Noninvasive assessment of breast cancer molecular subtypes on multiparametric MRI using convolutional neural network with transfer learning

Abstract

Abstract Background To evaluate the performances of multiparametric MRI‐based convolutional neural networks (CNNs) for the preoperative assessment of breast cancer molecular subtypes. Methods A total of 136 patients with 136 pathologically confirmed invasive breast cancers were randomly divided into training, validation, and testing sets in this retrospective study. The CNN models were established based on contrast‐enhanced T1‐weighted imaging (T1C), Apparent diffusion coefficient (ADC), and T2‐weighted imaging (T2W) using the training and validation sets. The performances of CNN models were evaluated on the testing set. The area under the receiver operating characteristic curve (AUC), sensitivity, specificity, and accuracy were calculated to assess the performance. Results For the separation of each subtype from other subtypes on the testing set, the T1C‐based models yielded AUCs from 0.762 to 0.920; the ADC‐based models yielded AUCs from 0.686 to 0.851; and the T2W‐based models achieved AUCs from 0.639 to 0.697. Conclusion T1C‐based models performed better than ADC‐based models and T2W‐based models in assessing the breast cancer molecular subtypes. The discriminating performances of our CNN models for triple negative and human epidermal growth factor receptor 2‐enriched subtypes were better than that of luminal A and luminal B subtypes.

Keywords

• breast cancer
• breast MRI
• deep learning
• molecular subtypes
• neural network