Diffusion-weighted Breast MRI in Prediction of Upstaging in Women with Biopsy-proven Ductal Carcinoma in Situ

Presurgical Upgrade Prediction of DCIS to Invasive Ductal Carcinoma Using Time-dependent Deep Learning Models with DCE MRI

Purpose To determine whether time-dependent deep learning models can outperform single time point models in predicting preoperative upgrade of ductal carcinoma in situ (DCIS) to invasive malignancy at dynamic contrast-enhanced (DCE) breast MRI without a lesion segmentation prerequisite. Materials and Methods In this exploratory study, 154 cases of biopsy-proven DCIS (25 upgraded at surgery and 129 not upgraded) were selected consecutively from a retrospective cohort of preoperative DCE MRI in women with a mean age of 59 years at time of diagnosis from 2012 to 2022. Binary classification was implemented with convolutional neural network (CNN)-long short-term memory (LSTM) architectures benchmarked against traditional CNNs without manual segmentation of the lesions. Combinatorial performance analysis of ResNet50 versus VGG16-based models was performed with each contrast phase. Binary classification area under the receiver operating characteristic curve (AUC) was reported. Results VGG16-based models consistently provided better holdout test AUCs than did ResNet50 in CNN and CNN-LSTM studies (multiphase test AUC, 0.67 vs 0.59, respectively, for CNN models [P = .04] and 0.73 vs 0.62 for CNN-LSTM models [P = .008]). The time-dependent model (CNN-LSTM) provided a better multiphase test AUC over single time point (CNN) models (0.73 vs 0.67; P = .04). Conclusion Compared with single time point architectures, sequential deep learning algorithms using preoperative DCE MRI improved prediction of DCIS lesions upgraded to invasive malignancy without the need for lesion segmentation. Keywords: MRI, Dynamic Contrast-enhanced, Breast, Convolutional Neural Network (CNN) Supplemental material is available for this article. © RSNA, 2024.

The Diagnostic Value of Conventional MRI Combined With Diffusion-Weighted Imaging in Microprolactinomas

BACKGROUND

Turbo spin-echo (TSE) diffusion-weighted imaging (DWI) sequences may reduce susceptibility artifacts and image distortion in sellar region, allowing better visualization of small pituitary lesions, and may be used to assist in the diagnosis of pituitary microadenomas.

PURPOSE

To explore the application value of conventional MRI combined with DWI sequences in the diagnosis of microprolactinomas.

STUDY TYPE

Prospective.

POPULATION

Thirty-four patients in microprolactinomas with high signal on T2WI (HT2-PRL) group (34 females, 34 ± 7 years), 26 patients in microprolactinomas with equal or low signal on T2WI (ELT2-PRL) group (21 females, 34 ± 7 years), 35 patients with hyperprolactinemia (33 females, 32 ± 8 years), and 30 normal controls (25 females, 31 ± 7 years).

FIELD STRENGTH/SEQUENCE

TSE sequence at 3 T.

ASSESSMENT

Pituitary morphological parameters (such as length and volume), dynamic contrast-enhanced parameters (such as time to peak) and the apparent diffusion coefficients (ADCs) were measured in each group.

STATISTICAL TESTS

ANOVA and Mann-Whitney U test were used to compare parameters among groups. Spearman's coefficient was used to evaluate the correlation between variables. ROC analysis was used to assess the performance of the parameters. A P-value <0.05 was considered statistically significant.

RESULTS

The pituitary volume of patients in HT2-PRL, ELT2-PRL, and hyperprolactinemia group were 831.00 (747.60, 887.60), 923.63 ± 219.34, and 737.20 (606.40, 836.80) mm3. The pituitary maximum height in these three groups were 7.03 (6.43, 8.63), 8.03 ± 1.41, and 6.63 ± 1.28 mm, respectively. The lesion ADC value was significantly correlated with T2 relative signal intensity (the ratio of signal intensity of microprolactinoma or anterior pituitary to left temporal cortex) (r = 0.821). Compared with patients with hyperprolactinemia, the diagnostic efficacy of T2 relative signal intensity was higher in HT2-PRL group, with an AUC of 0.954, whereas the ADC value was the highest in ELT2-PRL group, with an AUC of 0.924.

CONCLUSION

DWI sequences can be used to assist in the diagnosis of pituitary microadenomas.

EVIDENCE LEVEL

1 TECHNICAL EFFICACY: Stage 2.

Non-contrast Breast MR Imaging

Considering the high cost of dynamic contrast-enhanced MR imaging and various contraindications and health concerns related to administration of intravenous gadolinium-based contrast agents, there is emerging interest in non-contrast-enhanced breast MR imaging. Diffusion-weighted MR imaging (DWI) is a fast, unenhanced technique that has wide clinical applications in breast cancer detection, characterization, prognosis, and predicting treatment response. It also has the potential to serve as a non-contrast MR imaging screening method. Standardized protocols and interpretation strategies can help to enhance the clinical utility of breast DWI. A variety of other promising non-contrast MR imaging techniques are in development, but currently, DWI is closest to clinical integration, while others are still mostly used in the research setting.

