AI and Cancer Research ── Cancer biology ── 2026-10-30
Cancer molecular biology and AI
- Abstract
Barrett's esophagus (BE) patients require improved cancer risk stratification to identify high-risk individuals while reducing over-treatment in low-risk populations. BE evolution towards adenocarcinoma is likely driven by a combination of genomic and microenvironmental factors, suggesting the potential of predictive models that integrate both. Here, we developed BEACON (Barrett’s Esophagus DNA content Abnormality and immune ecology for Cancer Outcome), a spatially aware framework integrating deep learning-based prediction of DNA content and immune architecture from routine histopathology. First, DACOR, a multi-instance learning model that predicts DNA content from histopathology, was trained using 777 BE biopsies with flow cytometry-based DNA content data scanned at two institutions, and it demonstrated strong performance across both validation and test datasets for DNA content abnormality prediction. Patients classified as DNA content abnormal by DACOR demonstrated increased cancer progression. Complementary models for cell classification and tissue segmentation enabled spatial immune ecology metric computations. Abnormal regions exhibited increased lymphoplasmacytic inflammation versus normal regions. Among patients with DNA content abnormality, cancer progressors exhibited increased plasma cell clustering adjacent to abnormal epithelium compared to non-progressors. Finally, a logistic regression model was developed that integrated molecular, immune ecological, and epithelial morphology features for cancer risk stratification. The integrated risk classification model stratified DNA content abnormal patients into high- and low-risk groups that corresponded with progression and patient survival. Overall, BEACON spatially integrates molecular abnormality with immune ecology to stratify BE patients by cancer progression risk using routine pathology images.
Journal IF-equivalent: 0.6 (OpenAlex 2-year mean citedness, value as of 2026-10-28, retrieved 2026-10-29; not the official Clarivate IF)Reference: Ercan C, Pan X, Paulson TG, Stachler MD, Göknur Akarca F, Grady WM, et al. Histopathology-Based Spatial Profiling of Immune and Molecular Features Predicts Cancer Risk in Barrett’s Esophagus Patients. Cancer Res. 2026 Oct 27 [Epub ahead of print]. doi:10.1158/0008-5472.can-26-1476. PMID: 42944677.Checked: Abstract only - Abstract
OBJECTIVE: To develop and validate a noninvasive model for classifying T stage in gastrointestinal malignancies using circulating tumor cells (CTCs) and serum tumor markers and to compare the predictive value of CTCs with that of conventional tumor markers. METHODS: This retrospective study included 328 patients with gastrointestinal malignancies from two hospitals in the same region. The internal modelling cohort comprised 214 patients (T1 + T2, n = 49; T3 + T4, n = 165), and the independent validation cohort comprised 114 patients (T1 + T2, n = 55; T3 + T4, n = 59). Univariable and multivariable logistic regression analyses were used to identify stage-related factors associated with CTCs. Three-dimensional-matched feature sets were constructed to minimize bias from unequal feature numbers. Repeated stratified fivefold cross-validation, the foldwise synthetic minority oversampling technique, and weighted cross-entropy loss were used to address severe class imbalance. Model performance was evaluated using AUC, balanced accuracy, F1 score, and calibration metrics rather than overall accuracy. Logistic regression, decision tree, support vector machine, k-nearest neighbors, and the newly developed CTC-AttnNet were compared. K‒M and Cox analyses were performed as exploratory recurrence analyses. RESULTS: CTC count alone moderately discriminated the overall TNM stage (AUC = 0.742) but poorly discriminated the T stage (AUC = 0.595); the AUCs of all four conventional tumor markers were < 0.60. Advanced overall TNM stage was independently associated with CTC positivity (OR = 1.844, 95% CI: 1.255-2.710; P = 0.002). Under dimension-matched conditions, the CTC-containing feature set achieved an external validation AUC of 0.76, outperforming the dimension-reduced conventional marker combination (AUC = 0.65). CTC-AttnNet achieved an external validation AUC of 0.82, a balanced accuracy of 0.78, and an F1 score of 0.76. Ablation analysis revealed that the attention module improved the recognition of minority class T1 + T2 cases. CTC positivity was also independently associated with recurrence (HR = 5.263, 95% CI 1.637-16.927; P = 0.005). CONCLUSION: CTCs were significantly associated with gastrointestinal tumor stage and postoperative recurrence. Multivariable CTC-based models discriminated T stage better than models based on four conventional serum tumor markers did, although the CTC count alone had limited discriminatory ability. CTC-AttnNet represents an exploratory noninvasive stratification tool for this retrospective regional cohort and provides a methodological framework for developing liquid biopsy prediction models.
Journal IF-equivalent: 2.7 (OpenAlex 2-year mean citedness, value as of 2026-10-12, retrieved 2026-10-13; not the official Clarivate IF)Reference: Li L, Sun C, Wang S, Qiang H, Liu Z, Wang H, et al. CTC-AttnNet: development and validation of an attention-based neural network for staging gastrointestinal malignancies. World J Surg Oncol. 2026 Aug 1;24(1):409. doi:10.1186/s12957-026-04530-0. PMID: 42947149.Checked: Abstract only