Machine learning on MRI radiomic features: identification of molecular subtype alteration in breast cancer after neoadjuvant therapy

MRI-based vector radiomics for predicting breast cancer HER2 status and its changes after neoadjuvant therapy

PURPOSE

To develop a novel MRI-based vector radiomic approach to predict breast cancer (BC) human epidermal growth factor receptor 2 (HER2) status (zero, low, and positive; task 1) and its changes after neoadjuvant therapy (NAT) (positive-to-positive, positive-to-negative, and positive-to-pathologic complete response; task 2).

MATERIALS AND METHODS

Both dynamic contrast-enhanced (DCE) MRI data and multi-b-value (MBV) diffusion-weighted imaging (DWI) data were acquired in BC patients at two centers. Vector-radiomic and conventional-radiomic features were extracted from both DCE-MRI and MBV-DWI. After feature selection, the following models were built using the retained features and logistic regression: vector model, conventional model, and combined model that integrates the vector-radiomic and conventional-radiomic features. The models' performances were quantified by the area under the receiver-operating characteristic curve (AUC).

RESULTS

The training/external test set (center 1/2) included 483/361 women. For task 1, the vector model (AUCs=0.73∼0.86) was superior to (p<.05) the conventional model (AUCs=0.68∼0.81), and the addition of vector-radiomic features to conventional-radiomic features yielded an incremental predictive value (AUCs=0.80∼0.90, p<.05). For task 2, the combined MBV-DWI model (AUCs=0.85∼0.89) performed better than (p<.05) the conventional MBV-DWI model (AUCs=0.73∼0.82). In addition, for the combined DCE-MRI model and the combined MBV-DWI model, the former (AUCs=0.85∼0.90) outperformed (p<.05) the latter (AUCs=0.80∼0.85) in task 1, whereas the latter (AUCs=0.85∼0.89) outperformed (p<.05) the former (AUCs=0.76∼0.81) in task 2. The above results are true for the training and external test sets.

CONCLUSIONS

MRI-based vector radiomics may predict BC HER2 status and its changes after NAT and provide significant incremental prediction over and above conventional radiomics.

A clinicopathological-imaging nomogram for the prediction of pathological complete response in breast cancer cases administered neoadjuvant therapy

OBJECTIVE

To construct a user-friendly nomogram with MRI and clinicopathological parameters for the prediction of pathological complete response (pCR) after neoadjuvant therapy (NAT) in patients with breast cancer (BC).

METHODS

We retrospectively enrolled consecutive female patients pathologically confirmed with breast cancer who received NAT followed by surgery between January 2018 and December 2022 as the development cohort. Additionally, we prospectively collected eligible candidates between January 2023 and December 2023 as an external validation group at our institution. Pretreatment MRI features and clinicopathological variables were collected, and the pre- and post-treatment background parenchymal enhancement (BPE) and the changes in BPE on two MRIs were compared between patients who achieved pCR and those who did not. Multivariable logistic regression analysis was used to identify independent variables associated with pCR in the development cohort. These independent variables were combined into a predictive nomogram for which performance was assessed using the area under the receiver operating characteristic curve (AUC), calibration plot, decision curve analysis, and external validation.

RESULTS

In the development cohort, there were a total of 276 female patients with a mean age of 48.3 ± 8.7 years, while in the validation cohort, there were 87 female patients with a mean age of 49.0 ± 9.5 years. Independent prognostic factors of pCR included small tumor size, HER2(+), high Ki-67 index,high signal enhancement ratio (SER), low minimum value of apparent diffusion coefficient (ADCmin), and significantly decreased BPE after NAT(change of BPE). The nomogram, which incorporates the above parameters, demonstrated excellent predictive performance in both the development and external validation cohorts, with AUC values of 0.900 and 0.850, respectively. Additionally, the nomogram showed excellent calibration capacities, as indicated by Hosmer-Lemeshow test p values of 0.508 and 0.423 in the two cohorts. Furthermore, the nomogram provided greater net benefits compared to the default simple schemes in both cohorts.

CONCLUSION

A nomogram constructed using tumor size, HER2 status, Ki-67 index, SER, ADCmin, and changes in pre- and post-NAT BPE demonstrated strong predictive performance, calibration ability, and greater net benefits for predicting pCR in patients with BC after NAT. This suggests that the user-friendly nomogram could be a valuable imaging biomarker for identifying suitable candidates for NAT.

