Mammography-based radiomic analysis for predicting benign BI-RADS category 4 calcifications

Interpretable Radiomic Signature for Breast Microcalcification Detection and Classification

Breast microcalcifications are observed in 80% of mammograms, and a notable proportion can lead to invasive tumors. However, diagnosing microcalcifications is a highly complicated and error-prone process due to their diverse sizes, shapes, and subtle variations. In this study, we propose a radiomic signature that effectively differentiates between healthy tissue, benign microcalcifications, and malignant microcalcifications. Radiomic features were extracted from a proprietary dataset, composed of 380 healthy tissue, 136 benign, and 242 malignant microcalcifications ROIs. Subsequently, two distinct signatures were selected to differentiate between healthy tissue and microcalcifications (detection task) and between benign and malignant microcalcifications (classification task). Machine learning models, namely Support Vector Machine, Random Forest, and XGBoost, were employed as classifiers. The shared signature selected for both tasks was then used to train a multi-class model capable of simultaneously classifying healthy, benign, and malignant ROIs. A significant overlap was discovered between the detection and classification signatures. The performance of the models was highly promising, with XGBoost exhibiting an AUC-ROC of 0.830, 0.856, and 0.876 for healthy, benign, and malignant microcalcifications classification, respectively. The intrinsic interpretability of radiomic features, and the use of the Mean Score Decrease method for model introspection, enabled models' clinical validation. In fact, the most important features, namely GLCM Contrast, FO Minimum and FO Entropy, were compared and found important in other studies on breast cancer.

Improving the malignancy prediction of breast cancer based on the integration of radiomics features from dual-view mammography and clinical parameters

Radiomics has been a promising imaging biomarker for many malignant diseases. We developed a novel radiomics strategy that incorporating radiomics features extracted from dual-view mammograms and clinical parameters for identifying benign and malignant breast lesions, and validated whether the radiomics assessment could improve the accurate diagnosis of breast cancer. A total of 380 patients (mean age, 52 ± 7 years) with 621 breast lesions utilizing mammograms on craniocaudal (CC) and mediolateral oblique (MLO) views were randomly allocated into the training (n = 486) and testing (n = 135) sets in this retrospective study. A total of 1184 and 2368 radiomics features were extracted from single-position region of interest (ROI) and position-paired ROI, separately. Clinical parameters were then combined for better prediction. Recursive feature elimination and least absolute shrinkage and selection operator methods were applied to select optimal predictive features. Random forest was used to conduct the predictive model. Intraclass correlation coefficient test was used to assess repeatability and reproducibility of features. After preprocessing, 467 radiomics features and clinical parameters remained in the single-view and dual-view models. The performance and significance of models were quantified by the area under the curve (AUC), sensitivity, specificity, and accuracy. The correlation analysis between variables was evaluated using the correlation ratio and Pearson correlation coefficient. The model using a combination of dual-view radiomics and clinical parameters achieved a favorable performance (AUC: 0.804, 95% CI: 0.668-0.916), outperformed single-view model and model without clinical parameters. Incorporating with radiomics features of dual-view (CC&MLO) mammogram, age, breast density, and type of suspicious lesions can provide a noninvasive approach to evaluate the malignancy of breast lesions and facilitate clinical decision-making.

Techniques to produce and evaluate realistic multivariate synthetic data

Data modeling requires a sufficient sample size for reproducibility. A small sample size can inhibit model evaluation. A synthetic data generation technique addressing this small sample size problem is evaluated: from the space of arbitrarily distributed samples, a subgroup (class) has a latent multivariate normal characteristic; synthetic data can be generated from this class with univariate kernel density estimation (KDE); and synthetic samples are statistically like their respective samples. Three samples (n = 667) were investigated with 10 input variables (X). KDE was used to augment the sample size in X. Maps produced univariate normal variables in Y. Principal component analysis in Y produced uncorrelated variables in T, where the probability density functions were approximated as normal and characterized; synthetic data was generated with normally distributed univariate random variables in T. Reversing each step produced synthetic data in Y and X. All samples were approximately multivariate normal in Y, permitting the generation of synthetic data. Probability density function and covariance comparisons showed similarity between samples and synthetic samples. A class of samples has a latent normal characteristic. For such samples, this approach offers a solution to the small sample size problem. Further studies are required to understand this latent class.

