Predictive value of the time-intensity curves on dynamic contrast-enhanced magnetic resonance imaging for lymphatic spreading in breast cancer

Prediction of Lymphovascular invasion status in breast cancer based on magnetic resonance imaging radiomics features

OBJECTIVE

This study intended to investigate the feasibility and effectiveness of using clinical magnetic resonance imaging (MRI) radiomics features to predict lymphovascular invasion (LVI) status in breast cancer (BC) patients.

METHODS

A total of 182 BC patients were retrospectively collected and randomly divided into a training set (n = 127) and a validation set (n = 55) in a 7:3 ratio. Based on pathological examination results, the training set was further divided into LVI group (n = 60) and non-LVI group (n = 67), and the validation set was divided into LVI group (n = 24) and non-LVI group (n = 31). General data and MRI examination indicators were compared. Multivariate logistic regression was utilized to analyze MRI radiomics features and clinically relevant indicators that were significant in the baseline information of patients in training set, independent risk factors were identified, and a logistic regression model was built. The accuracy of logistic model was validated using ROC curves in training and validation sets.

RESULTS

Age, pathohistological classification, tumor length, tumor width, presence or absence of Magnetic Resonance Spectroscopy (MRS) cho peak, presence or absence of spicule sign, peritumoral enhancement, and peritumoral edema were statistically significant (P < 0.05) between the two groups. Multivariate logistic regression analysis presented that spicule and peritumoral edema were independent risk factors for LVI in BC patients (P < 0.05). The ROC curve illustrated that AUC of the logistic regression model in the training set was 0.807 (95%CI: 0.730-0.885) and that in the validation set was 0.837 (95%CI: 0.731-0.944).

CONCLUSION

Radiomics features of spicule sign and peritumoral edema were independent risk factors for LVI in BC patients. A logistic regression model based on these factors, along with age, could accurately predict LVI occurrence in BC patients, providing data support for diagnosis and modeling of LVI in BC patients.

MRI Radiomics of Breast Cancer: Machine Learning-Based Prediction of Lymphovascular Invasion Status

RATIONALE AND OBJECTIVES

In patients with breast cancer (BC), lymphovascular invasion (LVI) status is considered an important prognostic factor. We aimed to develop machine learning (ML)-based radiomics models for the prediction of LVI status in patients with BC, using preoperative MRI images.

MATERIALS AND METHODS

This retrospective study included patients with BC with known LVI status and preoperative MRI. The dataset was split into training and unseen testing sets by stratified sampling with a 2:1 ratio. 2D and 3D radiomic features were extracted from contrast-enhanced T1 weighted images (C+T1W) and apparent diffusion coefficient (ADC) maps. The reliability of the features was assessed with two radiologists' segmentation data. Dimension reduction was done with reliability analysis, multi-collinearity analysis, removal of low-variance features, and feature selection. ML models were created with base, tuned, and boosted random forest algorithms.

RESULT

A total of 128 lesions (LVI-positive, 76; LVI-negative, 52) were included. The best model performance was achieved with tunning and boosting model based on 3D ADC maps and selected four radiomic features. The area under the curve and accuracy were 0.726 and 63.5% in the training data, 0.732 and 76.7% in the test data, respectively. The overall sensitivity and positive predictive values were 68% and 69.6% in the training data, 84.6% and 78.6% in the test data, respectively.

CONCLUSION

ML and radiomics based on 3D segmentation of ADC maps can be used to predict LVI status in BC, with satisfying performance.

Development of a risk-stratification scoring system for predicting lymphovascular invasion in breast cancer

Background

Lymphovascular invasion (LVI) is a vital risk factor for prognosis across cancers. We aimed to develop a scoring system for stratifying LVI risk in patients with breast cancer.

Methods

A total of 301 consecutive patients (mean age, 49.8 ± 11.0 years; range, 29–86 years) with breast cancer confirmed by pathological reports were retrospectively evaluated at the authors’ institution between June 2015 and October 2018. All patients underwent contrast-enhanced Magnetic Resonance Imaging (MRI) examinations before surgery. MRI findings and histopathologic characteristics of tumors were collected for analysis. Breast LVI was confirmed by postoperative pathology. We used a stepwise logistic regression to select variables and two cut-points were determined to create a three-tier risk-stratification scoring system. The patients were classified as having low, moderate and high probability of LVI. The area under the receiver operating characteristic curve (AUC) was used to evaluate the discrimination ability of the scoring system.

