Leveraging multimodal MRI-based radiomics analysis with diverse machine learning models to evaluate lymphovascular invasion in clinically node-negative breast cancer

Multiphases DCE-MRI Radiomics Nomogram for Preoperative Prediction of Lymphovascular Invasion in Invasive Breast Cancer

RATIONALE AND OBJECTIVES

Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) radiomics had been used to evaluate lymphovascular invasion (LVI) in patients with breast cancer. However, no studies had explored the associations between features from delayed phase as well as multiphases DCE-MRI and the LVI status. Thus, we aimed to develop an efficient nomogram based on multiphases DCE-MRI to predict the LVI status in invasive (IBC) breast cancer patients.

MATERIALS AND METHODS

A retrospective analysis was conducted on preoperative clinical, pathological, and DCE-MRI data of 173 breast cancer patients. All patients were randomly assigned into training set (n=121) and validation set (n=52) in 7:3 ratio. The clinical, pathologic, and conventional MRI characteristics were then subjected to univariate and multivariate logistic regression analysis, and the clinical risk factors with P < 0.05 in the multivariate logistic regression were used to build clinical models. Different single-phase models (early phase, peak phase, and terminal phase), as well as a multiphases model integrating radiomics features from multiple phases, were established. Furthermore, a preoperative radiomics nomogram model was constructed by combining the rad-score of the multiphases model with clinicopathologic independent risk factors. Finally, the performance of the multiphases model, clinical model, and rad-score was compared using receiver operating characteristic (ROC) curves, area under the curve (AUC) values, and decision curve analysis (DCA). The clinical utility of the rad-score was evaluated using calibration curves, and Delong test was used to compare the differences in AUC values among the different models.

RESULTS

The axillary lymph nodes (ALN) status and Ki-67 had been identified as clinicopathologic independent predictors and a clinical model had been constructed. Image features that were extracted from the terminal phase of the DCE-MRI exhibited notably superior predictive performances compared to features from the other single phases. Particularly, in the multiphases model, terminal phase features were identified as potentially providing more predictive information. Among the nine features that were found to be associated with LVI in the multiphase model, one was derived from the early phase, two from the peak phase, and six from the terminal phase, indicating that terminal phase features contributed significantly more information towards predicting LVI. Evaluation of the nomogram performance revealed promising results in both the training set (AUCs: clinical model vs. multiphase model vs. nomogram=0.734 vs. 0.840 vs. 0.876) and the validation set (AUCs: clinical model vs. multiphase model vs. nomogram=0.765 vs. 0.753 vs. 0.832).

CONCLUSION

The DCE-MRI-based radiomics model demonstrated utility in predicting LVI status, features of the terminal phase offered more valuable information particularly. The preoperative radiomics nomogram enhanced the diagnostic capability of identifying LVI status in IBC patients, and might aid clinicians in making personalized treatment decisions.

MRI-based radiomic and machine learning for prediction of lymphovascular invasion status in breast cancer

OBJECTIVE

Lymphovascular invasion (LVI) is critical for the effective treatment and prognosis of breast cancer (BC). This study aimed to investigate the value of eight machine learning models based on MRI radiomic features for the preoperative prediction of LVI status in BC.

METHODS

A total of 454 patients with BC with known LVI status who underwent breast MRI were enrolled and randomly assigned to the training and validation sets at a ratio of 7:3. Radiomic features were extracted from T2WI and dynamic contrast-enhanced (DCE) of MRI sequences, the optimal feature filter and LASSO algorithm were used to obtain the optimal features, and eight machine learning algorithms, including LASSO, logistic regression, random forest, k-nearest neighbor (KNN), support vector machine, gradient boosting decision tree, extreme gradient boosting, and light gradient boosting machine, were used to construct models for predicating LVI status in BC. The area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity were used to evaluate the performance of the models.

RESULTS

Eighteen radiomic features were retained to construct the radiomic signature. Among the eight machine learning algorithms, the KNN model demonstrated superior performance to the other models in assessing the LVI status of patients with BC, with an accuracy of 0.696 and 0.642 in training and validation sets, respectively.

CONCLUSION

The eight machine learning models based on MRI radiomics serve as reliable indicators for identifying LVI status, and the KNN model demonstrated superior performance.This model offers substantial clinical utility, facilitating timely intervention in invasive BC and ultimately aiming to enhance patient survival rates.

