# MR‐DELTAnet: A Longitudinal MRI‐Transformer Model Predicting Pathological Complete Response and Revealing Immune Microenvironment via scRNA‐seq in Locally Advanced Rectal Cancer

## TL;DR

MR-DELTAnet is an MRI-based model that predicts treatment response in rectal cancer patients and identifies immune microenvironment differences using single-cell RNA sequencing.

## Contribution

MR-DELTAnet introduces a novel longitudinal MRI-Transformer model for predicting pathological complete response and revealing immune microenvironment patterns in rectal cancer.

## Key findings

- MR-DELTAnet achieved high AUC scores (0.93-0.90) in predicting pathological complete response across multiple datasets.
- High-score tumors are myeloid-rich and immunosuppressive, while low-score tumors are cytotoxic T-cell-dominant.
- MR-DELTAnet enables non-invasive risk stratification with significant survival differences between low- and high-score patients.

## Abstract

Accurate tumor response assessment to neoadjuvant chemoradiotherapy (NCRT) is crucial for personalized treatment strategies in locally advanced rectal cancer (LARC). However, reliable non‐invasive assessment tool remains clinically lacking. To fill this unmet need, MR‐DELTAnet, a longitudinal MRI‐based Transformer framework that integrates Delta‐Efficient Latent‐Temporal Attention, is constructed to predict pathological complete response (pCR) to NCRT in locally advanced rectal cancer patients. In a multicenter retrospective cohort of 1,026 LARC patients between July 2012 and July 2023, MR‐DELTAnet demonstrated robust discriminative performance across independent datasets, with the area under the curves (AUC) of 0.93 (95% CI 0.90‐0.96), 0.88 (95% CI 0.82‐0.94) and 0.90 (95% CI 0.79‐1.00) and in training (n═633), internal validation (n═212) and external validation (n═181) sets, respectively. Risk‐stratification by MR‐DELTAnet prediction scores reveals significant survival differences: low‐score patients exhibit prolonged disease‐free and overall survival versus high‐score patients (log‐rank p<0.05). Applying the model to an independent single‐cell RNA sequencing cohort (n═26) discloses biologically distinct immune microenvironments: high‐score tumors are myeloid‐rich and immunosuppressive, whereas low‐score tumors harbor cytotoxic T‐cell‐dominant. Clinically, MR‐DELTAnet provides an accurate, non‐invasive tool for preoperative identification of pCR likelihood and biological phenotype, thereby potentially informing individualized treatment strategies for LARC management.

The MR‐DELTAnet model utilizes longitudinal MRI to predict treatment response after neoadjuvant chemoradiotherapy in locally rectal cancer patients, accurately identifying patients likely to achieve pathological complete response for personalized management. Single‐cell RNA sequencing analysis reveals distinct immune microenvironments underlying model prediction: high‐score tumors are myeloid‐rich and immunosuppressive, whereas low‐score tumors harbor cytotoxic T‐cell‐dominant, elucidating the biological basis of its efficacy.