Deep learning-based prediction of response to neoadjuvant immunochemotherapy in triple-negative breast cancer based on pretreatment DCE-MRI
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.
Authors
- Xiaofei Huo
- Gaiane M. Rauch
- Jong Bum Son (ORCID: https://orcid.org/0000-0003-2548-5895)
- Clinton Yam (ORCID: https://orcid.org/0000-0002-0809-0851)
- Yuexin Liu (ORCID: https://orcid.org/0000-0003-3508-6652)
- Tanya W. Moseley (ORCID: https://orcid.org/0000-0002-2018-8253)
- Beatriz E. Adrada (ORCID: https://orcid.org/0000-0002-5539-5332)
- Zhan Xu (ORCID: https://orcid.org/0000-0002-5892-0227)
- Jingfei Ma (ORCID: https://orcid.org/0000-0003-2827-8891)
- Ziyu Fu
Publication Details
- Journal
- Proceedings on CD-ROM - International Society for Magnetic Resonance in Medicine. Scientific Meeting and Exhibition/Proceedings of the International Society for Magnetic Resonance in Medicine, Scientific Meeting and Exhibition
- Published
- 2025-09-16
- DOI
- https://doi.org/10.58530/2025/1556
- Primary Topic
- Radiomics and Machine Learning in Medical Imaging
- Type
- article
- Field-Weighted Citation Impact
- 0.00