Attention-based deep learning for breast lesions classification on contrast enhanced spectral mammography: a multicentre study

BACKGROUND

This study aims to develop an attention-based deep learning model for distinguishing benign from malignant breast lesions on CESM.

METHODS

Preoperative CESM images of 1239 patients, which were definitely diagnosed on pathology in a multicentre cohort, were divided into training and validation sets, internal and external test sets. The regions of interest of the breast lesions were outlined manually by a senior radiologist. We adopted three conventional convolutional neural networks (CNNs), namely, DenseNet 121, Xception, and ResNet 50, as the backbone architectures and incorporated the convolutional block attention module (CBAM) into them for classification. The performance of the models was analysed in terms of the receiver operating characteristic (ROC) curve, accuracy, the positive predictive value (PPV), the negative predictive value (NPV), the F1 score, the precision recall curve (PRC), and heat maps. The final models were compared with the diagnostic performance of conventional CNNs, radiomics models, and two radiologists with specialised breast imaging experience.

RESULTS

The best-performing deep learning model, that is, the CBAM-based Xception, achieved an area under the ROC curve (AUC) of 0.970, a sensitivity of 0.848, a specificity of 1.000, and an accuracy of 0.891 on the external test set, which was higher than those of other CNNs, radiomics models, and radiologists. The PRC and the heat maps also indicated the favourable predictive performance of the attention-based CNN model. The diagnostic performance of two radiologists improved with deep learning assistance.

CONCLUSIONS

Using an attention-based deep learning model based on CESM images can help to distinguishing benign from malignant breast lesions, and the diagnostic performance of radiologists improved with deep learning assistance.

Machine learning for multi-parametric breast MRI: radiomics-based approaches for lesion classification

In the artificial intelligence era, machine learning (ML) techniques have gained more and more importance in the advanced analysis of medical images in several fields of modern medicine. Radiomics extracts a huge number of medical imaging features revealing key components of tumor phenotype that can be linked to genomic pathways. The multi-dimensional nature of radiomics requires highly accurate and reliable machine-learning methods to create predictive models for classification or therapy response assessment.

Multi-parametric breast magnetic resonance imaging (MRI) is routinely used for dense breast imaging as well for screening in high-risk patients and has shown its potential to improve clinical diagnosis of breast cancer. For this reason, the application of ML techniques to breast MRI, in particular to multi-parametric imaging, is rapidly expanding and enhancing both diagnostic and prognostic power. In this review we will focus on the recent literature related to the use of ML in multi-parametric breast MRI for tumor classification and differentiation of molecular subtypes. Indeed, at present, different models and approaches have been employed for this task, requiring a detailed description of the advantages and drawbacks of each technique and a general overview of their performances.

A Radiomics Nomogram for Distinguishing Benign From Malignant Round-Like Breast Tumors

Objective

The objective of this study is to develop a radiomics nomogram for the presurgical distinction of benign and malignant round-like solid tumors.

Methods

This retrospective trial enrolled patients with round-like tumors who had received preoperative digital mammography (DM) no sooner than 20 days prior to surgery. Breast tumors were segmented manually on DM images in order to extract radiomic features. Four machine learning classification models were constructed, and their corresponding areas under the receiver operating characteristic (ROC) curves (AUCs) for differential tumor diagnosis were calculated. The optimal classifier was then selected for the validation set. After this, predictive machine learning models that employed radiomic features and/or patient features were applied for tumor assessment. The models' AUC, accuracy, negative (NPV) and positive (PPV) predictive values, sensitivity, and specificity were then derived.

Results

In total 129 cases with benign and malignant tumors confirmed by pathological analysis were enrolled in the study, including 91 and 38 in the training and test sets, respectively. The DM images yielded 1,370 features per patient. For the machine learning models, the Least Absolute Shrinkage and Selection Operator for Gradient Boosting Classifier turned out to be the optimal classifier (AUC=0.87, 95% CI 0.76-0.99), and ROC curves for the radiomics nomogram and the DM-only model were statistically different (P<0.001). The radiomics nomogram achieved an AUC of 0.90 (95% CI 0.80-1.00) in the test cohort and was statistically higher than the DM-based model (AUC=0.67, 95% CI 0.51-0.84). The radiomics nomogram was highly efficient in detecting malignancy, with accuracy, sensitivity, specificity, PPV, and NPV in the validation set of 0.868, 0.950, 0.778, 0.826, and 0.933, respectively.

Conclusions

This radiomics nomogram that combines radiomics signatures and clinical characteristics represents a noninvasive, cost-efficient presurgical prediction technique.

