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.
Highlights
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
Images used for the purpose of the presented study refer to a set of Dynamic Contrast-Enhanced Magnetic Resonance Imaging (DCE-MRI) from the multi-site Investigation of Serial Studies to Predict Your Therapeutic Response with Imaging and molecular Analysis (I-SPY1 TRIAL)[7,35,36] public dataset, which contains cases of 230 women enrolled between 2002 and 2006 with breast tumors of at least 3 cm in size, who received NAC with an anthracycline-cyclophosphamide (AC) regimen alone or followed by taxane
With the emergence and the spread of the modern concept of personalized medicine, an early prediction of pathological complete response for breast cancer patients undergoing neoadjuvant chemotherapy through the analysis of MRI examinations has become a topic of great interest in the state of the art
Summary
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). Early responder patients, i.e., responders even since the early stages of NAC, are more likely to take advantage from breast conserving surgery, avoiding them a full m astectomy[6] Within this emerging scenario, a systematic literature search has highlighted the Dynamic Contrast-Enhanced Magnetic Resonance Imaging (DCE-MRI) as an indispensable tool for monitoring the response to therapy[7,8,9,10]. The radiomic analysis of DCE-MR images by means of automatic and semi-automatic computerized systems developed by experts has become of great interest as evidenced in various breast imaging m ethods[16,17,18,19] Radiomic features, such as tissue, peritumoral or intratumoral features, extracted from raw images and appropriately combined with histological variables could help to predict the progress of the oncologic disease as well as pCR ever since the early stages of NAC1,7,14,20–23. The background parenchymal enhancement (BPE) parameter has been demonstrated to be a predictive factor of disease course and response to neoadjuvant therapy in breast cancer[24,25]
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
