TY - JOUR
T1 - Multi-input deep learning architecture for predicting breast tumor response to chemotherapy using quantitative MR images
AU - El Adoui, Mohammed
AU - Drisis, Stylianos
AU - Benjelloun, Mohammed
N1 - Funding Information:
This research was financially supported by the University of Mons in Belgium. Acknowledgements
Funding Information:
We would like to address our sincere acknowledgments to Dr. Marc Lemort, the head of the Radiology Department at the Jules Bordet Institute—Brussels, for offering the dataset used to evaluate our implemented models.
Publisher Copyright:
© 2020, CARS.
PY - 2020/9/1
Y1 - 2020/9/1
N2 - Purpose: Neoadjuvant chemotherapy (NAC) aims to minimize the tumor size before surgery. Predicting response to NAC could reduce toxicity and delays to effective intervention. Computational analysis of dynamic contrast-enhanced magnetic resonance images (DCE-MRI) through deep convolution neural network (CNN) has shown a significant performance to distinguish responders and no responder’s patients. This study intends to present a new deep learning (DL) model predicting the breast cancer response to NAC based on multiple MRI inputs. Methods: A cohort of 723 axial slices extracted from 42 breast cancer patients who underwent NAC therapy was used to train and validate the developed DL model. This dataset was provided by our collaborator institute of radiology in Brussels. Fourteen external cases were used to validate the best obtained model to predict pCR based on pre- and post-chemotherapy DCE-MRI. The model performance was assessed by area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, and feature map visualization. Results: The developed multi-inputs deep learning architecture was able to predict the pCR to NAC treatment in the validation dataset with an AUC of 0.91 using combined pre- and post-NAC images. The visual results showed that the most important extracted features from non-pCR tumors are in the peripheral region. The proposed method was more productive than the previous ones. Conclusion: Even with a limited training dataset size, the proposed and developed CNN model using DCE-MR images acquired before and after the first chemotherapy was able to classify pCR and non-pCR patients with substantial accuracy. This model could be used hereafter in clinical analysis after its evaluation based on more extra data.
AB - Purpose: Neoadjuvant chemotherapy (NAC) aims to minimize the tumor size before surgery. Predicting response to NAC could reduce toxicity and delays to effective intervention. Computational analysis of dynamic contrast-enhanced magnetic resonance images (DCE-MRI) through deep convolution neural network (CNN) has shown a significant performance to distinguish responders and no responder’s patients. This study intends to present a new deep learning (DL) model predicting the breast cancer response to NAC based on multiple MRI inputs. Methods: A cohort of 723 axial slices extracted from 42 breast cancer patients who underwent NAC therapy was used to train and validate the developed DL model. This dataset was provided by our collaborator institute of radiology in Brussels. Fourteen external cases were used to validate the best obtained model to predict pCR based on pre- and post-chemotherapy DCE-MRI. The model performance was assessed by area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, and feature map visualization. Results: The developed multi-inputs deep learning architecture was able to predict the pCR to NAC treatment in the validation dataset with an AUC of 0.91 using combined pre- and post-NAC images. The visual results showed that the most important extracted features from non-pCR tumors are in the peripheral region. The proposed method was more productive than the previous ones. Conclusion: Even with a limited training dataset size, the proposed and developed CNN model using DCE-MR images acquired before and after the first chemotherapy was able to classify pCR and non-pCR patients with substantial accuracy. This model could be used hereafter in clinical analysis after its evaluation based on more extra data.
KW - Breast cancer
KW - CNN
KW - DCE-MRI
KW - Deep learning
KW - Features visualization
KW - Multi-input network
UR - http://www.scopus.com/inward/record.url?scp=85086709774&partnerID=8YFLogxK
U2 - 10.1007/s11548-020-02209-9
DO - 10.1007/s11548-020-02209-9
M3 - Article
C2 - 32556920
AN - SCOPUS:85086709774
SN - 1861-6410
VL - 15
SP - 1491
EP - 1500
JO - International Journal of Computer Assisted Radiology and Surgery
JF - International Journal of Computer Assisted Radiology and Surgery
IS - 9
ER -