# Measurement of Intratumor Heterogeneity and Its Changing Pattern to Predict Response and Recurrence Risk After Neoadjuvant Chemotherapy in Breast Cancer

## TL;DR

This study uses MRI to measure tumor heterogeneity in breast cancer to predict treatment response and recurrence risk after chemotherapy.

## Contribution

A novel model combining MRI-based tumor heterogeneity and clinical data improves prediction of chemotherapy response and recurrence risk.

## Key findings

- Lower MRI heterogeneity was independently associated with achieving a pathological complete response (pCR).
- The model combining heterogeneity and clinical features improved specificity and accuracy in predicting pCR.
- Patients with rising heterogeneity during treatment had the worst survival outcomes and higher recurrence risk.

## Abstract

The heterogeneity of breast tumors might reflect biological complexity and provide prediction clues for the sensitivity of treatment. This study aimed to construct a model based on tumor heterogeneity in magnetic resonance imaging (MRI) for predicting the pathological complete response (pCR) to neoadjuvant chemotherapy (NAC). This retrospective study involved 217 patients with biopsy-confirmed invasive breast cancer who underwent MR before and after NAC. Patients were randomly divided into the training cohort and the validation cohort at a 1:1 ratio. MR images were processed by algorithms to quantify the heterogeneity of tumors. Models incorporating heterogeneity and clinical characteristics were constructed to predict pCR. The patterns of heterogeneity variation during NAC were classified into four categories abbreviated as the heterogeneity high-keep group (H_keep group), heterogeneity low-keep group (L_keep group), heterogeneity rising group, and decrease group. The average heterogeneity in patients achieving pCR was significantly lower than in those who did not (p = 0.029). Lower heterogeneity was independently associated with pCR (OR, 0.401 [95%CI: 0.21, 0.76]; p = 0.007). The model combining heterogeneity and clinical characteristics demonstrated improved specificity (True Negative Rate 0.857 vs. 0.698) and accuracy (Accuracy 0.828 vs. 0.753) compared to the clinical model. Survival outcomes were best for the L_keep group and worst for the rising group (Log-rank p = 0.031). Patients with increased heterogeneity exhibited a higher risk of recurrence approaching two years post-surgery, particularly within the non-pCR population. The quantified heterogeneity of breast cancer in MRI offers a non-invasive method for predicting pCR to NAC and evaluating the implementation of precision medicine.