Could breast multiparametric MRI discriminate between pure ductal carcinoma in situ and microinvasive carcinoma?

BACKGROUND

Ductal carcinoma in situ (DCIS) is often reclassified as invasive cancer in the final pathology report of the surgical specimen. It is of significant clinical relevance to acknowledge the possibility of underestimating invasive disease when utilizing preoperative biopsies for a DCIS diagnosis. In cases where such histologic upgrades occur, it is imperative to consider them in the preoperative planning process, including the potential inclusion of sentinel lymph node biopsy due to the risk of axillary lymph node metastasis.

PURPOSE

To assess the capability of breast multiparametric magnetic resonance imaging (MP-MRI) in differentiating between pure DCIS and microinvasive carcinoma (MIC).

MATERIAL AND METHODS

Between January 2018 and November 2022, this retrospective study enrolled patients with biopsy-proven DCIS who had undergone preoperative breast MP-MRI. We assessed various MP-MRI features, including size, morphology, margins, internal enhancement pattern, extent of disease, presence of peritumoral edema, time-intensity curve value, diffusion restriction, and ADC value. Subsequently, a logistic regression analysis was conducted to explore the association of these features with the pathological outcome.

RESULTS

Of 129 patients with biopsy-proven DCIS, 36 had foci of micro-infiltration on surgical specimens and eight were diagnosed with invasive ductal carcinoma (IDC). The presence of micro-infiltration foci was significantly associated with several MP-MRI features, including tumor size (P <0.001), clustered ring enhancement (P <0.001), segmental distribution (P <0.001), diffusion restriction (P = 0.005), and ADC values <1.3 × 10-3 mm2/s (P = 0.004).

CONCLUSION

Breast MP-MRI has the potential to predict the presence of micro-infiltration foci in biopsy-proven DCIS and may serve as a valuable tool for guiding therapeutic planning.

The features associated with mammography-occult MRI-detected newly diagnosed breast cancer analysed by comparing machine learning models with a logistic regression model

PURPOSE

To compare machine learning (ML) models with logistic regression model in order to identify the optimal factors associated with mammography-occult (i.e. false-negative mammographic findings) magnetic resonance imaging (MRI)-detected newly diagnosed breast cancer (BC).

MATERIAL AND METHODS

The present single-centre retrospective study included consecutive women with BC who underwent mammography and MRI (no more than 45 days apart) for breast cancer between January 2018 and May 2023. Various ML algorithms and binary logistic regression analysis were utilized to extract features linked to mammography-occult BC. These features were subsequently employed to create different models. The predictive value of these models was assessed using receiver operating characteristic curve analysis.

RESULTS

This study included 1957 malignant lesions from 1914 patients, with an average age of 51.64 ± 9.92 years and a range of 20-86 years. Among these lesions, there were 485 mammography-occult BCs. The optimal features of mammography-occult BC included calcification status, tumour size, mammographic density, age, lesion enhancement type on MRI, and histological type. Among the different ML models (ANN, L1-LR, RF, and SVM) and the LR-based combined model, the ANN model with RF features was found to be the optimal model. It demonstrated the best discriminative performance in predicting mammography false- negative findings, with an AUC of 0.912, an accuracy of 86.90%, a sensitivity of 85.85%, and a specificity of 84.18%.

CONCLUSION

Mammography-occult MRI-detected breast cancers have features that should be considered when performing breast MRI to improve the detection rate for breast cancer and aid in clinician management.

Development of a Multi-Parametric ultrasonography nomogram for prediction of invasiveness in ductal carcinoma in situ

OBJECTIVE

To investigate the independent risk variables associated with the potential invasiveness of ductal carcinoma in situ (DCIS) on multi-parametric ultrasonography, and further construct a nomogram for risk assessment.

METHODS

Consecutive patients from January 2017 to December 2022 who were suspected of having ductal carcinoma in situ (DCIS) based on magnetic resonance imaging or mammography were prospectively enrolled. Histopathological findings after surgical resection served as the gold standard. Grayscale ultrasound, Doppler ultrasound, shear wave elastography (SWE), and contrast-enhanced ultrasound (CEUS) examinations were preoperative performed. Binary logistic regression was used for multifactorial analysis to identify independent risk factors from multi-parametric ultrasonography. The correlation between independent risk factors and pathological prognostic markers was analyzed. The predictive efficacy of DCIS associated with invasiveness was assessed by logistic analysis, and a nomogram was established.

