Cancer treatment planning benefits from an accurate early prediction of the treatment efficacy. The goal of this study is to give an early prediction of three-year Breast Cancer Recurrence (BCR) for patients who underwent neoadjuvant chemotherapy. We addressed the task from a new perspective based on transfer learning applied to pre-treatment and early-treatment DCE-MRI scans. Firstly, low-level features were automatically extracted from MR images using a pre-trained Convolutional Neural Network (CNN) architecture without human intervention. Subsequently, the prediction model was built with an optimal subset of CNN features and evaluated on two sets of patients from I-SPY1 TRIAL and BREAST-MRI-NACT-Pilot public databases: a fine-tuning dataset (70 not recurrent and 26 recurrent cases), which was primarily used to find the optimal subset of CNN features, and an independent test (45 not recurrent and 17 recurrent cases), whose patients had not been involved in the feature selection process. The best results were achieved when the optimal CNN features were augmented by four clinical variables (age, ER, PgR, HER2+), reaching an accuracy of 91.7% and 85.2%, a sensitivity of 80.8% and 84.6%, a specificity of 95.7% and 85.4%, and an AUC value of 0.93 and 0.83 on the fine-tuning dataset and the independent test, respectively. Finally, the CNN features extracted from pre-treatment and early-treatment exams were revealed to be strong predictors of BCR.

Comes, M.c., Forgia, D.l., Didonna, V., Fanizzi, A., Giotta, F., Latorre, A., et al. (2021). Early prediction of breast cancer recurrence for patients treated with neoadjuvant chemotherapy: A transfer learning approach on dce-mris. CANCERS, 13(10) [10.3390/cancers13102298].

Early prediction of breast cancer recurrence for patients treated with neoadjuvant chemotherapy: A transfer learning approach on dce-mris

Martinelli E.;Mencattini A.;
2021-01-01

Abstract

Cancer treatment planning benefits from an accurate early prediction of the treatment efficacy. The goal of this study is to give an early prediction of three-year Breast Cancer Recurrence (BCR) for patients who underwent neoadjuvant chemotherapy. We addressed the task from a new perspective based on transfer learning applied to pre-treatment and early-treatment DCE-MRI scans. Firstly, low-level features were automatically extracted from MR images using a pre-trained Convolutional Neural Network (CNN) architecture without human intervention. Subsequently, the prediction model was built with an optimal subset of CNN features and evaluated on two sets of patients from I-SPY1 TRIAL and BREAST-MRI-NACT-Pilot public databases: a fine-tuning dataset (70 not recurrent and 26 recurrent cases), which was primarily used to find the optimal subset of CNN features, and an independent test (45 not recurrent and 17 recurrent cases), whose patients had not been involved in the feature selection process. The best results were achieved when the optimal CNN features were augmented by four clinical variables (age, ER, PgR, HER2+), reaching an accuracy of 91.7% and 85.2%, a sensitivity of 80.8% and 84.6%, a specificity of 95.7% and 85.4%, and an AUC value of 0.93 and 0.83 on the fine-tuning dataset and the independent test, respectively. Finally, the CNN features extracted from pre-treatment and early-treatment exams were revealed to be strong predictors of BCR.
2021
Pubblicato
Rilevanza internazionale
Articolo
Esperti anonimi
Settore ING-INF/07 - MISURE ELETTRICHE ED ELETTRONICHE
English
Breast cancer recurrence
Convolutional neural networks
DCE-MRI
Neoadjuvant chemotherapy
Support Vector Machine
Transfer learning
Comes, M.c., Forgia, D.l., Didonna, V., Fanizzi, A., Giotta, F., Latorre, A., et al. (2021). Early prediction of breast cancer recurrence for patients treated with neoadjuvant chemotherapy: A transfer learning approach on dce-mris. CANCERS, 13(10) [10.3390/cancers13102298].
Comes, Mc; Forgia, Dl; Didonna, V; Fanizzi, A; Giotta, F; Latorre, A; Martinelli, E; Mencattini, A; Paradiso, Av; Tamborra, P; Terenzio, A; Zito, A; Lorusso, V; Massafra, R
Articolo su rivista
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/2108/289501
Citazioni
  • ???jsp.display-item.citation.pmc??? 11
  • Scopus 28
  • ???jsp.display-item.citation.isi??? 28
social impact