Related Experiment Video
Updated: Jun 20, 2026
Polymalic Acid-based Nano Biopolymers for Targeting of Multiple Tumor Markers: An Opportunity for Personalized Medicine?
Published on: June 13, 2014
Spatially interpretable artificial intelligence framework to tailored neoadjuvant dual HER2 blockade in HER2-positive
Xiang-Rong Wu1,2, Hong Lv2,3, Shen Zhao1,2
1Department of Breast Surgery, Key Laboratory of Breast Cancer in Shanghai, Fudan University Shanghai Cancer Center, Shanghai, 200032, China.
Abstract:
Neoadjuvant dual HER2 blockade with trastuzumab and pertuzumab plus chemotherapy represents the current standard-of-care for HER2-positive breast cancer. However, treatment responses remain heterogeneous, underscoring the lack of clinically practical tools for predicting treatment efficacy and informing personalized therapy. Here, we developed HER2-LADDER (Layered AI-based Dual-targeteD anti-HER2 Recommendation), a spatially interpretable and clinically accessible artificial intelligence framework that integrates clinicopathological and spatial topological features from routine hematoxylin and eosin (H&E) and HER2 immunohistochemistry (IHC) slides. Using these spatially derived features, HER2-LADDER accurately predicted response to neoadjuvant TCbHP/PCbHP, achieving AUCs of 0.944 in the model construction cohort (N = 276), 0.917 in the temporal validation cohort (N = 82), and 0.869 in the trial-based validation cohort (N = 85). On the basis of HER2-LADDER scores, patients were stratified into Low (highly responsive), Medium (responsive), and High (resistant) groups, identifying candidates for treatment de-escalation (THP or TCbH/PCbH), standard-of-care (TCbHP/PCbHP), or alternative regimens (e.g., next-generation anti-HER2 antibody-drug conjugates), respectively. Importantly, Xenium in situ profiling further revealed biological correlates underlying model predictions, including HER2-enriched tumor cell aggregation and neutrophil-helper T-cell interactions, thereby highlighting the mechanistic interpretability of the model. Collectively, HER2-LADDER unites digital pathology and high-resolution spatial profiling into a clinically accessible AI framework, offering a robust, transparent, and biologically grounded tool to tailor individualized HER2-targeted therapy optimization.
Insights
A new AI tool, HER2-LADDER, predicts response to HER2-targeted breast cancer therapy using digital pathology images. This enables personalized treatment strategies, improving outcomes for patients with HER2-positive breast cancer.
Area of Science:
- Oncology
- Artificial Intelligence
- Digital Pathology
Background:
- Neoadjuvant dual HER2 blockade (trastuzumab and pertuzumab) is standard for HER2-positive breast cancer.
- Treatment response is heterogeneous, lacking tools for personalized therapy prediction.
Purpose of the Study:
- To develop HER2-LADDER, an AI framework for predicting response to neoadjuvant HER2-targeted therapy.
- To integrate clinicopathological and spatial features from H&E and HER2 IHC slides for accurate prediction.
Main Methods:
- Developed HER2-LADDER, an AI framework using spatial features from H&E and HER2 IHC slides.
- Validated the model on three independent cohorts (N=276, N=82, N=85), achieving high AUCs (0.944, 0.917, 0.869).
- Utilized Xenium in situ profiling to explore biological correlates of model predictions.
Main Results:
- HER2-LADDER accurately predicted treatment response to neoadjuvant TCbHP/PCbHP.
- Patients were stratified into Low, Medium, and High response groups, guiding treatment de-escalation or intensification.
- Identified biological correlates like HER2-enriched tumor cell aggregation and immune cell interactions.
Conclusions:
- HER2-LADDER is a clinically accessible AI tool for predicting HER2-targeted therapy response in breast cancer.
- The framework offers a robust, transparent, and biologically grounded approach for personalized treatment optimization.
- Unites digital pathology and spatial profiling for tailored HER2-targeted therapy.