Comprehensive quantitative malignant risk prediction of pure grouped amorphous calcifications: clinico-mammographic nomogram

BACKGROUND

Pure grouped amorphous calcifications are classified as Breast Imaging Reporting and Data System (BI-RADS) category 4B suspicious calcifications and recommended for biopsy. However, the biopsies often reveal benign findings, especially in screening mammograms (92.4-97.2%).

METHODS

Mammograms of 699 pure grouped amorphous calcifications with final pathological results were analyzed in this retrospective study. The maximum span (MS) of the group of calcifications and the MS of the parallel/vertical direction of the mammary duct (MPS/MVS) were measured, and the MPS to MVS ratio was calculated. Based on the MS and ratio, 2 prediction nomograms with other clinic-mammographic features were developed. The discrimination performance of the models was assessed and compared by the area under the receiver operating characteristic curve (AUC). Scatterplots were created to determine the cutoff values with fewer misdiagnoses of malignant calcifications and fewer false positives.

RESULTS

Ultimately, 2 prediction models were successfully developed based on the 4 risk factors of age, purpose of the mammogram, whether multiple or single calcifications, and the MS [odds ratio (OR) =1.06, P=0.02]/ratio (OR =6.05, P<0.001). Both models had good discrimination. The ratio model performed better than the MS model in the training cohort (AUC of 0.875 and 0.834, respectively, P=0.003) and validation cohort (AUC 0.908 and 0.867, respectively, P=0.047). For the group with probably benign calcifications (as detected by the ratio nomogram), the malignancy rates were 2.7% [95% confidence interval (CI): 1.00% to 6.53%] and 1.19% (95% CI: 0.06% to 7.37%) in the training and validation cohorts, respectively, and 44.12% and 47.70% of benign biopsies were detected in the training and validation cohorts, respectively.

CONCLUSIONS

The clinico-mammographic quantitative malignancy risk prediction nomogram showed favorable discrimination and calibration performance. The ratio model showed better diagnostic efficiency than the MS model, and identified >40% of benign biopsies.

Radiomics Based on Digital Mammography Helps to Identify Mammographic Masses Suspicious for Cancer

Objectives

This study aims to build radiomics model of Breast Imaging Reporting and Data System (BI-RADS) category 4 and 5 mammographic masses extracted from digital mammography (DM) for mammographic masses characterization by using a sensitivity threshold similar to that of biopsy.

Materials and Methods

This retrospective study included 288 female patients (age, 52.41 ± 10.31) who had BI-RADS category 4 or 5 mammographic masses with an indication for biopsy. The patients were divided into two temporal set (training set, 82 malignancies and 110 benign lesions; independent test set, 48 malignancies and 48 benign lesions). A total of 188 radiomics features were extracted from mammographic masses on the combination of craniocaudal (CC) position images and mediolateral oblique (MLO) position images. For the training set, Pearson’s correlation and the least absolute shrinkage and selection operator (LASSO) were used to select non-redundant radiomics features and useful radiomics features, respectively, and support vector machine (SVM) was applied to construct a radiomics model. The receiver operating characteristic curve (ROC) analysis was used to evaluate the classification performance of the radiomics model and to determine a threshold value with a sensitivity higher than 98% to predict the mammographic masses malignancy. For independent test set, identical threshold value was used to validate the classification performance of the radiomics model. The stability of the radiomics model was evaluated by using a fivefold cross-validation method, and two breast radiologists assessed the diagnostic agreement of the radiomics model.

Results

In the training set, the radiomics model obtained an area under the receiver operating characteristic curve (AUC) of 0.934 [95% confidence intervals (95% CI), 0.898–0.971], a sensitivity of 98.8% (81/82), a threshold of 0.22, and a specificity of 60% (66/110). In the test set, the radiomics model obtained an AUC of 0.901 (95% CI, 0.835–0.961), a sensitivity of 95.8% (46/48), and a specificity of 66.7% (32/48). The radiomics model had relatively stable sensitivities in fivefold cross-validation (training set, 97.39% ± 3.9%; test set, 98.7% ± 4%).

Conclusion

The radiomics method based on DM may help reduce the temporarily unnecessary invasive biopsies for benign mammographic masses over-classified in BI-RADS category 4 and 5 while providing similar diagnostic performance for malignant mammographic masses as biopsies.