Machine Learning Radiomics-Based Prediction of Non-sentinel Lymph Node Metastasis in Chinese Breast Cancer Patients with 1-2 Positive Sentinel Lymph Nodes: A Multicenter Study

RATIONALE AND OBJECTIVES

This study aimed to construct a machine learning radiomics-based model using dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) images to evaluate non-sentinel lymph node (NSLN) metastasis in Chinese breast cancer (BC) patients who underwent total mastectomy (TM) and had 1-2 positive sentinel lymph nodes (SLNs).

MATERIALS AND METHODS

In total, 494 patients were retrospectively enrolled from two hospitals, and were divided into the training (n = 286), internal validation (n = 122), and external validation (n = 86) cohorts. Features were extracted from DCE-MRI images for each patient and screened. Six ML classifies were trained and the best classifier was evaluated to calculate radiomics (Rad)-scores. A combined model was developed based on Rad-scores and clinical risk factors, then the calibration, discrimination, reclassification, and clinical usefulness were evaluated.

RESULTS

14 radiomics features were ultimately selected. The random forest (RF) classifier showed the best performance, with the highest average area under the curve (AUC) of 0.833 in the validation cohorts. The combined model incorporating RF-based Rad-scores, tumor size, lymphovascular invasion, and proportion of positive SLNs resulted in the best discrimination ability, with AUCs of 0.903, 0.890, and 0.836 in the training, internal validation, and external validation cohorts, respectively. Furthermore, the combined model significantly improved the classification accuracy and clinical benefit for NSLN metastasis prediction.

CONCLUSION

A RF-based combined model using DCE-MRI images exhibited a promising performance for predicting NSLN metastasis in Chinese BC patients who underwent TM and had 1-2 positive SLNs, thereby aiding in individualized clinical treatment decisions.

Prediction of Receptor Status in Radiomics: Recent Advances in Breast Cancer Research

Breast cancer is a multifactorial heterogeneous disease and the leading cause of cancer-related deaths in women; its diagnosis and treatment require clinical sensitivity and a comprehensive disciplinary research approach. The expression of different receptors on tumor cells not only provides the basis for molecular typing of breast cancer but also has a decisive role in the diagnosis, treatment, and prognosis of breast cancer. To date, immunohistochemistry (IHC), which uses invasive histological sampling, has been extensively used in clinical practice to analyze the status of receptors and to make an accurate diagnosis of breast cancer. As an invasive assay, IHC can provide important biological information on tumors at a single point in time, but cannot predict future changes (due to treatment or tumor mutations) without additional invasive procedures. These issues highlight the need to develop a non-invasive method for predicting receptor status. The emerging field of radiomics may offer a non-invasive approach to identification of receptor status without requiring biopsy. In this paper, we present a review of the latest research results in radiomics for predicting the status of breast cancer receptors, with potential important clinical applications.

Multiparametric MRI model to predict molecular subtypes of breast cancer using Shapley additive explanations interpretability analysis

PURPOSE

The purpose of this study was to assess the predictive performance of multiparametric magnetic resonance imaging (MRI) for molecular subtypes and interpret features using SHapley Additive exPlanations (SHAP) analysis.

MATERIAL AND METHODS

Patients with breast cancer who underwent pre-treatment MRI (including ultrafast dynamic contrast-enhanced MRI, magnetic resonance spectroscopy, diffusion kurtosis imaging and intravoxel incoherent motion) were recruited between February 2019 and January 2022. Thirteen semantic and thirteen multiparametric features were collected and the key features were selected to develop machine-learning models for predicting molecular subtypes of breast cancers (luminal A, luminal B, triple-negative and HER2-enriched) by using stepwise logistic regression. Semantic model and multiparametric model were built and compared based on five machine-learning classifiers. Model decision-making was interpreted using SHAP analysis.

RESULTS

A total of 188 women (mean age, 53 ± 11 [standard deviation] years; age range: 25-75 years) were enrolled and further divided into training cohort (131 women) and validation cohort (57 women). XGBoost demonstrated good predictive performance among five machine-learning classifiers. Within the validation cohort, the areas under the receiver operating characteristic curves (AUCs) for the semantic models ranged from 0.693 (95% confidence interval [CI]: 0.478-0.839) for HER2-enriched subtype to 0.764 (95% CI: 0.681-0.908) for luminal A subtype, inferior to multiparametric models that yielded AUCs ranging from 0.771 (95% CI: 0.630-0.888) for HER2-enriched subtype to 0.857 (95% CI: 0.717-0.957) for triple-negative subtype. The AUCs between the semantic and the multiparametric models did not show significant differences (P range: 0.217-0.640). SHAP analysis revealed that lower iAUC, higher kurtosis, lower D*, and lower kurtosis were distinctive features for luminal A, luminal B, triple-negative breast cancer, and HER2-enriched subtypes, respectively.

