Deep Learning-Based Multimodal Prediction of Neoadjuvant Chemotherapy Response in Locally Advanced Rectal Cancer by...

Locally advanced rectal cancer (LARC) exhibits significant heterogeneity in response to neoadjuvant chemotherapy (NAC), with poor responders facing delayed treatment and unnecessary toxicity. Although magnetic resonance imaging (MRI) provides spatial pathophysiological information and proteomics reveals molecular mechanisms, current single-modal approaches cannot integrate these complementary perspectives, resulting in limited predictive accuracy and biological insight.

This retrospective study developed a multimodal deep learning framework using a cohort of 274 LARC patients treated with NAC (2012-2021). Graph neural networks analyzed proteomic profiles from formalin-fixed paraffin-embedded tissues, incorporating Kyoto Encyclopedia of Genes and Genomes/gene ontology pathways and protein-protein interaction networks, while a spatially enhanced 3D ResNet152 processed T2-weighted imaging. A LightGBM classifier integrated both modalities with clinical features using zero-imputation for missing data. Model performance was assessed through area under the receiver operating characteristic curve (AUC)-receiver operating characteristic, decision curve analysis, and interpretability techniques (SHAP and Grad-CAM).

The integrated model achieved superior NAC response prediction (test AUC 0.828, sensitivity 0.875, specificity 0.750), significantly outperforming single-modal approaches (MRI ΔAUC +0.109; proteomics ΔAUC +0.125). SHAP analysis revealed MRI-derived features contributed 57.7% of predictive power, primarily through peritumoral stromal heterogeneity quantification. Proteomics identified 10 key chemoresistance proteins, including CYBA, GUSB, ATP6AP2, DYNC1I2, DAD1, ACOX1, COPG1, FBP1, DHRS7, and SSR3. Decision curve analysis confirmed clinical utility across threshold probabilities (0-0.75).

Our study established a novel MRI-proteomics integration framework for NAC response prediction, with MRI defining spatial resistance patterns and proteomics deciphering molecular drivers, enabling early organ preservation strategies. The zero-imputation design ensured deployability in diverse clinical settings.