Magnetic resonance imaging-based artificial intelligence model predicts neoadjuvant therapy response in triple-negative breast cancer.
Authors
Affiliations (9)
Affiliations (9)
- İzmir Foça State Hospital, Clinic of Radiology, İzmir, Türkiye.
- University of Health Sciences of Türkiye, İzmir City Hospital, Department of Radiology, İzmir, Türkiye.
- Burdur Mehmet Akif Ersoy University, Faculty of Bucak Computer and Informatics, Department of Software Engineering, Burdur, Türkiye.
- University of Health Sciences of Türkiye, İzmir City Hospital, Department of Medical Oncology, İzmir, Türkiye.
- Alanya Alaaddin Keykubat University Faculty of Engineering and Architecture, Department of Electrical and Electronics Engineering, Antalya, Türkiye.
- İzmir Katip Çelebi University Faculty of Medicine, Department of Radiology, İzmir, Türkiye.
- University of Health Sciences of Türkiye, İzmir City Hospital, Department of Pathology, İzmir, Türkiye.
- Ege University Faculty of Medicine, Department of Radiology, İzmir, Türkiye.
- University of Health Sciences, İzmir Faculty of Medicine, İzmir, Türkiye.
Abstract
Triple-negative breast cancer (TNBC) is an aggressive subtype of breast cancer with limited treatment options and poorer overall survival than other subtypes. Neoadjuvant chemotherapy (NACT) is often used to reduce tumor size and improve surgical outcomes. However, predicting patients' response to NACT remains challenging, and non-responding patients risk unnecessary chemotoxicity. This study aimed to develop a deep learning-based artificial intelligence (AI) model using pre-treatment magnetic resonance imaging (MRI) to predict pathological complete response (pCR) in patients with TNBC undergoing NACT. This retrospective, double-centered study included 49 lesions from 43 patients with TNBC. Data from MRI, including T2-weighted, T1-weighted, and diffusion-weighted imaging, were segmented and processed to train a residual convolutional neural network model. The AI model achieved an accuracy of 0.82 and an area under the receiver operating characteristic curve of 0.75 in differentiating pCR from non-pCR cases. The model's performance was validated through intra- and inter-reader agreement metrics, with Dice similarity coefficients ranging from 0.821 to 0.915. Our results demonstrate that AI models can effectively predict NACT responses in patients with TNBC using only pre-treatment MRI data. This proof-of-concept study supports the potential for AI-based tools to aid clinical decision-making and reduce the risks associated with ineffective therapies. Future research with larger datasets and additional imaging modalities is needed to improve model generalizability and clinical applicability.