AI and Cancer Research ── 2026-10-14
New papers on cancer and AI, collected from journal feeds, PubMed (searched across all journals) and OpenAlex (a public index used instead of Google Scholar), judged by Jev (an AI that makes language judgements): original research, AI central, which of 13 themes, treatment or trials, and then ranked by importance up to a daily limit. Journals are not filtered by impact factor; each paper shows its journal's IF-equivalent (OpenAlex two-year mean citedness) and the date of that value. Each entry shows the full original abstract.
Read by cancer type: Cancer biology（2） · Breast（2） · Lung（1） · Pancreatic（0） · Prostate（0） · ACC（0） · Brain（1） · Ovarian（0） · Endometrial（0） · Gastric（0） · Liver（0） · Kidney（0） · Bladder（0）
Cancer molecular biology and AI
- Abstract
Background: The convergence of multi-omics profiling, radiomics, and advanced machine learning has opened new frontiers in precision oncology.Despite this progress, existing computational frameworks remain static, failing to incorporate evolving patient data or simulate treatment outcomes dynamically.A self-evolving digital twin ecosystem offers a solution by continuously synchronizing patient-specific virtual models with real-world clinical trajectories.Objective: To develop and validate a self-evolving digital twin ecosystem integrating clinical, genomic, transcriptomic, proteomic, radiomic, and pathological data for early cancer detection, disease progression prediction, and personalized treatment optimization across breast, lung, colorectal, and ovarian cancers.Methods: A retrospective multi-center cohort of 400 patients (breast n=120, lung n=100, colorectal n=100, ovarian n=80; age range 25-75 years) was assembled.A six-layer digital twin framework was constructed, incorporating a cross-modal transformer foundation model alongside Random Forest, XGBoost, and Deep Neural Network comparators.Key performance metrics included accuracy, precision, recall, F1-score, and area under the ROC curve (AUC).Virtual clinical trial simulations and feature importance analyses were performed.Results: The foundation model achieved superior performance across all metrics (accuracy 0.921, AUC 0.947) compared with Random Forest (0.812/0.847),XGBoost (0.841/0.879), and Deep Neural Network (0.873/0.906).Tumor stage, TP53 mutation, and EGFR mutation emerged as the most predictive features.Risk stratification identified 148 (37.0%) low-risk, 153 (38.3%) moderate-risk, and 99 (24.8%)high-risk patients.Virtual trial simulation demonstrated a 23.4% improvement in projected progression-free survival for the high-risk subgroup.Conclusion: The self-evolving digital twin ecosystem significantly outperforms conventional machine learning approaches and provides a clinically actionable, adaptive platform for real-time precision oncology decision support across multiple cancer types.
Journal IF-equivalent: 0.0 (OpenAlex 2-year mean citedness, value as of 2026-10-07, retrieved 2026-10-08; not the official Clarivate IF)Reference: [No authors listed]. Self-Evolving Digital Twin Ecosystems for Early Detection and Precision Management of Breast, Lung, Colorectal, and Ovarian Cancers. IJDDT. 2026 Oct 12;16(65s). doi:10.25258/ijddt.16.65s.22.Checked: Abstract only - Abstract
Understanding non-genetic determinants of cell fate is critical for developing and improving cancer therapies, as genetically identical cells can exhibit divergent outcomes under the same treatment conditions. In this work, we present a deep learning approach for cell fate prediction from raw long-term live-cell recordings of cancer cell populations under chemotherapeutic treatment. Our Transformer model is trained to predict cell fate directly from raw image sequences, without relying on predefined morphological or molecular features. Beyond classification, we introduce a comprehensive explainability framework for interpreting the temporal and morphological cues guiding the model’s predictions. We demonstrate that prediction of cell outcomes is possible based on the video only, our model achieves balanced accuracy of 0.94 and an F1-score of 0.93. Attention and masking experiments further indicate that the signal predictive of the cell fate is not uniquely located in the final frames of a cell trajectory, as reliable predictions are possible up to 8 h before the event. Our analysis reveals distinct temporal distribution of predictive information in the mitotic and apoptotic sequences, as well as the role of cell morphology and p53 signaling in determining cell outcomes. Together, these findings demonstrate that attention-based temporal models enable accurate cell fate prediction while providing biologically interpretable insights into non-genetic determinants of cellular decision-making.
