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

Abstract 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 pre...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Maria Colomba Comes, Annarita Fanizzi, Samantha Bove, Vittorio Didonna, Sergio Diotaiuti, Daniele La Forgia, Agnese Latorre, Eugenio Martinelli, Arianna Mencattini, Annalisa Nardone, Angelo Virgilio Paradiso, Cosmo Maurizio Ressa, Pasquale Tamborra, Vito Lorusso, Raffaella Massafra
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/0c54abc80b30475eb5c5e7ab5ee519b9
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:0c54abc80b30475eb5c5e7ab5ee519b9
record_format	dspace
spelling	oai:doaj.org-article:0c54abc80b30475eb5c5e7ab5ee519b92021-12-02T16:24:49ZEarly prediction of neoadjuvant chemotherapy response by exploiting a transfer learning approach on breast DCE-MRIs10.1038/s41598-021-93592-z2045-2322https://doaj.org/article/0c54abc80b30475eb5c5e7ab5ee519b92021-07-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-93592-zhttps://doaj.org/toc/2045-2322Abstract 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.Maria Colomba ComesAnnarita FanizziSamantha BoveVittorio DidonnaSergio DiotaiutiDaniele La ForgiaAgnese LatorreEugenio MartinelliArianna MencattiniAnnalisa NardoneAngelo Virgilio ParadisoCosmo Maurizio RessaPasquale TamborraVito LorussoRaffaella MassafraNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-12 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Maria Colomba Comes Annarita Fanizzi Samantha Bove Vittorio Didonna Sergio Diotaiuti Daniele La Forgia Agnese Latorre Eugenio Martinelli Arianna Mencattini Annalisa Nardone Angelo Virgilio Paradiso Cosmo Maurizio Ressa Pasquale Tamborra Vito Lorusso Raffaella Massafra Early prediction of neoadjuvant chemotherapy response by exploiting a transfer learning approach on breast DCE-MRIs
description	Abstract 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.
format	article
author	Maria Colomba Comes Annarita Fanizzi Samantha Bove Vittorio Didonna Sergio Diotaiuti Daniele La Forgia Agnese Latorre Eugenio Martinelli Arianna Mencattini Annalisa Nardone Angelo Virgilio Paradiso Cosmo Maurizio Ressa Pasquale Tamborra Vito Lorusso Raffaella Massafra
author_facet	Maria Colomba Comes Annarita Fanizzi Samantha Bove Vittorio Didonna Sergio Diotaiuti Daniele La Forgia Agnese Latorre Eugenio Martinelli Arianna Mencattini Annalisa Nardone Angelo Virgilio Paradiso Cosmo Maurizio Ressa Pasquale Tamborra Vito Lorusso Raffaella Massafra
author_sort	Maria Colomba Comes
title	Early prediction of neoadjuvant chemotherapy response by exploiting a transfer learning approach on breast DCE-MRIs
title_short	Early prediction of neoadjuvant chemotherapy response by exploiting a transfer learning approach on breast DCE-MRIs
title_full	Early prediction of neoadjuvant chemotherapy response by exploiting a transfer learning approach on breast DCE-MRIs
title_fullStr	Early prediction of neoadjuvant chemotherapy response by exploiting a transfer learning approach on breast DCE-MRIs
title_full_unstemmed	Early prediction of neoadjuvant chemotherapy response by exploiting a transfer learning approach on breast DCE-MRIs
title_sort	early prediction of neoadjuvant chemotherapy response by exploiting a transfer learning approach on breast dce-mris
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/0c54abc80b30475eb5c5e7ab5ee519b9
work_keys_str_mv	AT mariacolombacomes earlypredictionofneoadjuvantchemotherapyresponsebyexploitingatransferlearningapproachonbreastdcemris AT annaritafanizzi earlypredictionofneoadjuvantchemotherapyresponsebyexploitingatransferlearningapproachonbreastdcemris AT samanthabove earlypredictionofneoadjuvantchemotherapyresponsebyexploitingatransferlearningapproachonbreastdcemris AT vittoriodidonna earlypredictionofneoadjuvantchemotherapyresponsebyexploitingatransferlearningapproachonbreastdcemris AT sergiodiotaiuti earlypredictionofneoadjuvantchemotherapyresponsebyexploitingatransferlearningapproachonbreastdcemris AT danielelaforgia earlypredictionofneoadjuvantchemotherapyresponsebyexploitingatransferlearningapproachonbreastdcemris AT agneselatorre earlypredictionofneoadjuvantchemotherapyresponsebyexploitingatransferlearningapproachonbreastdcemris AT eugeniomartinelli earlypredictionofneoadjuvantchemotherapyresponsebyexploitingatransferlearningapproachonbreastdcemris AT ariannamencattini earlypredictionofneoadjuvantchemotherapyresponsebyexploitingatransferlearningapproachonbreastdcemris AT annalisanardone earlypredictionofneoadjuvantchemotherapyresponsebyexploitingatransferlearningapproachonbreastdcemris AT angelovirgilioparadiso earlypredictionofneoadjuvantchemotherapyresponsebyexploitingatransferlearningapproachonbreastdcemris AT cosmomaurizioressa earlypredictionofneoadjuvantchemotherapyresponsebyexploitingatransferlearningapproachonbreastdcemris AT pasqualetamborra earlypredictionofneoadjuvantchemotherapyresponsebyexploitingatransferlearningapproachonbreastdcemris AT vitolorusso earlypredictionofneoadjuvantchemotherapyresponsebyexploitingatransferlearningapproachonbreastdcemris AT raffaellamassafra earlypredictionofneoadjuvantchemotherapyresponsebyexploitingatransferlearningapproachonbreastdcemris
_version_	1718384094239260672

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

Ejemplares similares