Deep Learning Models Based on Pretreatment MRI and Clinicopathological Data to Predict Responses to Neoadjuvant Systemic Therapy in Triple-Negative Breast Cancer

Authors

Zhan Xu
Zijian Zhou
Jong Bum Son
Haonan Feng
Beatriz E Adrada
Tanya W Moseley
Rosalind P Candelaria
Mary S Guirguis
Miral M Patel
Gary J Whitman
Jessica W T Leung
Huong T C Le-Petross
Rania M Mohamed
Bikash Panthi
Deanna L Lane
Huiqin Chen
Peng Wei
Debu Tripathy
Jennifer K Litton
Vicente Valero
Lei Huo
Kelly K Hunt
Anil Korkut
Alastair Thompson
Wei Yang
Clinton Yam
Gaiane M Rauch
Jingfei Ma

Publication Date

3-13-2025

Journal

Cancers

Abstract

Purpose: To develop deep learning models for predicting the pathologic complete response (pCR) to neoadjuvant systemic therapy (NAST) in patients with triple-negative breast cancer (TNBC) based on pretreatment multiparametric breast MRI and clinicopathological data.

Methods: The prospective institutional review board-approved study [NCT02276443] included 282 patients with stage I-III TNBC who had multiparametric breast MRI at baseline and underwent NAST and surgery during 2016-2021. Dynamic contrast-enhanced MRI (DCE), diffusion-weighted imaging (DWI), and clinicopathological data were used for the model development and internal testing. Data from the I-SPY 2 trial (2010-2016) were used for external testing. Four variables with a potential impact on model performance were systematically investigated: 3D model frameworks, tumor volume preprocessing, tumor ROI selection, and data inputs.

Results: Forty-eight models with different variable combinations were investigated. The best-performing model in the internal testing dataset used DCE, DWI, and clinicopathological data with the originally contoured tumor volume, the tight bounding box of the tumor mask, and ResNeXt50, and achieved an area under the receiver operating characteristic curve (AUC) of 0.76 (95% CI: 0.60-0.88). The best-performing models in the external testing dataset achieved an AUC of 0.72 (95% CI: 0.57-0.84) using only DCE images (originally contoured tumor volume, enlarged bounding box of tumor mask, and ResNeXt50) and an AUC of 0.72 (95% CI: 0.56-0.86) using only DWI images (originally contoured tumor volume, enlarged bounding box of tumor mask, and ResNet18).

Conclusions: We developed 3D deep learning models based on pretreatment data that could predict pCR to NAST in TNBC patients.

Keywords

deep learning, pathological complete response, pretreatment prediction, transfer learning, triple-negative breast cancer

DOI

10.3390/cancers17060966

PMID

40149299

PMCID

PMC11940201

PubMedCentral® Posted Date

3-13-2025

PubMedCentral® Full Text Version

Post-print

Published Open-Access

yes