Journal IF-equivalent: 4.7 (OpenAlex 2-year mean citedness, value as of 2026-10-13, retrieved 2026-10-14; not the official Clarivate IF)Reference: Bürger F, Dias Gomes M, Granada AE, Moreau N, Bozek K. Understanding cell fate decisions with temporal attention. PLoS Comput Biol. 2026 Oct 12;22(10):e1014813. doi:10.1371/journal.pcbi.1014813.Checked: Abstract only
See all 2 Cancer biology papers →
Breast cancer: treatment, trials and AI
- Abstract
Background: Accurate preoperative assessment of HER2 status is critical for guiding targeted therapy, but conventional biopsy-based methods are invasive and limited by tumor heterogeneity. Mammography is a widely accessible and cost-effective imaging modality routinely performed in the preoperative setting. This study aimed to develop and validate a mammography-based deep learning radiomics model for noninvasive prediction of HER2 expression status in breast cancer.
Methods: A total of 546 breast cancer patients from two centers were retrospectively enrolled: 420 from Center 1 (294 in the training cohort and 126 in the internal validation cohort) and 126 from Center 2 as the external validation cohort. Two classification tasks were defined: Task 1 distinguished HER2-positive from HER2-negative breast cancer, and Task 2 distinguished HER2-low from HER2-zero breast cancer. Radiomic features were extracted using the Visformer architecture. A weighted voting ensemble method was then employed to construct the prediction model, with weights optimized solely within the training cohort using cross-validated AUC. Model performance for both tasks was evaluated using receiver operating characteristic (ROC) curves.
Results: For Task 1 (HER2-positive vs. HER2-negative), the radiomics model achieved AUCs of 0.836, 0.763, and 0.714 in the training, internal validation, and external validation cohorts, respectively. For Task 2 (HER2-low vs. HER2-zero), the corresponding AUCs were 0.890, 0.785, and 0.713. Clinicopathological analysis revealed that histological grade (OR = 2.28), Ki-67 index (OR = 4.71), and BI-RADS category (OR = 2.49) were independent predictors of HER2-positive status, while PR status (OR = 4.48), BI-RADS category (OR = 1.75), and breast density (OR = 0.32) were independent predictors of HER2-low status (all P < 0.05).
Conclusion: The mammography-based deep learning radiomics model demonstrated meaningful discriminative ability for predicting HER2 expression status in breast cancer and may serve as a potential noninvasive adjunct for preoperative HER2 assessment, warranting further prospective validation. Clinical trial number Not applicable.
Journal IF-equivalent: 3.8 (OpenAlex 2-year mean citedness, value as of 2026-10-02, retrieved 2026-10-03; not the official Clarivate IF)Reference: Wang H, Liu C, Zhao Y, Fang Y, Kang Z, Deng L, et al. Mammography-based deep learning radiomics for predicting HER2 expression in breast cancer: a dual-center study with focus on HER2-low status. BMC Med Imaging. 2026 Oct 12 [Epub ahead of print]. doi:10.1186/s12880-026-02921-z.Checked: Abstract only - Abstract
INTRODUCTION: Breast cancer remains a leading cause of cancer incidence and mortality among women worldwide, with ongoing challenges in early detection, accurate diagnosis, prognosis estimation, and treatment-response assessment. Artificial intelligence (AI), including machine learning and deep learning, has rapidly advanced breast cancer research by enabling analysis of high-dimensional imaging, pathological, genomic, and clinical data. However, the rapid expansion of this literature has resulted in substantial fragmentation across clinical tasks, data modalities, algorithmic paradigms, and software ecosystems. This systematic review presents a comprehensive bibliometric analysis of AI-driven breast cancer research published recently. METHODS: Using a multi-database, Scopus and Web of Science, as primary data sources, a systematic bibliometric framework integrating performance analysis, science mapping, and thematic evolution was employed. The analysis is guided by explicit research questions examining: (i) the evolution of AI applications across diagnosis, prognosis, and treatment-response prediction; (ii) the adoption of explainable AI and hyperparameter optimization practices; (iii) the datasets, software frameworks, and algorithms shaping the field; (iv) the role of mammography as a core modality; and (v) emerging research hotspots, including transformer-based architectures. RESULTS AND DISCUSSION: Unlike prior bibliometric studies focused mainly on citation metrics, this work adopts a task-aware, methodologycentric perspective, offering actionable insights to support reproducible, interpretable, and clinically integrated AI systems for breast cancer care.
