across test sets, supporting its potential for preoperative risk stratification and decision support. KEY POINTS: Question The introduction of the FIGO 2023 staging system has made the differentiation between stages more challenging, highlighting the need for better tools.
Findings: A new MRI-based deep-learning radiomics nomogram (DLRN) accurately identifies high-risk patients, significantly outperforming traditional and individual clinical prediction methods. Critical relevance statement This tool helps doctors make better preoperative treatment plans, potentially improving patient outcomes in endometrial cancer.
Journal IF-equivalent: 6.5 (OpenAlex 2-year mean citedness, value as of 2026-11-03, retrieved 2026-11-05; not the official Clarivate IF)Reference: Chu X, Gao L, Wang X, Quan T, Ding Y, Chen Y, et al. MRI-based deep-learning radiomics nomogram for differentiating FIGO 2023 stage I from stage II–IV endometrial cancer: a multicenter study. Insights Imaging. 2026 Nov 6;17(1):284. doi:10.1186/s13244-026-02428-9.Checked: Abstract only
See all 1 Endometrial papers →
Gastric cancer: treatment, trials and AI
- Abstract
BACKGROUND: Gastric cancer (GC) exhibits substantial molecular heterogeneity and a complex tumor microenvironment (TME). Apoptotic protease-activating factor 1 (APAF1) is a core component of mitochondrial apoptosis; however, its association with immune characteristics, spatial heterogeneity and compound discovery in GC remains poorly defined. METHODS: The bulk transcriptomics, single-cell RNA sequencing and spatial transcriptomics with machine learning-based modeling, immune deconvolution and spatial niche analysis were integrated to characterize APAF1-associated features in GC. Machine learning-guided computational screening combining molecular docking and molecular dynamics (MD) simulations was used to prioritize morellic acid (MA). The biological effects of MA and the involvement of APAF1-associated signaling were evaluated through in vitro and in vivo assays using APAF1-targeting siRNA and shRNA, respectively. RESULTS: APAF1 expression was increased in GC, particularly in early-stage tumors and was independently associated with improved overall survival after multivariable adjustment (HR = 0.681, 95% CI: 0.494-0.940, P = 0.0196). However, its standalone prognostic discrimination was limited, with time-dependent ROC analyses showing poor predictive performance. Tumor-versus-normal ROC analysis demonstrated differential expression between GC and normal tissues (AUC = 0.875, 95% CI: 0.823-0.918). Single-cell and spatial analyses revealed that APAF1 expression was associated with distinct immune-cell patterns and tumor spatial niches. Machine learning-guided computational screening prioritized MA as a candidate compound. MA inhibited GC cell proliferation and migration (IC50: 1.807 ± 0.16 to 6.216 ± 0.23 μM) and suppressed tumor growth in vivo, achieving tumor inhibition rates of 79.32 ± 7.69%, 92.37 ± 4.21%, and 92.19 ± 2.99% at low, medium and high doses, respectively. APAF1 silencing attenuated MA-associated changes in cleaved Caspase-3 activation and GSDME-NT accumulation, suggesting the involvement of APAF1-associated cell-death signaling. CONCLUSION: APAF1 is associated with distinct tumor microenvironment characteristics and clinical features in GC, supporting its potential relevance to tumor biology beyond its canonical role in mitochondrial apoptosis. The novelty of this study lies in extending the investigation of APAF1 beyond its canonical apoptotic function by integrating machine learning with multimodal transcriptomic and spatial analyses to characterize APAF1-associated TME features and computationally prioritize MA. All the findings provide a cross-scale framework linking APAF1-associated tumor biology with candidate compound screening and MA-related cell-death responses in GC.
