Early prediction of neoadjuvant chemotherapy response by exploiting a transfer learning approach on breast DCE-MRIs

• Published in: Scientific reports Vol. 11; no. 1; p. 14123
• Main Authors: Comes, Maria Colomba, Fanizzi, Annarita, Bove, Samantha, Didonna, Vittorio, Diotaiuti, Sergio, La Forgia, Daniele, Latorre, Agnese, Martinelli, Eugenio, Mencattini, Arianna, Nardone, Annalisa, Paradiso, Angelo Virgilio, Ressa, Cosmo Maurizio, Tamborra, Pasquale, Lorusso, Vito, Massafra, Raffaella
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 08.07.2021; Nature Publishing Group; Nature Portfolio
• Subjects: 692/4028/67; 692/699/67/1059; 692/699/67/1347; 692/700/1421; Adult; Breast; Breast - diagnostic imaging; Breast - drug effects; Breast - pathology; Breast Neoplasms - diagnosis; Breast Neoplasms - diagnostic imaging; Breast Neoplasms - drug therapy; Breast Neoplasms - genetics; Chemotherapy; ErbB-2 protein; Female; Humanities and Social Sciences; Humans; Machine Learning; Magnetic Resonance Imaging; Middle Aged; multidisciplinary; Neoplasm Staging; Neural networks; Neural Networks, Computer; Patients; Predictions; Radiography; Receptor, ErbB-2 - genetics; Receptors, Estrogen - genetics; Receptors, Progesterone - genetics; Science; Science (multidisciplinary); Transfer learning; Treatment Outcome
• ISSN: 2045-2322; 2045-2322
• DOI: 10.1038/s41598-021-93592-z

The dynamic contrast-enhanced MR imaging plays a crucial role in evaluating the effectiveness of neoadjuvant chemotherapy (NAC) even since its early stage through the prediction of the final pathological complete response (pCR). In this study, we proposed a transfer learning approach to predict if a patient achieved pCR (pCR) or did not (non-pCR) by exploiting, separately or in combination, pre-treatment and early-treatment exams from I-SPY1 TRIAL public database. First, low-level features, i.e., related to local structure of the image, were automatically extracted by a pre-trained convolutional neural network (CNN) overcoming manual feature extraction. Next, an optimal set of most stable features was detected and then used to design an SVM classifier. A first subset of patients, called fine-tuning dataset (30 pCR; 78 non-pCR), was used to perform the optimal choice of features. A second subset not involved in the feature selection process was employed as an independent test (7 pCR; 19 non-pCR) to validate the model. By combining the optimal features extracted from both pre-treatment and early-treatment exams with some clinical features, i.e., ER, PgR, HER2 and molecular subtype, an accuracy of 91.4% and 92.3%, and an AUC value of 0.93 and 0.90, were returned on the fine-tuning dataset and the independent test, respectively. Overall, the low-level CNN features have an important role in the early evaluation of the NAC efficacy by predicting pCR. The proposed model represents a first effort towards the development of a clinical support tool for an early prediction of pCR to NAC.