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: Mohamed YB, ZainEldin H, Eladl SG, Sayed HA, Shehata M, Badawy M, et al. Artificial intelligence in breast cancer research: a systematic review and bibliometric analysis of emerging trends and future directions. Front Oncol. 2026 Sep 28;16:1800218. doi:10.3389/fonc.2026.1800218.Checked: Abstract only
Lung cancer: treatment, trials and AI
- Abstract
Objective: Spread through air spaces (STAS) is an invasive pattern of lung adenocarcinoma associated with increased recurrence risk and poor prognosis. Preoperative identification of STAS may inform surgical strategy selection. This study aimed to develop and validate a fusion model combining CT-based habitat radiomics and deep learning for preoperative prediction of STAS in early-stage lung adenocarcinoma. Materials and methods We retrospectively analyzed 248 patients with stage I lung adenocarcinoma (120 STAS-positive and 128 STAS-negative), comprising a training cohort (173 cases) and a testing cohort (75 cases). CT-based habitat analysis was performed by applying K-means clustering to pooled voxel-level feature vectors from all tumors, yielding four habitat subregions. After feature selection, five model categories were constructed and compared: conventional radiomics, habitat radiomics, multichannel 2D deep learning, 3D deep learning, and a deep learning-habitat fusion model. All models were evaluated using the area under the receiver operating characteristic curve (AUC), calibration curves, and decision curve analysis.
Results: Among the conventional and habitat radiomics models, Habitat H4—one of the four CT-based clustered habitat subregions—achieved the highest testing-cohort AUC at 0.802 (95% CI: 0.700–0.904), outperforming the conventional whole-tumor radiomics model (AUC = 0.739, 95% CI: 0.626–0.853). For the deep learning models, the 3D deep learning model (testing-cohort AUC = 0.815, 95% CI: 0.715–0.915) outperformed the multichannel 2D deep learning model (testing-cohort AUC = 0.747, 95% CI: 0.633–0.862). Among all models, the fusion model combining Habitat H4 and 3D deep learning achieved the highest numerical performance. The AUCs in the training and testing cohorts were 0.913 (95% CI: 0.873–0.953) and 0.824 (95% CI: 0.727–0.920), respectively, and were significantly higher than those of the radiomics model. DeLong test revealed that the fusion model significantly outperformed the conventional radiomics model ( P < 0.05). Decision curve analysis revealed higher clinical net benefit of the fusion model, and calibration curves showed favorable consistency between predicted and actual probabilities.
Conclusion: The fusion of habitat radiomics and 3D deep-learning features showed favorable performance for noninvasive preoperative prediction of STAS in early-stage lung adenocarcinoma, with the two feature representations providing potential complementary value. This model may aid preoperative risk stratification, but its role in surgical decision-making requires further validation in external and prospective studies.
Journal IF-equivalent: 3.8 (OpenAlex 2-year mean citedness, value as of 2026-10-02, retrieved 2026-10-03; not the official Clarivate IF)Reference: Liu X, Wu L, Li L, Rao Z, Su R, Xu F, et al. CT-based habitat radiomics and deep learning for preoperative prediction of spread through air spaces in early-stage lung adenocarcinoma. BMC Med Imaging. 2026 Oct 12 [Epub ahead of print]. doi:10.1186/s12880-026-02892-1.Checked: Abstract only
Pancreatic cancer: treatment, trials and AI
No new qualifying paper for this issue.
