RESUMO
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.
Assuntos
Antineoplásicos/uso terapêutico , Neoplasias da Mama/diagnóstico por imagem , Aprendizado Profundo , Diagnóstico por Computador/métodos , Imageamento por Ressonância Magnética , Terapia Neoadjuvante , Adulto , Área Sob a Curva , Neoplasias da Mama/tratamento farmacológico , Quimioterapia Adjuvante , Meios de Contraste , Feminino , Humanos , Processamento de Imagem Assistida por Computador , Pessoa de Meia-Idade , Redes Neurais de Computação , Curva ROC , Estudos Retrospectivos , Resultado do TratamentoRESUMO
BACKGROUND: Early prediction of nonresponse is essential in order to avoid inefficient treatments. PURPOSE: To evaluate if parametrical response mapping (PRM)-derived biomarkers could predict early morphological response (EMR) and pathological complete response (pCR) 24-72 hours after initiation of chemotherapy treatment and whether concentric analysis of nonresponding PRM regions could better predict response. STUDY TYPE: This was a retrospective analysis of prospectively acquired cohort, nonrandomized, monocentric, diagnostic study. POPULATION: Sixty patients were initially recruited, with 39 women participating in the final cohort. FIELD STRENGTH/SEQUENCE: A 1.5T scanner was used for MRI examinations. ASSESSMENT: Dynamic contrast-enhanced (DCE)-MR images were acquired at baseline (timepoint 1, TP1), 24-72 hours after the first chemotherapy (TP2), and after the end of anthracycline treatment (TP3). PRM was performed after fusion of T1 subtraction images from TP1 and TP2 using an affine registration algorithm. Pixels with an increase of more than 10% of their value (PRMdce+) were corresponding nonresponding regions of the tumor. Patients with a decrease of maximum diameter (%dDmax) between TP1 and TP3 of more than 30% were defined as EMR responders. pCR patients achieved a residual cancer burden score of 0. STATISTICAL TESTS: T-test, receiver operating characteristic (ROC) curves, and logistic regression were used for the analysis. RESULTS: PRM showed a statistical difference between pCR response groups (P < 0.01) and AUC of 0.88 for the prediction of non-pCR. Logistic regression analysis demonstrated that PRMdce+ and Grade II were significant (P < 0.01) for non-pCR prediction (AUC = 0.94). Peripheral tumor region demonstrated higher performance for the prediction of non-pCR (AUC = 0.85) than intermediate and central zones; however, statistical comparison showed no significant difference. DATA CONCLUSION: PRM could be predictive of non-pCR 24-72 hours after initiation of chemotherapy treatment. Moreover, the peripheral region showed increased AUC for non-pCR prediction and increased signal intensity during treatment for non-pCR tumors, information that could be used for optimal tissue sampling. LEVEL OF EVIDENCE: 1 Technical Efficacy Stage: 4 J. Magn. Reson. Imaging 2020;51:1403-1411.
Assuntos
Neoplasias da Mama , Terapia Neoadjuvante , Mama , Neoplasias da Mama/diagnóstico por imagem , Neoplasias da Mama/tratamento farmacológico , Feminino , Humanos , Imageamento por Ressonância Magnética , Estudos Retrospectivos , Resultado do TratamentoRESUMO
PURPOSE: This study aims to provide and optimize a performing algorithm for predicting the breast cancer response rate to the first round of chemotherapy using Magnetic Resonance Imaging (MRI). This provides an early recognition of breast tumor reaction to chemotherapy by using the Parametric Response Map (PRM) method. METHODS: PRM may predict the breast cancer response to chemotherapy by analyzing voxel-by-voxel temporal intra-tumor changes during one round of chemotherapy. Indeed, the tumor recognizes intra-tumor changes concerning its vascularity, which is an important criterion in the present study. This method is mainly based on spatial image affine registration between the breast tumor MRI volumes, acquired before and after the first cycle of chemotherapy, and region growing segmentation of the tumor volume. To evaluate our method, we used a retrospective study of 40 patients provided by a collaborating institute. RESULTS: PRM allows a color map to be created with the percentages of positive, negative and stable breast tumor response during the first round of chemotherapy, identifying each region with its response rate. We assessed the accuracy of the proposed method using technical and medical validation methods. The technical validation was based on landmarks-based registration and fully manual segmentation. The medical evaluation was based on the accuracy calculation of the standard reference of anatomic pathology. The p-values and the Area Under the Curve (AUC) of the Receiver Operating Characteristics were calculated to evaluate the proposed PRM method. CONCLUSION: We performed and evaluated the proposed PRM method to study and analyze the behavior of a tumor during the first round of chemotherapy, based on the intra-tumor changes of MR breast tumor images. The AUC obtained for the PRM method is considered as relevant in the early prediction of breast tumor response.