RESULTS

A total of 250 DCIS lesions were enrolled from 249 patients, comprising 85 pure DCIS and 165 DCIS with invasion (DCIS-IDC), of which 41 exhibited micro-invasion. The multivariate analysis identified independent risk factors for DCIS with invasion on multi-parametric ultrasonography, including image size (>2cm), Doppler ultrasound RI (≥0.72), SWE's Emax (≥66.4 kPa), hyper-enhancement, centripetal enhancement, increased surrounding vessel, and no contrast agent retention on CEUS. These factors correlated with histological grade, Ki-67, and human epidermal growth factor receptor 2 (HER2) (P < 0.1). The multi-parametric ultrasound approach demonstrated good predictive performance (sensitivity 89.7 %, specificity 73.8 %, AUC 0.903), surpassing single US modality or combinations with SWE or CEUS modalities. Utilizing these factors, a predictive nomogram achieved a respectable performance (AUC of 0.889) for predicting DCIS with invasion. Additionally, a separate nomogram for predicting DCIS with micro-invasion, incorporating independent risk factors such as RI (≥0.72), SWE's Emax (≥65.2 kPa), and centripetal enhancement, demonstrated an AUC of 0.867.

CONCLUSION

Multi-parametric ultrasonography demonstrates good discriminatory ability in predicting both DCIS with invasion and micro-invasion through the analysis of lesion morphology, stiffness, neovascular architecture, and perfusion. The use of a nomogram based on ultrasonographic images offers an intuitive and effective method for assessing the risk of invasion in DCIS. Although the nomogram is not currently considered a clinically applicable diagnostic tool due to its AUC being below the threshold of 0.9, further research and development are anticipated to yield positive outcomes and enhance its viability for clinical utilization.

An MRI-Based Radiomics Nomogram to Distinguish Ductal Carcinoma In Situ with Microinvasion From Ductal Carcinoma In Situ of Breast Cancer

RATIONALE AND OBJECTIVES

Accurate preoperative differentiation between ductal carcinoma in situ with microinvasion (DCISM) and ductal carcinoma in situ (DCIS) could facilitate treatment optimization and individualized risk assessment. The present study aims to build and validate a radiomics nomogram based on dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) that could distinguish DCISM from pure DCIS breast cancer.

MATERIALS AND METHODS

MR images of 140 patients obtained between March 2019 and November 2022 at our institution were included. Patients were randomly divided into a training (n = 97) and a test set (n = 43). Patients in both sets were further split into DCIS and DCISM subgroups. The independent clinical risk factors were selected by multivariate logistic regression to establish the clinical model. The optimal radiomics features were chosen by the least absolute shrinkage and selection operator, and a radiomics signature was built. The nomogram model was constructed by integrating the radiomics signature and independent risk factors. The discrimination efficacy of our nomogram was assessed by using calibration and decision curves.

RESULTS

Six features were selected to construct the radiomics signature for distinguishing DCISM from DCIS. The radiomics signature and nomogram model exhibited better calibration and validation performance in the training (AUC 0.815, 0.911, 95% confidence interval [CI], 0.703-0.926, 0.848-0.974) and test (AUC 0.830, 0.882, 95% CI, 0.672-0.989, 0.764-0.999) sets than in the clinical factor model (AUC 0.672, 0.717, 95% CI, 0.544-0.801, 0.527-0.907). The decision curve also demonstrated that the nomogram model exhibited good clinical utility.

CONCLUSION

The proposed noninvasive MRI-based radiomics nomogram model showed good performance in distinguishing DCISM from DCIS.

Prediction of the histologic upgrade of ductal carcinoma in situ using a combined radiomics and machine learning approach based on breast dynamic contrast-enhanced magnetic resonance imaging

Objective

To investigate whether support vector machine (SVM) trained with radiomics features based on breast magnetic resonance imaging (MRI) could predict the upgrade of ductal carcinoma in situ (DCIS) diagnosed by core needle biopsy (CNB) after surgical excision.

Materials and methods

This retrospective study included a total of 349 lesions from 346 female patients (mean age, 54 years) diagnosed with DCIS by CNB between January 2011 and December 2017. Based on histological confirmation after surgery, the patients were divided into pure (n = 198, 56.7%) and upgraded DCIS (n = 151, 43.3%). The entire dataset was randomly split to training (80%) and test sets (20%). Radiomics features were extracted from the intratumor region-of-interest, which was semi-automatically drawn by two radiologists, based on the first subtraction images from dynamic contrast-enhanced T1-weighted MRI. A least absolute shrinkage and selection operator (LASSO) was used for feature selection. A 4-fold cross validation was applied to the training set to determine the combination of features used to train SVM for classification between pure and upgraded DCIS. Sensitivity, specificity, accuracy, and area under the receiver-operating characteristic curve (AUC) were calculated to evaluate the model performance using the hold-out test set.

Results

The model trained with 9 features (Energy, Skewness, Surface Area to Volume ratio, Gray Level Non Uniformity, Kurtosis, Dependence Variance, Maximum 2D diameter Column, Sphericity, and Large Area Emphasis) demonstrated the highest 4-fold mean validation accuracy and AUC of 0.724 (95% CI, 0.619–0.829) and 0.742 (0.623–0.860), respectively. Sensitivity, specificity, accuracy, and AUC using the test set were 0.733 (0.575–0.892) and 0.7 (0.558–0.842), 0.714 (0.608–0.820) and 0.767 (0.651–0.882), respectively.

Conclusion

Our study suggested that the combined radiomics and machine learning approach based on preoperative breast MRI may provide an assisting tool to predict the histologic upgrade of DCIS.