AI and Cancer Research ── 2026-10-06
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（0） · Breast（1） · Lung（1） · Pancreatic（0） · Prostate（0） · ACC（0） · Brain（1） · Ovarian（0） · Endometrial（0） · Gastric（0） · Liver（1） · Kidney（0） · Bladder（0）
Cancer molecular biology and AI
No new qualifying paper for this issue.
Breast cancer: treatment, trials and AI
- Abstract
Background and objective The accurate classification of human epidermal growth factor receptor 2 (HER2) status is very important for the diagnosis and treatment of breast cancer. However, the biopsy, the current gold standard for differentiating HER2 status, is invasive and time-consuming. To overcome these drawbacks, a novel deep learning model was developed to differentiate HER2-negative and HER2-positive status in breast cancer solely based on diffusion-weighted imaging (DWI). Materials and methods This retrospective study included 239 women patients confirmed with breast cancer from two local medical centers. A hybrid CNN-Transformer DL model was proposed, which took DWI images (the ADC maps, DWI images with b = 0 s/mm² and b = 800 s/mm²) as inputs and output the classification of HER2-negative and HER2-positive status. Classification by the proposed DL model was quantitatively compared to the classification by the other benchmark DL models and two clinical experts.
Results: Data of the 239 patients (mean age, 49.4 ± 10.0 years) were separated into a training set (n = 156), an internal test set (n = 39), and an external test set (n = 44). On the internal test set, the proposed DL model performed numerically better than the best benchmark DL model (area under the curve [AUC]: 0.93 vs. 0.89; accuracy: 0.90 vs. 0.85). On the external test set, the proposed model also performed numerically better than the best benchmark model (AUC: 0.91 vs. 0.87; accuracy: 0.84 vs. 0.82), and significantly better than the two clinical experts (AUC: 0.91 vs. 0.65 vs. 0.63; accuracy: 0.84 vs. 0.61 vs. 0.57).
Conclusion: This study demonstrates the promise of combining DWI and DL for the classification of HER2 status in breast cancer, and it may potentially serve as a non-invasive adjunct or decision-support tool.
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: Zhang Y, Kan X, Wang J, Peng J, Cai J, Ma Y, et al. Deep learning-based prediction of HER2 status from breast diffusion-weighted MRI. Front Oncol. 2026 Oct 5;16:1863720. doi:10.3389/fonc.2026.1863720.Checked: Abstract only
Lung cancer: treatment, trials and AI
- Abstract
This record contains the data and code supporting the systematic review and meta-analysis "Incremental value of integrating histopathology with omics for prediction in non-small-cell lung cancer: a systematic review and meta-analysis" (submitted to Briefings in Bioinformatics). The review followed PRISMA 2020. PubMed, Scopus and IEEE Xplore were searched; of 5504 records, 35 studies using artificial intelligence to integrate histological imaging with genomic, transcriptomic, proteomic or epigenomic data in non-small-cell lung cancer (NSCLC) were included, and 16 contributed to meta-analyses. The primary outcome was the within-study difference in discrimination (AUC or C-index) between multimodal models and the strongest histology-only comparator evaluated on the same patients, pooled with restricted maximum-likelihood random-effects models and Hartung–Knapp–Sidik–Jonkman confidence intervals. Contents:1. Extraction dataset: 35 included studies × 32 fields (bibliographic data, cohorts, modalities, architectures, fusion strategy, validation design, endpoints and all reported performance estimates).2. Analysis dataset: every value entering a meta-analysis, with its source location (table, figure or page) in the original article and the derived standard errors.3. Risk-of-bias assessments: PROBAST with PROBAST-AI signalling questions for all 35 studies.4. Analysis code (Python 3.11, NumPy, SciPy): REML random-effects meta-analysis with HKSJ confidence intervals, prediction intervals, subgroup analyses, meta-regression, sensitivity and leave-one-out analyses, and Egger's test. The code reproduces the reference outputs of the R metafor package on the BCG benchmark dataset.5.
Results: (JSON) and figure-generation scripts. The included articles themselves are not redistributed; they remain subject to their original licences.
Journal IF: unknown (could not be matched)Reference: [No authors listed]. Extraction dataset, risk-of-bias assessments and analysis code for Incremental value of integrating histopathology with omics for prediction in non-small-cell lung cancer: a systematic review and meta-analysis. Zenodo (CERN European Organization for Nuclear Research). [Epub ahead of print]. doi:10.5281/zenodo.23132027.Checked: Abstract only
Pancreatic cancer: treatment, trials and AI
No new qualifying paper for this issue.
Prostate cancer: treatment, trials and AI
No new qualifying paper for this issue.
Adenoid cystic carcinoma: treatment, trials and AI
No new qualifying paper for this issue.