MRI Radiomics-Based Machine Learning to Predict Lymphovascular Invasion of HER2-Positive Breast Cancer

This study aims to develop and prospectively validate radiomic models based on MRI to predict lymphovascular invasion (LVI) status in patients with HER2-positive breast cancer. A total of 225 patients with HER2-positive breast cancer who preoperatively underwent breast MRI were selected, forming the training set (n = 99 LVI-positive, n = 126 LVI-negative). A prospective validation cohort included 130 patients with breast cancer from the Affiliated Zhongshan Hospital of Dalian University (n = 57 LVI-positive, n = 73 LVI-negative). A total of 390 radiomic features and eight conventional radiological characteristics were extracted. For the optimum feature selection phase, the LASSO regression model with tenfold cross-validation (CV) was employed to identify features with non-zero coefficients. The conventional radiological (CR) model was determined based on visual morphological (VM) features and the optimal radiomic features correlated with LVI, identified through multivariate logistic analyses. Subsequently, various machine learning (ML) models were developed using algorithms such as support vector machine (SVM), k-nearest neighbor (KNN), gradient boosting machine (GBM), and random forest (RF). The performance of ML and CR models. The results show that the AUC of the CR model in the training and validation sets were 0.81 (95% confidence interval [CI], 0.74-0.86) and 0.82 (95% CI, 0.69-0.89), respectively. The ML model achieved the best performance, with AUCs of 0.96 (95% CI, 0.99-1.00) in the training set and 0.95 (95% CI, 0.89-0.96) in the validation set. There were significant differences between the CR and ML models in predicting LVI status. Our study demonstrated that the machine learning models exhibited superior performance in predicting LVI status based on pretreatment MRI compared to the CR model, which does not necessarily rely on a priori knowledge of visual morphology.

Exploring habitats-based spatial distributions: improving predictions of lymphovascular invasion in invasive breast cancer

RATIONALE AND OBJECTIVES

Accurate assessment of lymphovascular invasion (LVI) in invasive breast cancer (IBC) plays a pivotal role in tailoring personalized treatment plans. This study aimed to investigate habitats-based spatial distributions to quantitatively measure tumor heterogeneity on multiparametric magnetic resonance imaging (MRI) scans and assess their predictive capability for LVI in patients with IBC.

MATERIALS AND METHODS

In this retrospective cohort study, we consecutively enrolled 241 women diagnosed with IBC between July 2020 and July 2023 and who had 1.5 T/T1-weighted images, fat-suppressed T2-weighted images, and dynamic contrast-enhanced MRI. Habitats-based spatial distributions were derived from the gross tumor volume (GTV) and gross tumor volume plus peritumoral volume (GPTV). GTV_habitats and GPTV_habitats were generated through sub-region segmentation, and their performances were compared. Subsequently, a combined nomogram was developed by integrating relevant spatial distributions with the identified MR morphological characteristics. Diagnostic performance was compared using receiver operating characteristic curve analysis and decision curve analysis. Statistical significance was set at p < 0.05.

RESULTS

GPTV_habitats exhibited superior performance compared to GTV_habitats. Consequently, the GPTV_habitats, diffusion-weighted imaging rim signs, and peritumoral edema were integrated to formulate the combined nomogram. This combined nomogram outperformed individual MR morphological characteristics and the GPTV_habitats index, achieving area under the curve values of 0.903 (0.847 -0.959), 0.770 (0.689 -0.852), and 0.843 (0.776 -0.910) in the training set and 0.931 (0.863 -0.999), 0.747 (0.613 -0.880), and 0.849 (0.759 -0.938) in the validation set.

CONCLUSION

The combined nomogram incorporating the GPTV_habitats and identified MR morphological characteristics can effectively predict LVI in patients with IBC.

Prediction of lymphovascular invasion in invasive breast cancer based on clinical-MRI radiomics features

OBJECTIVE

We aim to develop a predictive model for lymphovascular invasion (LVI) in patients with invasive breast cancer (IBC), using magnetic resonance imaging (MRI)-based radiomics features.

METHODS

A total of 204 patients with IBC admitted to our hospital were included in this retrospective study. The data was split into training and validation sets at a 7:3 ratio. Feature normalization was conducted, followed by feature selection using ANOVA, correlation analysis, and LASSO in the training set. The final step involved building a logistic regression model. The LVI prediction models were established by single sequence image and combined different sequence images as follows: A: prediction model based on the optimal sequence in the 7-phase enhanced MRI scans; B: prediction model based on the optimal sequences in the sequences T1WI, T2WI, and DWI; and C: the combined model based on the optimal sequences selected from A and B. Subjects' work characteristic curves (ROC) and decision curves (DCA) were plotted to determine the extent to which they predicted LVI performance in the training and validation sets. Simultaneously, nomogram models were constructed by integrating radiomics features and independent risk factors. In addition, an additional 16 patients from the center between January and August 2024 were collected as the Nomogram external validation set. The ROC and DCA were used to evaluate the performance of the model.

