Search

Background: Siamese network (SN) using longitudinal DCE‐MRI for pathologic complete response (pCR) identification lack a unified approach to phases selection. Purpose: To identify pCR in early‐stage NAC, using SN with longitudinal DCE‐MRI and introducing IPS for phases selection. Study Type: Multicenter, longitudinal. Population: Center A: 162 female patients (50.63 ± 8.41 years) divided 7:3 into training and internal validation cohorts. Center B: 61 female patients (50.08 ± 7.82 years) were used as an external validation cohort. Field Strength/Sequence: Center A: single vendor 3.0 T with a compressed‐sensing volume interpolated breath‐hold examination sequence. Center B: single vendor 1.5 T with volume interpolated breath‐hold examination sequence. Assessment: Patients underwent DCE‐MRI before and after two NAC cycles, with tumor regions of interest (ROI) manually delineated. Histopathology was the reference for pCR identification. Models developed included a clinical one, four SN models based on IPS‐selected phases, and integrated models combining clinical and SN features. Statistical Tests: Model performance was evaluated using the area under the receiver operating characteristic curve (AUC). The DeLong test was used to compare AUCs. Net reclassification improvement and integrated discrimination improvement (IDI) tests were employed for performance comparison. P < 0.05 was considered significant. Results: In internal and external validation cohorts, the clinical model showed AUCs of 0.760 and 0.718. SN and integrated models, with increasing phases via IPS, achieved AUCs ranging from 0.813 to 0.951 and 0.818 to 0.922. Notably, SN‐3 and integrated‐3 and integrated‐4 outperformed the clinical model. However, input phases beyond 20% did not significantly enhance performance (IDI test: SN‐4 vs. SN‐3, P = 0.314 and 0.630; integrated‐4 vs. integrated‐3, P = 0.785 and 0.709). Data Conclusion: The longitudinal multiphase DCE‐MRI based on the SN demonstrates promise for identifying pCR in breast cancer. Evidence Level: 1 Technical Efficacy: Stage 4 [ABSTRACT FROM AUTHOR]

Background: Multiparametric dual-energy computed tomography (mpDECT) is widely used to differentiate various kinds of tumors; however, the data regarding its diagnostic performance with machine learning to diagnose breast tumors is limited. We evaluated univariate analysis and machine learning performance with mpDECT to distinguish between benign and malignant breast lesions., Methods: In total, 172 patients with 214 breast lesions (55 benign and 159 malignant) who underwent preoperative dual-phase contrast-enhanced DECT were included in this retrospective study. Twelve quantitative features were extracted for each lesion, including CT attenuation (precontrast, arterial, and venous phases), the arterial-venous phase difference in normalized effective atomic number (nZ eff ), normalized iodine concentration (NIC), and slope of the spectral Hounsfield unit (HU) curve (λ Hu ). Predictive models were developed using univariate analysis and eight machine learning methods [logistic regression, extreme gradient boosting (XGBoost), stochastic gradient descent (SGD), linear discriminant analysis (LDA), adaptive boosting (AdaBoost), random forest (RF), decision tree, and linear support vector machine (SVM)]. Classification performances were assessed based on the area under the receiver operating characteristic curve (AUROC). The best performances of the conventional univariate analysis and machine learning methods were compared using the Delong test., Results: The univariate analysis showed that the venous phase λ Hu had the highest AUROC (0.88). Machine learning with mpDECT achieved an excellent and stable diagnostic performance, as shown by the mean classification performances in the training dataset (AUROC, 0.88-0.99) and testing (AUROC, 0.83-0.96) datasets. The performance of the AdaBoost model based on mpDECT was more stable than the other machine learning models and superior to the univariate analysis (AUROC, 0.96 vs. 0.88; P<0.001)., Conclusions: The performance of the AdaBoost classifier based on mpDECT data achieved the highest mean accuracy compared to the other machine learning models and univariate analysis in differentiating between benign and malignant breast lesions., Competing Interests: Conflicts of Interest: All authors have completed the ICMJE uniform disclosure form (available at https://dx.doi.org/10.21037/qims-21-39). The authors have no conflicts of interest to declare., (2022 Quantitative Imaging in Medicine and Surgery. All rights reserved.)