Radiomic Applications on Digital Breast Tomosynthesis of BI-RADS Category 4 Calcifications Sent for Vacuum-Assisted Breast Biopsy

Background: A fair amount of microcalcifications sent for biopsy are false positives. The study investigates whether quantitative radiomic features extracted from digital breast tomosynthesis (DBT) can be an additional and useful tool to discriminate between benign and malignant BI-RADS category 4 microcalcification. Methods: This retrospective study included 252 female patients with BI-RADS category 4 microcalcifications. The patients were divided into two groups according to micro-histopathology: 126 patients with benign lesions and 126 patients with certain or possible malignancies. A total of 91 radiomic features were extracted for each patient, and the 12 most representative features were selected by using the agglomerative hierarchical clustering method. The binary classification task of the two groups was carried out by using four different machine-learning algorithms (i.e., linear support vector machine (SVM), radial basis function (RBF) SVM, logistic regression (LR), and random forest (RF)). Accuracy, sensitivity, sensibility, and the area under the curve (AUC) were calculated for each of them. Results: The best performance was achieved using the RF classifier (AUC = 0.59, 95% confidence interval 0.57–0.60; sensitivity = 0.56, 95% CI 0.54–0.58; specificity = 0.61, 95% CI 0.59–0.63; accuracy = 0.58, 95% CI 0.57–0.59). Conclusions: DBT-based radiomic analysis seems to have only limited potential in discriminating benign from malignant microcalcifications.

Preoperative Prediction Power of Radiomics for Breast Cancer: A Systemic Review and Meta-Analysis

Background

To evaluate the preoperative predictive value of radiomics in the diagnosis of breast cancer (BC).

Methods

By searching PubMed and Embase libraries, our study identified 19 eligible studies. We conducted a meta-analysis to assess the differential value in the preoperative assessment of BC using radiomics methods.

Results

Nineteen radiomics studies focusing on the diagnostic efficacy of BC and involving 5865 patients were enrolled. The integrated sensitivity and specificity were 0.84 (95% CI: 0.80–0.87, I^{2 =} 76.44%) and 0.83 (95% CI: 0.78–0.87, I^{2 =} 81.79%), respectively. The AUC based on the SROC curve was 0.91, indicating a high diagnostic value.

Conclusion

Radiomics has shown excellent diagnostic performance in the preoperative prediction of BC and is expected to be a promising method in clinical practice.

Cancer yield and imaging features of probably benign calcifications at digital magnification view

OBJECTIVES

To investigate the malignancy rate of probably benign calcifications assessed by digital magnification view and imaging and clinical features associated with malignancy.

METHODS

This retrospective study included consecutive women with digital magnification views assessed as probably benign for calcifications without other associated mammographic findings from March 2009 to January 2014. Initial studies rendering a probably benign assessment were analyzed, with biopsy or 4-year imaging follow-up. Fisher's exact test and univariable logistic regression were performed. Cancer yields were calculated.

RESULTS

A total of 458 lesions in 422 patients were finally included. The overall cancer yield was 2.2% (10 of 458, invasive cancer [n = 4] and DCIS [n = 6]). Calcification distribution (OR = 23.80, p = .041), calcification morphology (OR = 10.84, p = .005), increased calcifications (OR = 29.40, p = .001), and having a concurrent newly diagnosed breast cancer or high-risk lesion (OR = 10.24, p = .001) were associated with malignancy. Cancer yields did not significantly differ between grouped punctate calcifications vs. calcifications with other features (1.2% [2 of 162] vs. 2.7% [8 of 296], p = .506). The cancer yield was 1.6% (7 of 437) in women without newly diagnosed breast cancer or high-risk lesions.

CONCLUSION

The cancer yield of probably benign calcifications assessed by digital magnification view was below the 2% threshold for grouped punctate calcifications and for women without newly diagnosed breast cancer or high-risk lesions. Calcification distribution, morphology, increase in calcifications, and the presence of newly diagnosed breast cancer/high-risk lesion were associated with malignancy.

KEY POINTS

• Among 458 probably benign calcifications assessed by digital magnification view, the overall cancer yield was 2.2% (10 of 458). • The cancer yield was below the 2% threshold for grouped punctate calcifications (1.2%, 2 of 162) and in women without newly diagnosed breast cancer or high-risk lesions (1.6%, 7 of 437). • Calcification distribution, morphology, increase in calcifications, and the presence of newly diagnosed breast cancer/high-risk lesion were associated with malignancy (all p < .05).