Brain tumours: treatment, trials and AI
- Abstract
Glioblastoma (GB) is the most aggressive primary brain tumor, characterized by a poor prognosis, limited response to therapy, and high rates of recurrence. Early therapeutic response assessment is challenging due to phenomena such as pseudoresponse and pseudoprogression. This study explores the potential of advanced machine learning (ML) strategies to predict long-term therapy outcomes using longitudinal T2weighted Magnetic Resonance Imaging (MRI) data from a preclinical GL261 glioblastoma mouse model, acquired prior and during treatment. We compare two distinct approaches: a classical pipeline based on radiomic features coupled with an XGBoost classifier, and a deep learning (DL) pipeline using a fine-tuned EfficientNetB0 model. Our results demonstrate that while the radiomics approach identifies interpretable imaging biomarkers and achieves good predictive performance (AUC ≈ 0.770, 95% CI 0.703–0.832), the DL-based model outperforms it across most evaluation metrics, reaching an AUC of 0.868 (95% CI 0.810– 0.918) and a sensitivity of 0.818. The DL model shows better generalization across individual subjects, and the discriminative performance improves progressively throughout the follow-up period for both approaches. Interpretability analysis via Grad-CAM confirms that the DL model’s predictions are driven by anatomically relevant features. These findings suggest that DL, enhanced by transfer learning, has the potential to serve as a powerful non-invasive tool for the early prediction of treatment efficacy in glioblastoma, paving the way for more robust and personalized therapy monitoring.
Journal IF-equivalent: 5.2 (OpenAlex 2-year mean citedness, value as of 2026-10-04, retrieved 2026-10-05; not the official Clarivate IF)Reference: González J, Candiota AP, Vellido A. Advanced machine learning strategies for predicting therapy response in preclinical glioblastoma using longitudinal MRI. Sci Rep. 2026 Oct 4 [Epub ahead of print]. doi:10.1038/s41598-026-73929-2.Checked: Abstract only
Ovarian cancer: treatment, trials and AI
No new qualifying paper for this issue.
Endometrial cancer: treatment, trials and AI
No new qualifying paper for this issue.
Gastric cancer: treatment, trials and AI
No new qualifying paper for this issue.
Liver cancer: treatment, trials and AI
- Abstract
BACKGROUND: During radiation therapy, liver tumor motion can reduce dose delivery accuracy and increase irradiation of adjacent healthy tissues. Because liver tumors are difficult to visualize directly on kilovoltage (kV) X-ray images, fiducial markers are commonly implanted as surrogates for tumor position during treatment. Conventional marker-segmentation approaches such as template matching can lose accuracy when markers are obscured by bone, surgical clips, or stents. Although Convolutional Neural Network (CNN)-based approaches have shown strong performance for image analysis, their application has been constrained to more static organs such as the prostate or has used single-center and vendor-specific datasets, limiting assessment of model transportability across different institutions and anatomic sites. PURPOSE: The aim of this study was to develop, integrate, and evaluate a CNN-based method for fiducial marker detection in kV X-ray images to support real-time image-guided radiation therapy (IGRT) during liver radiotherapy using a multi-institutional, multi-platform dataset spanning both large and fast free-breathing motion and slow and small breath-hold motion. METHODS: A compact Convolutional Neural Network (CNN) was trained on 314,625 kilovoltage (kV) X-ray images encompassing 28 patients from the multi-institutional TROG 17.03 LARK clinical trial (NCT02984566). The model was validated using a hold-out set of 31,463 images (10%) from the same cohort of 12 patients and 55 treatment fractions, spanning three centers and three respiratory motion-management techniques. The CNN was tested on 4184 images from 16 patients and 55 fractions across three centers and three motion-management techniques. The ground truth for testing was manually segmented marker positions from every 10 degrees of gantry rotation for each fraction of each test patient. Based on AAPM guidelines (TG147 and TGB135.B), feasibility for clinical implementation was predefined as > 95% of marker positions being within 2 mm of the ground truth position in each dimension, and processing time less than 150 ms per image using a simulated real-time Kilovoltage Intrafraction Monitoring (KIM) framework. Additional evaluation metrics included sensitivity, specificity, and the area under the precision-recall curve (AUC). RESULTS: For the unseen test patient data, the marker position was segmented by the CNN within 2 mm in 95.4% of frames on the X axis and 97.6% of frames on the Y axis, meeting AAPM criteria. Sensitivity reached 97.76%, specificity was 99.94%, and the AUC was 0.9964. No statistically significant difference in localization error was observed between breath-hold and free-breathing treatments, although this comparison was limited by the small number of free-breathing patients. Localization error differed significantly between Varian and Elekta linacs due to imbalance within the dataset. The processing time for each image was 50-60 ms using a NVIDIA GeForce RTX 3070 GPU. CONCLUSION: A CNN-based method for fiducial marker detection in the liver was developed and evaluated on multi-institutional kV X-ray images spanning free-breathing and breath-hold motion, as well as Varian and Elekta linac platforms. The method satisfied the predefined feasibility criteria for positional accuracy and computation time, supporting future translation toward clinical implementation.
Journal IF-equivalent: 2.9 (OpenAlex 2-year mean citedness, value as of 2026-10-05, retrieved 2026-10-06; not the official Clarivate IF)Reference: Kan F, Jin F, Mylonas A, Zwan B, Nguyen T, Moodie T, et al. Deep learning‐based CNN method for fiducial marker detection in kilovoltage X‐ray images for liver tumor motion monitoring. Med Phys. 2026 Oct 4;53(10):e70691. doi:10.1002/mp.70691. PMID: 42830534.Checked: Abstract only
Kidney cancer: treatment, trials and AI
No new qualifying paper for this issue.
Bladder cancer: treatment, trials and AI
No new qualifying paper for this issue.