Journal IF-equivalent: 10.4 (OpenAlex 2-year mean citedness, value as of 2026-11-08, retrieved 2026-11-09; not the official Clarivate IF)Reference: Jia B, Yan B, Li S, Yang J, Cheng Z, Zhou X, et al. Machine learning-guided multimodal analysis of APAF1-associated tumor microenvironment features prioritizes morellic acid for gastric cancer. Phytomedicine. 2026 Nov;162:158895. doi:10.1016/j.phymed.2026.158895.Checked: Abstract only
Liver cancer: treatment, trials and AI
- Abstract
BACKGROUND: Postoperative pulmonary complications (PPCs) are common after hepatectomy and are associated with delayed recovery, prolonged hospitalization, and increased healthcare burden in patients with primary liver cancer (PLC). Existing PPC risk assessment approaches are mainly derived from general surgical populations and may not adequately incorporate hepatectomy-specific perioperative factors, including surgical complexity and intraoperative characteristics. This study aimed to develop and externally validate an explainable machine-learning prediction model for postoperative PPC risk stratification after hepatectomy in patients with PLC. METHODS: This retrospective prediction-model development and validation study included 906 consecutive adult patients with pathologically confirmed PLC who underwent elective hepatectomy at a tertiary hospital in China. Patients with preoperative pulmonary infection, emergency surgery, non-resection procedures, severe preoperative organ failure, concomitant malignancy, or incomplete key clinical data were excluded. The development cohort was randomly divided into training (n=635) and internal testing (n=271) cohorts. An independent external validation cohort included 388 patients from another hospital. Candidate predictors were obtained from routine perioperative electronic medical records (EMRs), including demographic characteristics, comorbidities, laboratory parameters, tumor-related characteristics, and intraoperative variables. Missing predictors were handled using multiple imputation by chained equations (MICE). PPCs were defined according to the European Perioperative Clinical Outcome (EPCO) criteria and assessed within 30 days after surgery. Feature selection was performed using least absolute shrinkage and selection operator (LASSO) regression and random forest recursive feature elimination (RF-RFE). Eight machine-learning algorithms were developed using training-cohort cross-validation and evaluated based on discrimination, precision-recall performance, calibration, classification performance, and decision-curve analysis (DCA). Model interpretability was assessed using Shapley Additive Explanations (SHAP). RESULTS: Among 906 patients in the development cohort, 131 (14.5%) developed PPCs, while 66 of 388 patients (17.0%) developed PPCs in the external validation cohort. Among the evaluated algorithms, the Naïve Bayes (NB) model demonstrated the most balanced performance. In the internal testing cohort, NB achieved an area under the curve (AUC) of 0.851 [95% confidence interval (CI): 0.767-0.934], an area under the precision-recall curve (PR-AUC) of 0.668 (95% CI: 0.485-0.798), sensitivity of 71.1%, specificity of 90.6%, and Brier score of 0.075. In the external validation cohort, NB maintained consistent performance with an AUC of 0.861 (95% CI: 0.810-0.911), a PR-AUC of 0.650 (95% CI: 0.516-0.759), sensitivity of 63.6%, specificity of 86.0%, and Brier score of 0.094. SHAP analysis identified age, intraoperative blood transfusion, and portal triad clamping duration as major contributors to individualized PPC risk predictions. CONCLUSIONS: An explainable NB-based machine-learning model was developed and externally evaluated for postoperative PPC risk stratification after hepatectomy in patients with PLC. The model demonstrated consistent discrimination, precision-recall performance, calibration, and potential clinical utility and may assist in identifying patients who could benefit from enhanced postoperative respiratory surveillance. Further prospective multicenter validation and clinical impact studies are required before broader clinical translation.
Journal IF-equivalent: 2.0 (OpenAlex 2-year mean citedness, value as of 2026-11-08, retrieved 2026-11-09; not the official Clarivate IF)Reference: Lu L, Ma Y, Li Q. Development and external validation of an explainable machine learning model using routine perioperative clinical variables for postoperative pulmonary complication risk stratification after hepatectomy for primary liver cancer. J Gastrointest Oncol. 2026 Oct;17(5):301-1. doi:10.21037/jgo-2026-0702.Checked: Abstract only
Kidney cancer: treatment, trials and AI
No new qualifying paper for this issue.
Bladder cancer: treatment, trials and AI
- Abstract
BACKGROUND AND PURPOSE: After bladder-sparing chemoradiotherapy (CRT) for muscle-invasive bladder cancer (MIBC), residual microscopic disease may cause intravesical recurrence. This study aimed to develop machine learning models to predict pathological complete response (pCR) after CRT. MATERIALS AND METHODS: We retrospectively analyzed 285 patients with cT2-4N0M0 MIBC who underwent CRT followed by partial or radical cystectomy. CRT response was determined from cystectomy specimens. Patients were randomly assigned to a training cohort ( n = 228) and a test cohort ( n = 57) using a fixed random seed. A total of 102 machine learning models were evaluated in the training cohort. The model with the highest area under the receiver operating characteristic curve (AUC) in the training-cohort was selected and then evaluated in the test cohort. The model incorporated clinical T stage, tumor size, multiplicity, hydronephrosis, bladder neck involvement (BNI), concomitant carcinoma in situ (CIS), variant histology, grade, and progression. RESULTS: Clinical T stages were T2/3/4 in 169/105/11 patients, respectively. Hydronephrosis was observed in 69 patients. Transurethral resection before CRT revealed multiplicity, BNI, and concomitant CIS in 108, 54, and 34 patients, respectively. Overall, 178/285 patients (62%) achieved pCR. WeightedEnsemble_L4 was selected as the final model and had a test-cohort AUC of 0.829 (95% confidence interval [CI], 0.706-0.932). The calibration slope was 0.856 (95% CI, 0.469-1.639), and the wide CI indicated uncertainty in calibration. CONCLUSION: Machine learning based on clinicopathologic variables estimated pCR after CRT. This may support decision-making regarding bladder preservation in patients with MIBC.
Journal IF-equivalent: 2.1 (OpenAlex 2-year mean citedness, value as of 2026-11-08, retrieved 2026-11-09; not the official Clarivate IF)Reference: Fujiwara M, Tanaka H, Hirahara D, Saho T, Takaya E, Matsumoto S, et al. Machine learning models to predict pathological complete response after chemoradiotherapy in muscle-invasive bladder cancer: toward optimized indications for bladder preservation. Clinical and Translational Radiation Oncology. 2027 Jan;62:101320. doi:10.1016/j.ctro.2026.101320.Checked: Abstract only
Rare cancers
Adenoid cystic carcinoma: treatment, trials and AI
No new qualifying paper for this issue.