Background: To develop an AI-based predictive model for neoadjuvant therapy (NAT) efficacy in breast cancer, we integrated multimodal data and analyzed tumor microenvironment (TME) features to provide interpretability. Methods: We retrospectively analyzed H&E-stained whole-slide images (WSIs) from a multicenter cohort of breast cancer patients receiving NAT to develop an AI predictive model. The cohort was stratified into training, test, internal validation, and external validation sets. Feature extraction used UNI and classification employed a multiple instance learning (MIL) framework. Model performance was evaluated via ROC curve analysis (AUC, precision, specificity, recall). Molecular mechanisms underlying model predictions were explored using TCGA multimodal data, integrating differential gene expression profiling with pathway enrichment analysis (GO, KEGG). TME component correlations with model scores were also investigated. Results: The AI model demonstrated robust discriminative capacity across three residual cancer burden (RCB)-based classification tasks in 826 patients from two centers, achieving peak performance in subtask 2 (NAT-sensitive: RCB 0–1 vs. NAT-resistant: RCB 2–3). For subtask 2, AUCs were 0.901 (training), 0.858 (test), 0.808 (internal validation), and 0.819 (external validation). Molecular analysis linked the model’s predictive efficacy to tumor cell cycle processes. TME analysis revealed positive correlations between model scores and activated immune cells (M0/M1 macrophages, dendritic cells), and negative correlations with inhibitory cells (M2 macrophages, resting mast cells). Crucially, the model’s predictive scores were closely related to tumor-infiltrating lymphocytes (TILs), with spatial colocalization observed between classification weights and TILs distribution. Significant differences in TILs levels occurred across model score strata, validating the model’s biological plausibility in predicting NAT response mechanisms. Conclusion: We developed an interpretable AI model that predicts response to neoadjuvant therapy in breast cancer using H&E slides. The model’s predictions are biologically interpretable, correlating with TME dynamics and spatial TIL patterns, offering a novel strategy for personalizing NAT treatment strategies.
24 September 2025 in Journal of Translational Medicine
Owing to the complexity of TME components and the heterogeneity of cancer cells, the relationship between the niches of TME and prognosis in breast ductal carcinoma remains unknown. The staged characteristics of corresponding cancer cell behaviors are unclear. Our study aims to reveal spatial structures and specific cellular information of TME and cancer cells subgroups during the progression from DCIS to IDC and lymph node metastasis. Single-cell sequencing, spatial transcriptomics, bulk RNA sequencing datasets were used to explore the changes in microenvironmental components and transcriptional programs of tumor cells during the progression of breast ductal carcinoma. Immunohistochemistry, multiplex immunofluorescence, flow cytometry cell cycle detection, invasion migration experiments, and WB imprinting were employed for validation. Analysis of TME cell type subsets revealed the accumulation of TEX, iTreg, and stress-phenotype TAM in the mammary gland in situ during the invasion process. Lymphatic metastases exhibited enrichment of nTregs and a more naïve-like CD8 T cell population. Spatial analysis and survival analysis showed that the spatial niches of CD4 TN and phagocytic-phenotype macrophages were associated with a favorable prognosis, and these niches were lost during disease progression. The proliferative subpopulation of breast ductal carcinoma was enriched in lymphatic metastatic tissues, expressing high levels of FAM111B and exhibiting intense TCA and oxidative phosphorylation metabolism. Silencing FAM111B led to cell cycle arrest, decreased invasion and migration abilities, and downregulation of core mediator genes for cuproptosis and disulfidptosis. The stage-specific microenvironmental characteristics of breast ductal carcinoma correspond to some extent to the behavior of tumor cells. During the progression of ductal carcinoma in breast tissue, the establishment of an immunosuppressive microenvironment occurs. The microenvironmental spectrum at lymph node metastases differs somewhat, corresponding to a more enriched turnover of cancer cell proliferation and death. Inhibitors of FAM111B and inducers of cuproptosis and disulfidptosis may serve as potential therapeutic targets for proliferative subgroups.
Background: Conventional histopathological assessment of residual cancer burden (RCB) following neoadjuvant therapy for breast cancer relies on manual visual evaluation, lacking objective quantification of spatial interactions among tumor, necrosis, and lymphocyte compartments. This limits prognostic accuracy and impedes personalized treatment stratification. Methods: We developed an explainable AI framework to segment three tissue compartments from H&E patches and constructed 11 spatial pathological features. This two-center study included 347 post-neoadjuvant patients (182 development, 165 external validation) plus 843 TCGA-BRCA cases for exploratory external validation. VGG-16, ResNet-50, and ViT-Base were evaluated; multiple instance learning identified target regions for feature construction. Six machine learning models with LASSO-selected features were interpreted via SHAP and Grad-CAM, with TCGA-BRCA serving as an exploratory external cohort. Results: VGG-16 achieved optimal segmentation (all AUCs > 0.90). In the external validation set, XGBoost achieved AUCs of 0.781 for Task 1 (RCB-0 vs. RCB-1+2+3) and 0.896 for Task 2 (RCB-0+1 vs. RCB-2+3). For Task 3 (RCB-0+1+2 vs. RCB-3), the model achieved an AUC of 1.000, with complete separation between groups. SHAP analysis revealed that the Necrotic Tumor Mixed Cluster (T+N) was the dominant indicator for Task 1 (mean |SHAP| = 0.439) and Task 2 (mean |SHAP| = 0.803), while the Pure Necrotic-Rich Zone (N-only) was the dominant indicator for Task 3 (mean |SHAP| = 1.967). In exploratory TCGA association analyses, the Pure Tumor-Rich Zone (T-only) exhibited a positive correlation (ρ = 0.706, p < 0.001; T-only is a feature used to derive this model-estimated RCB-like score), whereas the Lymphocyte-Infiltrated Necrotic Zone (N+L) showed a negative correlation (ρ = −0.407, p < 0.001) with the model-estimated RCB-like score, linking tumor-rich zones to immunosuppression and lymphocyte-infiltrated necrotic zones to immune activation. Conclusions: Our spatial pathological features effectively estimate RCB, with T+N and N-only as the predominant SHAP-identified indicators across the three tasks. Exploratory analyses further suggest that tumor-rich and lymphocyte-infiltrated necrotic zones correlate with opposing immune phenotypes, supporting personalized breast cancer management.