Early prediction of neoadjuvant chemotherapy response by exploiting a transfer learning approach on breast DCE-MRIs
| العنوان: | Early prediction of neoadjuvant chemotherapy response by exploiting a transfer learning approach on breast DCE-MRIs |
|---|---|
| المؤلفون: | Sergio Diotaiuti, Daniele La Forgia, Eugenio Martinelli, Cosmo Maurizio Ressa, Maria Colomba Comes, Vito Lorusso, Raffaella Massafra, Arianna Mencattini, A Latorre, Pasquale Tamborra, Samantha Bove, Vittorio Didonna, Annalisa Nardone, Annarita Fanizzi, Angelo Paradiso |
| المصدر: | Scientific Reports Scientific Reports, Vol 11, Iss 1, Pp 1-12 (2021) |
| بيانات النشر: | Nature Publishing Group UK, 2021. |
| سنة النشر: | 2021 |
| مصطلحات موضوعية: | Adult, Cancer therapy, Computer science, Receptor, ErbB-2, Science, Feature extraction, Feature selection, Breast Neoplasms, Convolutional neural network, Settore ING-INF/07, Article, 030218 nuclear medicine & medical imaging, Machine Learning, 03 medical and health sciences, 0302 clinical medicine, Text mining, Breast cancer, Early prediction, Humans, Breast, Stage (cooking), Cancer, Neoplasm Staging, Multidisciplinary, business.industry, Pattern recognition, Middle Aged, Magnetic Resonance Imaging, Radiography, Treatment Outcome, Receptors, Estrogen, 030220 oncology & carcinogenesis, Medicine, Female, Artificial intelligence, Medical imaging, Neural Networks, Computer, business, Transfer of learning, Receptors, Progesterone, Chemotherapy response |
| الوصف: | 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. |
| اللغة: | English |
| تدمد: | 2045-2322 |
| الوصول الحر: | https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1b664bc803f23314638a361e8ee4eaafTest http://europepmc.org/articles/PMC8266861Test |
| حقوق: | OPEN |
| رقم الانضمام: | edsair.doi.dedup.....1b664bc803f23314638a361e8ee4eaaf |
| قاعدة البيانات: | OpenAIRE |
| تدمد: | 20452322 |
|---|