What type of study is this?

This is a Quantitative Study study.

September 17, 2025

Deep learning-based prediction of response to neoadjuvant immunochemotherapy in triple-negative breast cancer based on pretreatment DCE-MRI

Key Points

The model achieved an average AUC of 0.63 in predicting treatment response.
Deep learning leverages DCE-MRI data from 100 patients with triple-negative breast cancer.
This approach to prediction may enhance individualized treatment strategies.
Initial findings indicate potential but are limited by a small sample size.

Abstract

Motivation: Accurate prediction of the response to neoadjuvant immunochemotherapy (NICT) in triple negative breast cancer (TNBC) is valuable in guiding individualized treatment. Goal(s): To develop a deep learning-based model to predict response before the initiation of NICT. Approach: Our deep-learning model used pretreatment DCE-MRI from 100 TNBC patients. Results: Although preliminary and limited by a small patient number, our model yielded an average AUC of 0.63 in predicting the response to NICT in an independent testing. Impact: A deep learning model has the potential to predict TNBC response to NICT before treatment and to help with the clinical management.

Ask AI

Helpful

Bookmark