An MRI-Based Radiomics Model for Predicting the Benignity and Malignancy of BI-RADS 4 Breast Lesions

Objectives

The probability of Breast Imaging Reporting and Data Systems (BI-RADS) 4 lesions being malignant is 2%–95%, which shows the difficulty to make a diagnosis. Radiomics models based on magnetic resonance imaging (MRI) can replace clinicopathological diagnosis with high performance. In the present study, we developed and tested a radiomics model based on MRI images that can predict the malignancy of BI-RADS 4 breast lesions.

Methods

We retrospective enrolled a total of 216 BI-RADS 4 patients MRI and clinical information. We extracted 3,474 radiomics features from dynamic contrast-enhanced (DCE), T₂-weighted images (T₂WI), and diffusion-weighted imaging (DWI) MRI images. Least absolute shrinkage and selection operator (LASSO) and logistic regression were used to select features and build radiomics models based on different sequence combinations. We built eight radiomics models which were based on DCE, DWI, T₂WI, DCE+DWI, DCE+T₂WI, DWI+T₂WI, and DCE+DWI+T₂WI and a clinical predictive model built based on the visual assessment of radiologists. A nomogram was constructed with the best radiomics signature combined with patient characteristics. The calibration curves for the radiomics signature and nomogram were conducted, combined with the Hosmer-Lemeshow test.

Results

Pearson’s correlation was used to eliminate 3,329 irrelevant features, and then LASSO and logistic regression were used to screen the remaining feature coefficients for each model we built. Finally, 12 related features were obtained in the model which had the best performance. These 12 features were used to build a radiomics model in combination with the actual clinical diagnosis of benign or malignant lesion labels we have obtained. The best model built by 12 features from the 3 sequences has an AUC value of 0.939 (95% CI, 0.884-0.994) and an accuracy of 0.931 in the testing cohort. The sensitivity, specificity, precision and Matthews correlation coefficient (MCC) of testing cohort are 0.932, 0.923, 0.982, and 0.791, respectively. The nomogram has also been verified to have calibration curves with good overlap.

Conclusions

Radiomics is beneficial in the malignancy prediction of BI-RADS 4 breast lesions. The radiomics predictive model built by the combination of DCE, DWI, and T₂WI sequences has great application potential.

Diagnosis of Breast Cancer Using Radiomics Models Built Based on Dynamic Contrast Enhanced MRI Combined With Mammography

Objective

To build radiomics models using features extracted from DCE-MRI and mammography for diagnosis of breast cancer.

Materials and Methods

266 patients receiving MRI and mammography, who had well-enhanced lesions on MRI and histologically confirmed diagnosis were analyzed. Training dataset had 146 malignant and 56 benign, and testing dataset had 48 malignant and 18 benign lesions. Fuzzy-C-means clustering algorithm was used to segment the enhanced lesion on subtraction MRI maps. Two radiologists manually outlined the corresponding lesion on mammography by consensus, with the guidance of MRI maximum intensity projection. Features were extracted using PyRadiomics from three DCE-MRI parametric maps, and from the lesion and a 2-cm bandshell margin on mammography. The support vector machine (SVM) was applied for feature selection and model building, using 5 datasets: DCE-MRI, mammography lesion-ROI, mammography margin-ROI, mammography lesion+margin, and all combined.

Results

In the training dataset evaluated using 10-fold cross-validation, the diagnostic accuracy of the individual model was 83.2% for DCE-MRI, 75.7% for mammography lesion, 64.4% for mammography margin, and 77.2% for lesion+margin. When all features were combined, the accuracy was improved to 89.6%. By adding mammography features to MRI, the specificity was significantly improved from 69.6% (39/56) to 82.1% (46/56), p<0.01. When the developed models were applied to the independent testing dataset, the accuracy was 78.8% for DCE-MRI and 83.3% for combined MRI+Mammography.

Conclusion

The radiomics model built from the combined MRI and mammography has the potential to provide a machine learning-based diagnostic tool and decrease the false positive diagnosis of contrast-enhanced benign lesions on MRI.

Diagnostic Performance of Artificial Intelligence-Based Computer-Aided Diagnosis for Breast Microcalcification on Mammography

The present study evaluated the diagnostic performance of artificial intelligence-based computer-aided diagnosis (AI-CAD) compared to that of dedicated breast radiologists in characterizing suspicious microcalcification on mammography. We retrospectively analyzed 435 unilateral mammographies from 420 patients (286 benign; 149 malignant) undergoing biopsy for suspicious microcalcification from June 2003 to November 2019. Commercial AI-CAD was applied to the mammography images, and malignancy scores were calculated. Diagnostic performance was compared between radiologists and AI-CAD using the area under the receiving operator characteristics curve (AUC). The AUCs of radiologists and AI-CAD were not significantly different (0.722 vs. 0.745, p = 0.393). The AUCs of the adjusted category were 0.726, 0.744, and 0.756 with cutoffs of 2%, 10%, and 38.03% for AI-CAD, respectively, which were all significantly higher than those for radiologists alone (all p < 0.05). None of the 27 cases downgraded to category 3 with a cutoff of 2% were confirmed as malignant on pathological analysis, suggesting that unnecessary biopsies could be avoided. Our findings suggest that the diagnostic performance of AI-CAD in characterizing suspicious microcalcification on mammography was similar to that of the radiologists, indicating that it may aid in making clinical decisions regarding the treatment of breast microcalcification.

Recent Radiomics Advancements in Breast Cancer: Lessons and Pitfalls for the Next Future

Radiomics is an emerging translational field of medicine based on the extraction of high-dimensional data from radiological images, with the purpose to reach reliable models to be applied into clinical practice for the purposes of diagnosis, prognosis and evaluation of disease response to treatment. We aim to provide the basic information on radiomics to radiologists and clinicians who are focused on breast cancer care, encouraging cooperation with scientists to mine data for a better application in clinical practice. We investigate the workflow and clinical application of radiomics in breast cancer care, as well as the outlook and challenges based on recent studies. Currently, radiomics has the potential ability to distinguish between benign and malignant breast lesions, to predict breast cancer’s molecular subtypes, the response to neoadjuvant chemotherapy and the lymph node metastases. Even though radiomics has been used in tumor diagnosis and prognosis, it is still in the research phase and some challenges need to be faced to obtain a clinical translation. In this review, we discuss the current limitations and promises of radiomics for improvement in further research.

An Approach Based on Mammographic Imaging and Radiomics for Distinguishing Male Benign and Malignant Lesions: A Preliminary Study

Purpose

To develop and validate an imaging-radiomics model for the diagnosis of male benign and malignant breast lesions.

Methods

Ninety male patients who underwent preoperative mammography from January 2011 to December 2018 were enrolled in this study (63 in the training cohort and 27 in the validation cohort). The region of interest was segmented into a mediolateral oblique view, and 104 radiomics features were extracted. The minimum redundancy and maximum relevance (mRMR) and the least absolute shrinkage and selection operator (LASSO) methods were used to exclude radiomics features to establish the radiomics score (rad-score). Mammographic features were evaluated by two radiologists. Univariate logistic regression was used to select for imaging features, and multivariate logistic regression was used to construct an imaging model. An imaging-radiomics model was eventually established, and a nomogram was developed based on the imaging-radiomics model. Area under the curve (AUC) and decision curve analysis (DCA) were applied to assess the clinical value.

Results

The AUC based on the imaging model in the validation cohort was 0.760, the sensitivity was 0.750, and the specificity was 0.727. The AUC, sensitivity and specificity based on the radiomics in the validation cohort were 0.820, 0.750, and 0.867, respectively. The imaging-radiomics model was better than the imaging and radiomics models; the AUC, sensitivity, and specificity of the imaging-radiomics model in the validation cohort were 0.870, 0.824, and 0.900, respectively.

Conclusion

The imaging-radiomics model created by the imaging characteristics and radiomics features exhibited a favorable discriminatory ability for male breast cancer.

Images Are Data: A Breast Imaging Perspective on a Contemporary Paradigm

BACKGROUND

 Considering radiological examinations not as mere images, but as a source of data, has become the key paradigm in the diagnostic imaging field. This change of perspective is particularly popular in breast imaging. It allows breast radiologists to apply algorithms derived from computer science, to realize innovative clinical applications, and to refine already established methods. In this context, the terminology "imaging biomarker", "radiomics", and "artificial intelligence" are of pivotal importance. These methods promise noninvasive, low-cost (e. g., in comparison to multigene arrays), and workflow-friendly (automated, only one examination, instantaneous results, etc.) delivery of clinically relevant information.

METHODS AND RESULTS

 This paper is designed as a narrative review on the previously mentioned paradigm. The focus is on key concepts in breast imaging and important buzzwords are explained. For all areas of breast imaging, exemplary studies and potential clinical use cases are discussed.

CONCLUSION

 Considering radiological examination as a source of data may optimize patient management by guiding individualized breast cancer diagnosis and oncologic treatment in the age of precision medicine.

KEY POINTS

  · In conventional breast imaging, examinations are interpreted based on patterns perceivable by visual inspection.. · The radiomics paradigm treats breast images as a source of data, containing information beyond what is visible to our eyes.. · This results in radiomic signatures that may be considered as imaging biomarkers, as they provide diagnostic, predictive, and prognostic information.. · Radiomics derived imaging biomarkers may be used to individualize breast cancer treatment in the era of precision medicine.. · The concept and key research of radiomics in the field of breast imaging will be discussed in this narrative review..

CITATION FORMAT

· Dietzel M, Clauser P, Kapetas P et al. Images Are Data: A Breast Imaging Perspective on a Contemporary Paradigm. Fortschr Röntgenstr 2021; 193: 898 - 908.

A deep learning model integrating mammography and clinical factors facilitates the malignancy prediction of BI-RADS 4 microcalcifications in breast cancer screening

OBJECTIVES

To investigate the value of full-field digital mammography-based deep learning (DL) in predicting malignancy of Breast Imaging Reporting and Data System (BI-RADS) 4 microcalcifications.

METHODS

A total of 384 patients with 414 pathologically confirmed microcalcifications (221 malignant and 193 benign) were randomly allocated into the training, validation, and testing datasets (272/71/71 lesions) in this retrospective study. A combined DL model was developed incorporating mammography and clinical variables. Model performance was evaluated by using areas under the receiver operating characteristic curve (AUC) and compared with the clinical model, stand-alone DL image model, and BI-RADS approach. The predictive performance for malignancy was also compared between the combined model and human readers (2 juniors and 2 seniors).

RESULTS

The combined DL model demonstrated favorable AUC, sensitivity, and specificity of 0.910, 85.3%, and 91.9% in predicting BI-RADS 4 malignant microcalcifications in the testing dataset, which outperformed the clinical model, DL image model, and BI-RADS with AUCs of 0.799, 0.841, and 0.804, respectively. The combined model achieved non-inferior performance as senior radiologists (p = 0.860, p = 0.800) and outperformed junior radiologists (p = 0.155, p = 0.029). The diagnostic performance of two junior radiologists was improved after artificial intelligence assistance with AUCs increased to 0.854 and 0.901 from 0.816 (p = 0.556) and 0.773 (p = 0.046), while the interobserver agreement was improved with a kappa value increased to 0.843 from 0.331.

CONCLUSIONS

The combined deep learning model can improve the malignancy prediction of BI-RADS 4 microcalcifications in screening mammography and assist junior radiologists to achieve better performance, which can facilitate clinical decision-making.

KEY POINTS

• The combined deep learning model demonstrated high diagnostic power, sensitivity, and specificity for predicting malignant BI-RADS 4 mammographic microcalcifications. • The combined model achieved similar performance with senior breast radiologists, while it outperformed junior breast radiologists. • Deep learning could improve the diagnostic performance of junior radiologists and facilitate clinical decision-making.

Application of digital mammography-based radiomics in the differentiation of benign and malignant round-like breast tumors and the prediction of molecular subtypes

BACKGROUND

This study aimed to investigate the diagnostic performance of radiomic features based on digital mammography (DM) in the differential diagnosis of benign and malignant round-like (round and oval) solid tumors with circumscribed or obscured margins but without suspicious malignant or benign macrocalcifications and to investigate whether quantitative radiomic features can distinguish triple-negative breast cancer (TNBC) from non-TNBC (NTNBC).

METHODS

This retrospective study included 112 patients with round-like tumors who underwent DM within 20 days preoperatively. Breast masses were segmented manually on the DM images, then radiomic features were extracted. The predictive models were used to distinguish between benign and malignant tumors and to predict TNBC in invasive ductal carcinoma. The receiver operating characteristic curves (ROCs) for these models were obtained for initial DM characteristics, radiomic features to predict malignant tumors and TNBC. The decision curve was obtained to evaluate the clinical usefulness of the model for the prediction of benign or malignant tumors.

RESULTS

The study cohort included 79 patients with pathologically confirmed malignant masses and 33 patients with benign (training cohort: n=79; testing cohort: n=33). A total of 396 features were extracted from the DM images for each patient. The radiomics model for the prediction of malignant tumors achieved an area under the receiver operating characteristic curve (AUC) of 0.88 [95% confidence interval (CI), 0.76-1.00] in the testing cohort; the radiomics model for the prediction of TNBC achieved an AUC of 0.84 (95% CI, 0.73-0.96). In contrast, DM characteristics alone poorly predicted malignant tumors, with the density achieving an AUC 0.69 (95% CI, 0.59-0.79); there was no significant difference in DM characteristics between TNBC and NTNBC (P>0.05, all). The decision curve showed the good clinical usefulness of the model for the prediction of malignant tumors.

CONCLUSIONS

This study showed that DM-based radiomics can accurately discriminate between benign and malignant round-like tumors with circumscribed or obscured margins but without suspicious malignant or benign macrocalcifications. Additionally, it can be used to predict TNBC in invasive ductal carcinoma. DM-based radiomics can aid radiologists in mammogram reading, clinical diagnosis and decision-making.

Contrast-Enhanced Spectral Mammography-Based Radiomics Nomogram for Identifying Benign and Malignant Breast Lesions of Sub-1 cm

Objectives

To develop a radiomics nomogram that incorporates contrast-enhanced spectral mammography (CESM)-based radiomics features and clinico-radiological variables for identifying benign and malignant breast lesions of sub-1 cm.

Methods

This retrospective study included 139 patients with the diameter of sub-1 cm on cranial caudal (CC) position of recombined images. Radiomics features were extracted from low-energy and recombined images on CC position. The variance threshold, analysis of variance (ANOVA) and least absolute shrinkage and selection operator (LASSO) algorithms were used to select optimal predictive features. Radiomics signature (Rad-score) was calculated by a linear combination of selected features. The independent predictive factors were identified by ANOVA and multivariate logistic regression. A radiomics nomogram was developed to predict the malignant probability of lesions. The performance and clinical utility of the nomogram was evaluated by receiver operating characteristic (ROC) curve, calibration curve, and decision curve analysis (DCA).

Results

Nineteen radiomics features were selected to calculate Rad-score. Breast imaging reporting and data system (BI-RADS) category and age were identified as predictive factors. The radiomics nomogram combined with Rad-score, BI-RADS category, and age showed better performance (area under curves [AUC]: 0.940, 95% confidence interval [CI]: 0.804-0.992) than Rad-score (AUC: 0.868, 95% CI: 0.711-0.958) and clinico-radiological model (AUC: 0.864, 95% CI: 0.706-0.956) in the validation cohort. The calibration curve and DCA showed that the radiomics nomogram had good consistency and clinical utility.

Conclusions

The radiomics nomogram incorporated with CESM-based radiomics features, BI-RADS category and age could identify benign and malignant breast lesions of sub-1 cm.

Predicting the Type of Tumor-Related Epilepsy in Patients With Low-Grade Gliomas: A Radiomics Study

Purpose: The majority of patients with low-grade gliomas (LGGs) experience tumor-related epilepsy during the disease course. Our study aimed to build a radiomic prediction model for LGG-related epilepsy type based on magnetic resonance imaging (MRI) data.

Methods: A total of 205 cases with LGG-related epilepsy were enrolled in the retrospective study and divided into training and validation cohorts (1:1) according to their surgery time. Seven hundred thirty-four radiomic features were extracted from T2-weighted imaging, including six location features. Pearson correlation coefficient, univariate area under curve (AUC) analysis, and least absolute shrinkage and selection operator regression were adopted to select the most relevant features for the epilepsy type to build a radiomic signature. Furthermore, a novel radiomic nomogram was developed for clinical application using the radiomic signature and clinical variables from all patients.

Results: Four MRI-based features were selected from the 734 radiomic features, including one location feature. Good discriminative performances were achieved in both training (AUC = 0.859, 95% CI = 0.787–0.932) and validation cohorts (AUC = 0.839, 95% CI = 0.761–0.917) for the type of epilepsy. The accuracies were 80.4 and 80.6%, respectively. The radiomic nomogram also allowed for a high degree of discrimination. All models presented favorable calibration curves and decision curve analyses.

Conclusion: Our results suggested that the MRI-based radiomic analysis may predict the type of LGG-related epilepsy to enable individualized therapy for patients with LGG-related epilepsy.