CONCLUSION

Multiparametric MRI is superior to semantic models to effectively predict the molecular subtypes of breast cancer.

A simple and convenient model combining multiparametric MRI and clinical features to predict tumour-infiltrating lymphocytes in breast cancer

AIM

To develop a simple and convenient method based on multiparametric magnetic resonance imaging (MRI) and clinical features to non-invasively predict tumour-infiltrating lymphocytes (TILs) in breast cancer (BC) and to explore the relationship between TIL levels and disease-free survival (DFS).

MATERIALS AND METHODS

A total of 172 BC patients were enrolled between November 2017 and June 2021 in this retrospective study. The patients were divided into high (≥10%) and low (<10%) TIL groups. Clinicopathological data were collected. MRI features were reviewed by two radiologists. Predictors associated with TILs were determined by using multivariable logistic regression analyses. Kaplan-Meier survival curves based on TIL levels were used to estimate DFS.

RESULTS

A total of 102 patients with low TILs and 70 patients with high TILs were included in the study. Tumour size (odds ratio [OR], 1.040; 95% confidence interval [CI]: 1.006, 1.075; p=0.020), apparent diffusion coefficient (ADC; OR, 1.003; 95% CI: 1.001, 1.005; p=0.015), clinical axillary lymph node status (CALNS; OR, 3.222; 95% CI: 1.372,7.568; p=0.007), and enhancement pattern (OR, 0.284; 95% CI: 0.143, 0.563; p<0.001) were independently associated with TIL levels. These features were used in the ALSE model (where A is ADC, L is CALNS, S is size, and E is enhancement pattern). High TILs were associated with better DFS (p=0.016).

CONCLUSION

The ALSE model derived from multiparametric MRI and clinical features could non-invasively predict TIL levels in BC, and high TILs were associated with longer DFS, especially in human epidermal growth factor receptor 2 (HER2)-positive BC and triple-negative BC (TNBC).

Freehand 1.5T MR-Guided Vacuum-Assisted Breast Biopsy (MR-VABB): Contribution of Radiomics to the Differentiation of Benign and Malignant Lesions

Radiomics and artificial intelligence have been increasingly applied in breast MRI. However, the advantages of using radiomics to evaluate lesions amenable to MR-guided vacuum-assisted breast biopsy (MR-VABB) are unclear. This study includes patients scheduled for MR-VABB, corresponding to subjects with MRI-only visible lesions, i.e., with a negative second-look ultrasound. The first acquisition of the multiphase dynamic contrast-enhanced MRI (DCE-MRI) sequence was selected for image segmentation and radiomics analysis. A total of 80 patients with a mean age of 55.8 years ± 11.8 (SD) were included. The dataset was then split into a training set (50 patients) and a validation set (30 patients). Twenty out of the 30 patients with a positive histology for cancer were in the training set, while the remaining 10 patients with a positive histology were included in the test set. Logistic regression on the training set provided seven features with significant p values (<0.05): (1) 'AverageIntensity', (2) 'Autocorrelation', (3) 'Contrast', (4) 'Compactness', (5) 'StandardDeviation', (6) 'MeanAbsoluteDeviation' and (7) 'InterquartileRange'. AUC values of 0.86 (95% C.I. 0.73-0.94) for the training set and 0.73 (95% C.I. 0.54-0.87) for the test set were obtained for the radiomics model. Radiological evaluation of the same lesions scheduled for MR-VABB had AUC values of 0.42 (95% C.I. 0.28-0.57) for the training set and 0.4 (0.23-0.59) for the test set. In this study, a radiomics logistic regression model applied to DCE-MRI images increased the diagnostic accuracy of standard radiological evaluation of MRI suspicious findings in women scheduled for MR-VABB. Confirming this performance in large multicentric trials would imply that using radiomics in the assessment of patients scheduled for MR-VABB has the potential to reduce the number of biopsies, in suspicious breast lesions where MR-VABB is required, with clear advantages for patients and healthcare resources.