Prostate cancer: treatment, trials and AI
No new qualifying paper for this issue.
Adenoid cystic carcinoma: treatment, trials and AI
No new qualifying paper for this issue.
Brain tumours: treatment, trials and AI
- Abstract
Background: Accurate and timely classification is essential for brain tumor treatment planning. Classical machine learning (ML) with handcrafted features on moderate-sized datasets is under-represented, despite deep learning (DL) dominating medical image analysis.
Purpose: This study proposes a paradigm-agnostic comparison of classical ML and DL for brain tumor classification using a novel multi-domain feature framework, identifying which paradigm best balances accuracy, efficiency, and clinical use.
Methods: The Kaggle Brain Tumor magnetic resonance imaging (MRI) dataset (7,023 images; Glioma 1,621, Meningioma 1,645, No Tumor 2,000, Pituitary 1,757) was used. Nine feature domains—Gabor filters, local binary patterns (LBP), gray-level co-occurrence matrix (GLCM), discrete wavelet transform (DWT), discrete cosine transform (DCT), morphological, statistical, gradient, intensity gave 289 features, reduced to 150 by SelectKBest with the analysis of variance (ANOVA) F-test. Sixteen models were tested: 8 ML (Support Vector Machine with Radial Basis Function kernel (SVM-RBF), Random Forest, Gradient Boosting, Extra Trees, AdaBoost, K-Nearest Neighbors, Logistic Regression, Linear Discriminant Analysis) and 8 DL (Deep Multilayer Perceptron (Deep MLP), 1-Dimensional Convolutional Neural Network (1D-CNN), Bidirectional Long Short-Term Memory (Bi-LSTM), Gated Recurrent Unit (GRU), Convolutional Neural Network–Long Short-Term Memory (CNN-LSTM), ResNet-inspired, DenseNet-inspired, Autoencoder). The Wilcoxon signed-rank test assessed significance. Shapley Additive explanations (SHAP), Local Interpretable Model-agnostic Explanations (LIME), single-domain, progressive, leave-one-out (LOO) ablations, data-size sensitivity, and ImageNet transfer-learning comparisons were performed.
Results: SVM-RBF achieved 96.80 ± 0.68% accuracy, 96.73% precision, 96.63% recall, 96.65% F1, 99.63% Receiver Operating Characteristic Area Under the Curve (ROC-AUC), Cohen’s Kappa 0.957, Matthews Correlation Coefficient 0.957, outperforming all 8 DL models ( p ≤ 0.0039). DenseNet- and ResNet-inspired, trained on the same handcrafted features, reached 94.86 ± 0.76% and 93.95 ± 0.82%. The ML mean (92.78 ± 3.06%) exceeded the DL mean (89.92 ± 4.50%, p = 0.0020), with shorter training (21.12s vs . 166.62s, p = 0.0020). Per-class recall ranged 93.2–99.0%. Gabor was the most influential domain (single-domain 94.85%; SHAP 0.122; LOO drop −1.25%, p < 0.001).
Conclusions: Classical ML with multi-domain handcrafted features outperformed all 8 DL architectures with shorter training time, challenging DL’s assumed universality in medical imaging. The framework also raised DL accuracy by 1–16 percentage points over raw-image transfer learning, showing engineered features benefit both paradigms. With strong interpretability (SHAP, LIME) and low computational needs, the approach suits clinical deployment in resource-limited settings.
Journal IF-equivalent: 4.8 (OpenAlex 2-year mean citedness, value as of 2026-10-13, retrieved 2026-10-14; not the official Clarivate IF)Reference: Sethuraman R, Pandiarajan GS, Sadagopan P. Challenging deep learning universality: a complete evaluation of conventional machine learning and deep learning in classifying brain tumors using magnetic resonance imaging. PeerJ Computer Science. 2026 Oct 12;12:e4106. doi:10.7717/peerj-cs.4106.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
No new qualifying paper for this issue.
Kidney cancer: treatment, trials and AI
No new qualifying paper for this issue.
Bladder cancer: treatment, trials and AI
No new qualifying paper for this issue.