Results

Tumor margins, lobulation sign, diffusion-weighted imaging appearance, MRI-reported axillary lymph node metastasis, time to signal intensity curve pattern, and HER-2 were selected as predictors for LVI in the point-based scoring system. Patients were considered at low risk if the score was < 3.5, moderate risk if the score was 3.5 to 6.0, and high risk if the score was ≥6.0. LVI risk was segmented from 0 to 100.0% and was positively associated with an increase in risk scores. The AUC of the scoring system was 0.824 (95% confidence interval [CI]: 0.776--0.872).

Conclusion

This study shows that a simple and reliable score-based risk-stratification system can be practically used in stratifying the risk of LVI in breast cancer.

Imaging the lymphatic system

Visualization of the lymphatic system is clinically necessary during diagnosis or treatment of many conditions and diseases; it is used for identifying and monitoring lymphedema, for detecting metastatic lesions during cancer staging and for locating lymphatic structures so they can be spared during surgical procedures. Imaging lymphatic anatomy and function also plays an important role in experimental studies of lymphatic development and function, where spatial resolution and accessibility are better. Here, we review technologies for visualizing and imaging the lymphatic system for clinical applications. We then describe the use of lymphatic imaging in experimental systems as well as some of the emerging technologies for improving these methodologies.

Design study of a high-resolution breast-dedicated PET system built from cadmium zinc telluride detectors

We studied the performance of a dual-panel positron emission tomography (PET) camera dedicated to breast cancer imaging using Monte Carlo simulation. The proposed system consists of two 4 cm thick 12 x 15 cm(2) area cadmium zinc telluride (CZT) panels with adjustable separation, which can be put in close proximity to the breast and/or axillary nodes. Unique characteristics distinguishing the proposed system from previous efforts in breast-dedicated PET instrumentation are the deployment of CZT detectors with superior spatial and energy resolution, using a cross-strip electrode readout scheme to enable 3D positioning of individual photon interaction coordinates in the CZT, which includes directly measured photon depth-of-interaction (DOI), and arranging the detector slabs edge-on with respect to incoming 511 keV photons for high photon sensitivity. The simulation results show that the proposed CZT dual-panel PET system is able to achieve superior performance in terms of photon sensitivity, noise equivalent count rate, spatial resolution and lesion visualization. The proposed system is expected to achieve approximately 32% photon sensitivity for a point source at the center and a 4 cm panel separation. For a simplified breast phantom adjacent to heart and torso compartments, the peak noise equivalent count (NEC) rate is predicted to be approximately 94.2 kcts s(-1) (breast volume: 720 cm(3) and activity concentration: 3.7 kBq cm(-3)) for a approximately 10% energy window around 511 keV and approximately 8 ns coincidence time window. The system achieves 1 mm intrinsic spatial resolution anywhere between the two panels with a 4 cm panel separation if the detectors have DOI resolution less than 2 mm. For a 3 mm DOI resolution, the system exhibits excellent sphere resolution uniformity (sigma(rms)/mean) < or = 10%) across a 4 cm width FOV. Simulation results indicate that the system exhibits superior hot sphere visualization and is expected to visualize 2 mm diameter spheres with a 5:1 activity concentration ratio within roughly 7 min imaging time. Furthermore, we observe that the degree of spatial resolution degradation along the direction orthogonal to the two panels that is typical of a limited angle tomography configuration is mitigated by having high-resolution DOI capabilities that enable more accurate positioning of oblique response lines.

Angle between 1 and 4 min gives the most significant difference in time-intensity curves between benign disease and breast cancer: analysis of dynamic magnetic resonance imaging in 103 patients with breast lesions

The aim of the present study was to clarify the morphologic characteristics of time-intensity curves (TICs) that are useful for distinguishing benign from malignant lesions. One hundred three patients with breast lesions underwent dynamic breast MRI. The areas under the receiver operating characteristic (ROC) curves (AUC) from every component of TIC were compared between benign and malignant disease. As a result, angle of cross line between 1 and 4 min is more useful than rapid enhancement for distinguishing benign from malignant lesions.