RESULTS

In the enhanced images, Model A built based on the enhanced 2-phase achieved the best average AUC, with a validation set of 0.764. Model B built based on the T2WI had better results, with a validation set of 0.693. Model C built by combining enhanced 2-phase and T2WI sequences had a mean AUC of 0.705 in the validation set. In addition, the tumor size, whether the tumor boundary was clear or not, and whether there was a coelom in the tumor tissue had a statistically significant effect on the LVI of IBC, and a clinical-radiomics nomogram was established. DCAs as well as Nomogram also indicate that Model A has good clinical utility. The AUC of the nomogram in the training set, internal validation set, and external validation set were 0.703, 0.615, and 0.609, respectively. The DCA also showed that the radiomics nomogram combined with clinical factors had good predictive ability for LVI.

CONCLUSION

In IBC, MRI radiomics can serve as a noninvasive predictor of LVI. The clinical-MRI radiomics model, as an efficient visual prognostic tool, shows promise in forecasting LVI. This highlights the significant potential of pre-radiomics prediction in enhancing treatment strategies.

Machine learning based on optimal VOI of multi-sequence MR images to predict lymphovascular invasion in invasive breast cancer

Objectives

Lymphovascular invasion serves as a crucial prognostic indicator in invasive breast cancer, influencing treatment decisions. We aimed to develop a machine learning model utilizing optimal volumes of interest extracted from multisequence magnetic resonance images to predict lymphovascular invasion in patients with invasive breast cancer.

Materials and methods

This study comprised 191 patients postoperatively diagnosed with invasive breast cancer through multi-sequence magnetic resonance imaging. Independent predictors were identified through univariate and multivariate logistic regression analyses, culminating in the construction of a clinical model. Radiomic features were extracted from multi-sequence magnetic resonance imaging images across various volume of interest scales (-2 mm, entire, +2 mm, +4 mm, and +6 mm). Subsequently, various radiomic models were developed using machine learning model algorithms, including logistic regression, support vector machine, k-nearest neighbor, gradient boosting machine, classification and regression tree, and random forest. A hybrid model was then formulated, amalgamating optimal radiomic and clinical models.

Results

The area under the curve of the clinical model was 0.757. Among the radiomic models, the most efficient diagnosis was achieved by the k-nearest neighbor-based radiomics-volume of interest (+2 mm), resulting in an area under the curve of 0.780. The hybrid model, integrating the k-nearest neighbor-based radiomics-volume of interest (+2 mm), and the clinical model surpassed the individual clinical and radiomics models, exhibiting a superior area under the curve of 0.864.

Conclusion

Utilizing a hybrid approach integrating clinical data and multi-sequence magnetic resonance imaging-derived radiomics models based on the multiscale tumor region volume of interest (+2 mm) proved effective in determining lymphovascular invasion status in patients with invasive breast cancer. This innovative methodology may offer valuable insights for treatment planning and disease management.

Prediction of the benign and malignant nature of masses in COPD background based on Habitat-based enhanced CT radiomics modeling: A preliminary study

BACKGROUND

It is difficult to differentiate between chronic obstructive pulmonary disease (COPD)-peripheral bronchogenic carcinoma (COPD-PBC) and inflammatory masses.

OBJECTIVE

This study aims to predict COPD-PBC based on clinical data and preoperative Habitat-based enhanced CT radiomics (HECT radiomics) modeling.

METHODS

A retrospective analysis was conducted on clinical imaging data of 232 cases of postoperative pathological confirmed PBC or inflammatory masses. The PBC group consisted of 82 cases, while the non-PBC group consisted of 150 cases. A training set and a testing set were established using a 7:3 ratio and a time cutoff point. In the training set, multiple models were established using clinical data and radiomics texture changes within different enhanced areas of the CT mass (HECT radiomics). The AUC values of each model were compared using Delong's test, and the clinical net benefit of the models was tested using decision curve analysis (DCA). The models were then externally validated in the testing set, and a nomogram of predicting COPD-PBC was created.

RESULTS

Univariate analysis confirmed that female gender, tumor morphology, CEA, Cyfra21-1, CT enhancement pattern, and Habitat-Radscore B/C were predictive factors for COPD-PBC (P< 0.05). The combination model based on these factors had significantly higher predictive performance [AUC: 0.894, 95% CI (0.836-0.936)] than the clinical data model [AUC: 0.758, 95% CI (0.685-0.822)] and radiomics model [AUC: 0.828, 95% CI (0.761-0.882)]. DCA also confirmed the higher clinical net benefit of the combination model, which was validated in the testing set. The nomogram developed based on the combination model helped predict COPD-PBC.

CONCLUSION

The combination model based on clinical data and Habitat-based enhanced CT radiomics can help differentiate COPD-PBC, providing a new non-invasive and efficient method for its diagnosis, treatment, and clinical decision-making.