Dataset Information

Robustness Evaluation of a Deep Learning Model on Sagittal and Axial Breast DCE-MRIs to Predict Pathological Complete Response to Neoadjuvant Chemotherapy.

ABSTRACT: To date, some artificial intelligence (AI) methods have exploited Dynamic Contrast-Enhanced Magnetic Resonance Imaging (DCE-MRI) to identify finer tumor properties as potential earlier indicators of pathological Complete Response (pCR) in breast cancer patients undergoing neoadjuvant chemotherapy (NAC). However, they work either for sagittal or axial MRI protocols. More flexible AI tools, to be used easily in clinical practice across various institutions in accordance with its own imaging acquisition protocol, are required. Here, we addressed this topic by developing an AI method based on deep learning in giving an early prediction of pCR at various DCE-MRI protocols (axial and sagittal). Sagittal DCE-MRIs refer to 151 patients (42 pCR; 109 non-pCR) from the public I-SPY1 TRIAL database (DB); axial DCE-MRIs are related to 74 patients (22 pCR; 52 non-pCR) from a private DB provided by Istituto Tumori "Giovanni Paolo II" in Bari (Italy). By merging the features extracted from baseline MRIs with some pre-treatment clinical variables, accuracies of 84.4% and 77.3% and AUC values of 80.3% and 78.0% were achieved on the independent tests related to the public DB and the private DB, respectively. Overall, the presented method has shown to be robust regardless of the specific MRI protocol.

SUBMITTER: Massafra R

PROVIDER: S-EPMC9225219 | biostudies-literature | 2022 Jun

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Robustness Evaluation of a Deep Learning Model on Sagittal and Axial Breast DCE-MRIs to Predict Pathological Complete Response to Neoadjuvant Chemotherapy.

Massafra Raffaella R Comes Maria Colomba MC Bove Samantha S Didonna Vittorio V Gatta Gianluca G Giotta Francesco F Fanizzi Annarita A La Forgia Daniele D Latorre Agnese A Pastena Maria Irene MI Pomarico Domenico D Rinaldi Lucia L Tamborra Pasquale P Zito Alfredo A Lorusso Vito V Paradiso Angelo Virgilio AV

Journal of personalized medicine 20220610 6

To date, some artificial intelligence (AI) methods have exploited Dynamic Contrast-Enhanced Magnetic Resonance Imaging (DCE-MRI) to identify finer tumor properties as potential earlier indicators of pathological Complete Response (pCR) in breast cancer patients undergoing neoadjuvant chemotherapy (NAC). However, they work either for sagittal or axial MRI protocols. More flexible AI tools, to be used easily in clinical practice across various institutions in accordance with its own imaging acquis ...[more]

PMID: 35743737

Similar Datasets

Project description:ObjectiveThe aim of this study was to develop and validate a deep learning-based radiomic (DLR) model combined with clinical characteristics for predicting pathological complete response (pCR) to neoadjuvant chemotherapy (NAC) in breast cancer. For early prediction of pCR, the DLR model was based on pre-treatment and early treatment dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) data.Materials and methodsThis retrospective study included 95 women (mean age, 48.1 years; range, 29-77 years) who underwent DCE-MRI before (pre-treatment) and after two or three cycles of NAC (early treatment) from 2018 to 2021. The patients in this study were randomly divided into a training cohort (n=67) and a validation cohort (n=28) at a ratio of 7:3. Deep learning and handcrafted features were extracted from pre- and early treatment DCE-MRI contoured lesions. These features contribute to the construction of radiomic signature RS1 and RS2 representing information from different periods. Mutual information and least absolute shrinkage and selection operator regression were used for feature selection. A combined model was then developed based on the DCE-MRI features and clinical characteristics. The performance of the models was assessed using the area under the receiver operating characteristic curve (AUC) and compared using the DeLong test.ResultsThe overall pCR rate was 25.3% (24/95). One radiomic feature and three deep learning features in RS1, five radiomic features and 11 deep learning features in RS2, and five clinical characteristics remained in the feature selection. The performance of the DLR model combining pre- and early treatment information (AUC=0.900) was better than that of RS1 (AUC=0.644, P=0.068) and slightly higher that of RS2 (AUC=0.888, P=0.604) in the validation cohort. The combined model including pre- and early treatment information and clinical characteristics showed the best ability with an AUC of 0.925 in the validation cohort.ConclusionThe combined model integrating pre-treatment, early treatment DCE-MRI data, and clinical characteristics showed good performance in predicting pCR to NAC in patients with breast cancer. Early treatment DCE-MRI and clinical characteristics may play an important role in evaluating the outcomes of NAC by predicting pCR.

Project description:BACKGROUND:The main purpose was to investigate the correlation between magnetic resonance imaging (MRI)-based response patterns halfway through neoadjuvant chemotherapy and immunotherapy (NAC) and pathological tumor response in patients with breast cancer. Secondary purposes were to compare the predictive value of MRI-based response patterns measured halfway through NAC and after NAC and to measure interobserver variability. METHODS:All consecutive patients treated with NAC for primary invasive breast cancer from 2012 to 2015 and who underwent breast MRI before, halfway through (and after) NAC were included. All breast tumors were reassessed on MRI by two experienced breast radiologists and classified into six patterns: type 0 (complete radiologic response); type 1 (concentric shrinkage); type 2 (crumbling); type 3 (diffuse enhancement); type 4 (stable disease); type 5 (progressive disease). Percentages of tumors showing pathological complete response (pCR), > 50% tumor reduction and > 50% tumor diameter reduction per MRI-based response pattern were calculated. Correlation between MRI-based response patterns and pathological tumor reduction was studied with Pearson's correlation coefficient, and interobserver agreement was tested with Cohen's Kappa. RESULTS:Patients (n = 76; mean age 53, range 29-72 years) with 80 tumors (4 bilateral) were included. There was significant correlation between these MRI-based response patterns halfway through NAC and tumor reduction on pathology assessment (reader 1 r = 0.33; p = 0.003 and reader 2 r = 0.45; p < 0.001). Type-0, type-1 or type-2 patterns halfway through NAC showed highest tumor reduction rates on pathology assessment, with > 50% tumor reduction in 90%, 78% and 65% of cases, respectively. In 83% of tumors with type 0 halfway through NAC, pathology assessment showed pCR. There was no significant correlation between MRI-based response patterns after NAC and tumor reduction rates on pathology assessment (reader 1 r = - 0.17; p = 0.145 and reader 2 r = - 0.17; p = 0.146). In 41% of tumors with type 0 after NAC, pathology assessment showed pCR. CONCLUSION:MRI-based response patterns halfway through NAC can predict pathologic response more accurately than MRI-based response patterns after NAC. Complete radiological response halfway NAC is associated with 83% pCR, while complete radiological response after NAC seems to be correct in only 41% of cases.

Dataset Information

Robustness Evaluation of a Deep Learning Model on Sagittal and Axial Breast DCE-MRIs to Predict Pathological Complete Response to Neoadjuvant Chemotherapy.

Publications

Robustness Evaluation of a Deep Learning Model on Sagittal and Axial Breast DCE-MRIs to Predict Pathological Complete Response to Neoadjuvant Chemotherapy.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets