Artificial intelligence-based, semi-automated segmentation for the extraction of ultrasound-derived radiomics features in breast cancer: a prospective multicenter study.

PURPOSE: To investigate the feasibility of an artificial intelligence (AI)-based semi-automated segmentation for the extraction of ultrasound (US)-derived radiomics features in the characterization of focal breast lesions (FBLs). MATERIAL AND METHODS: Two expert radiologists classified according to US BI-RADS criteria 352 FBLs detected in 352 patients (237 at Center A and 115 at Center B). An AI-based semi-automated segmentation was used to build a machine learning (ML) model on the basis of B-mode US of 237 images (center A) and then validated on an external cohort of B-mode US images of 115 patients (Center B). RESULTS: A total of 202 of 352 (57.4%) FBLs were benign, and 150 of 352 (42.6%) were malignant. The AI-based semi-automated segmentation achieved a success rate of 95.7% for one reviewer and 96% for the other, without significant difference (p = 0.839). A total of 15 (4.3%) and 14 (4%) of 352 semi-automated segmentations were not accepted due to posterior acoustic shadowing at B-Mode US and 13 and 10 of them corresponded to malignant lesions, respectively. In the validation cohort, the characterization made by the expert radiologist yielded values of sensitivity, specificity, PPV and NPV of 0.933, 0.9, 0.857, 0.955, respectively. The ML model obtained values of sensitivity, specificity, PPV and NPV of 0.544, 0.6, 0.416, 0.628, respectively. The combined assessment of radiologists and ML model yielded values of sensitivity, specificity, PPV and NPV of 0.756, 0.928, 0.872, 0.855, respectively. CONCLUSION: AI-based semi-automated segmentation is feasible, allowing an instantaneous and reproducible extraction of US-derived radiomics features of FBLs. The combination of radiomics and US BI-RADS classification led to a potential decrease of unnecessary biopsy but at the expense of a not negligible increase of potentially missed cancers.

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.

MRI Insights in Breast Imaging.

In the world, breast cancer is the most commonly diagnosed cancer among women. Currently, MRI is the most sensitive breast imaging method for detecting breast cancer, although false positive rates are still an issue. To date, the accuracy of breast MRI is widely recognized across various clinical scenarios, in particular, staging of known cancer, screening for breast cancer in high-risk women, and evaluation of response to neoadjuvant chemotherapy. Since technical development and further clinical indications have expanded over recent years, dedicated breast radiologists need to constantly update their knowledge and expertise to remain confident and maintain high levels of diagnostic performance in breast MRI. This review aims to detail current and future applications of breast MRI, from technological requirements and advances to new multiparametric and abbreviated protocols, and ultrafast imaging, as well as current and future indications.

Artificial Intelligence in Breast Imaging: A Special Focus on Advances in Digital Mammography & Digital Breast Tomosynthesis.

Breast cancer accounts for 30% of female cancers and is the second leading cause of cancerrelated deaths in women. The rate is rising at 0.4% per year. Early detection is crucial to improve treatment efficacy and overall survival of women diagnosed with breast cancer. Digital Mammography and Digital Breast Tomosynthesis have widely demonstrated their role as a screening tool. However, screening mammography is limited by radiologist's experience, unnecessarily high recalls, overdiagnosis, overtreatment and, in the case of Digital Breast Tomosynthesis, long reporting time. This is compounded by an increasing shortage of manpower and resources issue, especially among breast imaging specialists. Recent advances in image analysis with the use of artificial intelligence (AI) in breast imaging have the potential to overcome some of these needs and address the clinical challenges in cancer detection, assessment of treatment response, and monitoring disease progression. This article focuses on the most important clinical implication and future application of AI in the field of digital mammography and digital breast tomosynthesis, providing the readers with a comprehensive overview of AI impact in cancer detection, diagnosis, reduction of workload and breast cancer risk stratification.

Diagnostic performance of 2D-shear wave elastography in the diagnosis of breast cancer: a clinical appraisal of cutoff values.

PURPOSE: To assess the role of 2D-shear wave elastography (2D-SWE) in differentiating benign from malignant focal breast lesions (FBLs), providing new vendor-specific cutoff values. METHODS: 158 FBLs (size: 3.5-50 mm) detected in 151 women (age: 21-87 years) were prospectively evaluated by means 2D-SWE. For each lesion, an expert radiologist assessed US BI-RADS category and calculated the following four 2D-SWE parameters: (1) elasticity maximum (Emax); (2) mean elasticity (Emean); (3) minimum elasticity (Emin); (4) elasticity ratio (Eratio). US-guided core-biopsy was considered as standard of reference for all the FBLs classified as BI-RADS 4 or 5. For each 2D-SWE parameter, the optimal cutoff value for a diagnostic test was calculated using the Youden method. Diagnostic performance of the US BI-RADS and 2D-SWE parameters was calculated accordingly. RESULTS: 83/158 (52.5%) FBLs were benign and 75/158 (47.5%) were malignant. Statistically significant higher stiffness values were observed in malignant FBLs for all 2D-SWE parameters than in benign ones (p < 0.001). 2D-SWE cutoff values were 82.6 kPa, 66.0 kPa and 53.6 kPa, respectively, for Emax, Emean, Emin and 330.8% for Eratio. The 2D-SWE parameter showing the best diagnostic accuracy was Emax (85.44%). Considering US BI-RADS 3 (n = 60) and 4a (n = 32) FBLs, Emax and Emean showed the best diagnostic accuracy (85.87% for both), without a statistically significant decrease in sensitivity (p = 0.7003 and p = 1, respectively). CONCLUSION: Our study provides new vendor-specific cutoff values for 2D-SWE, suggesting its possible clinical use in the adjunctive assessment of category US-BI-RADS 3 and 4a breast masses.

Diagnostic Performance of an Artificial Intelligence System in Breast Ultrasound.

OBJECTIVES: We study the performance of an artificial intelligence (AI) program designed to assist radiologists in the diagnosis of breast cancer, relative to measures obtained from conventional readings by radiologists. METHODS: A total of 10 radiologists read a curated, anonymized group of 299 breast ultrasound images that contained at least one suspicious lesion and for which a final diagnosis was independently determined. Separately, the AI program was initialized by a lead radiologist and the computed results compared against those of the radiologists. RESULTS: The AI program's diagnoses of breast lesions had concordance with the 10 radiologists' readings across a number of BI-RADS descriptors. The sensitivity, specificity, and accuracy of the AI program's diagnosis of benign versus malignant was above 0.8, in agreement with the highest performing radiologists and commensurate with recent studies. CONCLUSION: The trained AI program can contribute to accuracy of breast cancer diagnoses with ultrasound.

3D DCE-MRI Radiomic Analysis for Malignant Lesion Prediction in Breast Cancer Patients.

RATIONALE AND OBJECTIVES: To develop and validate a radiomic model, with radiomic features extracted from breast Dynamic Contrast-Enhanced Magnetic Resonance Imaging (DCE-MRI) from a 1.5T scanner, for predicting the malignancy of masses with enhancement. Images were acquired using an 8-channel breast coil in the axial plane. The rationale behind this study is to show the feasibility of a radiomics-powered model that could be integrated into the clinical practice by exploiting only standard-of-care DCE-MRI with the goal of reducing the required image pre-processing (ie, normalization and quantitative imaging map generation). MATERIALS AND METHODS: 107 radiomic features were extracted from a manually annotated dataset of 111 patients, which was split into discovery and test sets. A feature calibration and pre-processing step was performed to find only robust non-redundant features. An in-depth discovery analysis was performed to define a predictive model: for this purpose, a Support Vector Machine (SVM) was trained in a nested 5-fold cross-validation scheme, by exploiting several unsupervised feature selection methods. The predictive model performance was evaluated in terms of Area Under the Receiver Operating Characteristic (AUROC), specificity, sensitivity, PPV and NPV. The test was performed on unseen held-out data. RESULTS: The model combining Unsupervised Discriminative Feature Selection (UDFS) and SVMs on average achieved the best performance on the blinded test set: AUROC = 0.725±0.091, sensitivity = 0.709±0.176, specificity = 0.741±0.114, PPV = 0.72±0.093, and NPV = 0.75±0.114. CONCLUSION: In this study, we built a radiomic predictive model based on breast DCE-MRI, using only the strongest enhancement phase, with promising results in terms of accuracy and specificity in the differentiation of malignant from benign breast lesions.

Ultrasonographic Detection of Vascularity of Focal Breast Lesions: Microvascular Imaging Versus Conventional Color and Power Doppler Imaging.

To compare microvascular flow imaging (MVFI) to conventional Color-Doppler (CDI) and Power-Doppler (PDI) imaging in the detection of vascularity of Focal Breast Lesions (FBLs). A total of 180 solid FBLs (size: 3.5-45.2 mm) detected in 180 women (age: 21-87 years) were evaluated by means of CDI, PDI, and MVFI. Two blinded reviewers categorized lesion vascularity in absent or present, and vascularity pattern as (a) internal; (b) vessels in rim; (c) combined. The presence of a "penetrating vessel" was assessed separately. Differences in vascularization patterns (chi2 test) and intra- and inter-observer agreement (Fleiss method) were calculated. ROC analysis was performed to assess performance of each technique in differentiating benign from malignant lesions. About 103/180 (57.2%) FBLs were benign and 77/180 (42.8%) were malignant. A statistically significant (p < .001) increase in blood flow detection was observed for both readers with MVFI in comparison to either CDI or PDI. Benign FBLs showed mainly absence of vascularity (p = .02 and p = .01 for each reader, respectively), rim pattern (p < .001 for both readers) or combined pattern (p = .01 and p = .04). Malignant lesions showed a statistically significant higher prevalence of internal flow pattern (p < .001 for both readers). The prevalence of penetrating vessels was significantly higher with MVFI in comparison to either CDI or PDI (p < .001 for both readers) and in the malignant FBLs (p < .001). ROC analysis showed MVFI (AUC = 0.70, 95%CI = [0.64-0.77]) more accurate than CDI (AUC = 0.67, 95%CI = [0.60-0.74]) and PDI (AUC = 0.67, 95%CI = [0.60-0.74]) though not significantly (p = .5436). Sensitivity/Specificity values for MVFI, PDI, and CDI were 76.6%/64.1%, 59.7%/73.8% and 58.4%/74.8%, respectively. Inter-reader agreement with MVFI was always very good (k-score 0.85-0.96), whereas with CDI and PDI evaluation ranged from good to very good. No differences in intra-observer agreement were noted. MVFI showed a statistically significant increase in the detection of the vascularization of FBLs in comparison to Color and Power-Doppler.

S-Detect characterization of focal solid breast lesions: a prospective analysis of inter-reader agreement for US BI-RADS descriptors.

BACKGROUND: To assess inter-reader agreement for US BI-RADS descriptors using S-Detect: a computer-guided decision-making software assisting in US morphologic analysis. METHODS: 73 solid focal breast lesions (FBLs) (mean size: 15.9 mm) in 73 consecutive women (mean age: 51 years) detected at US were randomly and independently assessed according to the BI-RADS US lexicon, without and with S-Detect, by five independent reviewers. US-guided core-biopsy and 24-month follow-up were considered as standard of reference. Kappa statistics were calculated to assess inter-operator agreement, between the baseline and after S-Detect evaluation. Agreement was graded as poor (≤ 0.20), moderate (0.21-0.40), fair (0.41-0.60), good (0.61-0.80), or very good (0.81-1.00). RESULTS: 33/73 (45.2%) FBLs were malignant and 40/73 (54.8%) FBLs were benign. A statistically significant improvement of inter-reader agreement from fair to good with the use of S-Detect was observed for shape (from 0.421 to 0.612) and orientation (from 0.417 to 0.7) (p < 0.0001) and from moderate to fair for margin (from 0.204 to 0.482) and posterior features (from 0.286 to 0.522) (p < 0.0001). At baseline analysis isoechoic (0.0485) and heterogeneous (0.1978) echo pattern, microlobulated (0.1161) angular (0.1204) and spiculated (0.1692) margins and combined pattern (0.1549) for posterior features showed the worst agreement rate (poor). After S-Detect evaluation, all variables but isoechoic pattern showed an agreement class upgrade with a statistically significant improvement of inter-reader agreement (p < 0.0001). CONCLUSIONS: S-Detect significantly improved inter-reader agreement in the assessment of FBLs according to the BI-RADS US lexicon but evaluation of margin and echo pattern needs to be further improved, particularly isoechoic pattern.

S-Detect characterization of focal breast lesions according to the US BI RADS lexicon: a pictorial essay.

High-resolution ultrasonography (US) is a valuable tool in breast imaging. Nevertheless, US is an operator-dependent technique: to overcome this issue, the American College of Radiology (ACR) has developed the breast imaging-reporting and data system (BI-RADS) US lexicon. Despite this effort, the variability in the assessment of focal breast lesions (FBLs) with the use of BI-RADS US lexicon is still an issue. Within this framework, evidence shows that computer-aided image analysis may be effective in improving the radiologist's assessment of FBLs. In particular, S-Detect is a newly developed image-analytic computer program that provides assistance in morphologic analysis of FBLs seen on US according to the BI-RADS US lexicon. This pictorial essay describes state-of-the-art of sonographic characterization of FBLs by using S-Detect.