Screening in Patients With Dense Breasts: Comparison of Mammography, Artificial Intelligence, and Supplementary Ultrasound

Emerging nanoparticle-based x-ray imaging contrast agents for breast cancer screening

Breast cancer is one of the most common types of cancer, however, preventive screening has contributed to a significant reduction in mortality over the past four decades. The first-line screening methods for breast cancer, such as mammography and tomosynthesis, are x-ray-based modalities. Unfortunately, their cancer detection rates are low in patients with dense breasts. These, and other high-risk women, are now encouraged to receive supplemental screening. The supplemental imaging methods are diverse, including ultrasound, MRI, nuclear imaging, and X-ray-based modalities such as breast CT and contrast-enhanced mammography/tomosynthesis. Due to their low cost and wide availability, x-ray-based modalities see significant clinical use worldwide. These techniques benefit from the use of contrast agents, which are currently iodinated small molecules designed for other purposes. Consequently, developing new contrast agents that are specifically for breast cancer screening is of interest. This review describes these modalities and the nanoparticle-based contrast agents being researched for their enhanced performance. The relevant parameters for nanoparticle-based contrast agent design are evaluated, including contrast generation and potential biointeractions. Iodinated agents are discussed for comparison. Nanoparticles covered include silver sulfide, silver telluride, gold, and bismuth sulfide-based agents, among others. Finally, perspectives on future developments in this field are offered.

Comparative Evaluation of Machine Learning-Based Radiomics and Deep Learning for Breast Lesion Classification in Mammography

Background: Breast cancer is the second leading cause of cancer-related mortality among women, accounting for 12% of cases. Early diagnosis, based on the identification of radiological features, such as masses and microcalcifications in mammograms, is crucial for reducing mortality rates. However, manual interpretation by radiologists is complex and subject to variability, emphasizing the need for automated diagnostic tools to enhance accuracy and efficiency. This study compares a radiomics workflow based on machine learning (ML) with a deep learning (DL) approach for classifying breast lesions as benign or malignant. Methods: matRadiomics was used to extract radiomics features from mammographic images of 1219 patients from the CBIS-DDSM public database, including 581 cases of microcalcifications and 638 of masses. Among the ML models, a linear discriminant analysis (LDA) demonstrated the best performance for both lesion types. External validation was conducted on a private dataset of 222 images to evaluate generalizability to an independent cohort. Additionally, a deep learning approach based on the EfficientNetB6 model was employed for comparison. Results: The LDA model achieved a mean validation AUC of 68.28% for microcalcifications and 61.53% for masses. In the external validation, AUC values of 66.9% and 61.5% were obtained, respectively. In contrast, the EfficientNetB6 model demonstrated superior performance, achieving an AUC of 81.52% for microcalcifications and 76.24% for masses, highlighting the potential of DL for improved diagnostic accuracy. Conclusions: This study underscores the limitations of ML-based radiomics in breast cancer diagnosis. Deep learning proves to be a more effective approach, offering enhanced accuracy and supporting clinicians in improving patient management.

A multi-task self-supervised approach for mass detection in automated breast ultrasound using double attention recurrent residual U-Net

Breast cancer is the most common and lethal cancer among women worldwide. Early detection using medical imaging technologies can significantly improve treatment outcomes. Automated breast ultrasound, known as ABUS, offers more advantages compared to traditional mammography and has recently gained considerable attention. However, reviewing hundreds of ABUS slices imposes a high workload on radiologists, increasing review time and potentially leading to diagnostic errors. Consequently, there is a strong need for efficient computer-aided detection, CADe, systems. In recent years, researchers have proposed deep learning-based CADe systems to enhance mass detection accuracy. However, these methods are highly dependent on the number of training samples and often struggle to balance detection accuracy with the false positive rate. To reduce the workload for radiologists and achieve high detection sensitivities with low false positive rates, this study introduces a novel CADe system based on a self-supervised framework that leverages unannotated ABUS datasets to improve detection results. The proposed framework is integrated into an innovative 3-D convolutional neural network called DATTR2U-Net, which employs a multi-task learning approach to simultaneously train inpainting and denoising pretext tasks. A fully convolutional network is then attached to the DATTR2U-Net for the detection task. The proposed method is validated on the TDSCABUS public dataset, demonstrating promising detection results with a recall of 0.7963 and a false positive rate of 5.67 per volume that signifies its potential to improve detection accuracy while reducing workload for radiologists. The code is available at: github.com/Pooryamn/SSL_ABUS.

Nonmass Lesions on Breast Ultrasound: Interreader Agreement and Associations With Malignancy

BACKGROUND. Nonmass lesions (NMLs) on breast ultrasound lack clear definition and encompass a broad range of benign and malignant entities. Given the anticipated inclusion of NMLs in the BI-RADS 6th edition, a thorough understanding of these lesions will be critical for their optimal management. OBJECTIVE. The purpose of the present study was to evaluate interreader agreement for classification of lesions observed on breast ultrasound as NMLs and to identify the imaging features associated with malignancy in these lesions. METHODS. This retrospective study included 2007 patients (2005 women and two men; mean age, 54.0 ± 9.6 [SD] years) who underwent ultrasound-guided biopsy of 2381 breast lesions between January 2020 and December 2020. Two radiologists independently classified the lesions as masses or NMLs, using a definition of NMLs from a presentation at the Radiological Society of North America 2023 annual meeting. The radiologists attempted to reach consensus for discordant cases. Another radiologist recorded the mammographic and ultrasound characteristics of the NMLs. Pathologic outcomes for NMLs were extracted from the EHR. RESULTS. Interreader agreement for lesion classification (mass vs NML) was substantial (κ = 0.73) A total of 216 lesions were classified as NMLs by both readers independently; an additional 101 lesions were classified as NMLs by consensus review after initial discordance. Thus, 317 of 2381 lesions (13.3%) were classified as NMLs; initial reader discordance occurred for 101 of these 317 lesions (31.9%). A total of 133 of 317 NMLs (42.0%) were malignant, including invasive ductal carcinoma (48/133), ductal carcinoma in situ (43/133), and microinvasive ductal carcinoma (micro-IDC) (34/133). A total of 30.8% of malignant NMLs lacked correlative mammographic abnormalities. Ultrasound findings with the highest accuracy for identifying malignancy of NMLs were calcifications (65.6%), posterior shadowing (62.8%), and nonparallel orientation (59.3%). In multivariable analysis, variables showing significant independent associations with malignancy included calcifications (OR = 8.9), asymmetry (OR = 4.7), and mass (OR = 6.4) on mammography and greater size (OR = 1.03), nonparallel orientation (OR = 8.8), and posterior shadowing (OR = 6.3) on ultrasound. CONCLUSION. The analysis provides insights regarding reader variability for classifying ultrasound lesions as NMLs on the basis of an existing definition as well as regarding the potential utility of imaging findings for characterizing such lesions as malignant. CLINICAL IMPACT. These findings indicate the need for further precision and clarification regarding the definition of NMLs and for further investigation to determine which NMLs have the greatest malignancy risk.

Extremely dense breasts: A comprehensive review of increased cancer risk and supplementary screening methods

Women with extremely dense breasts account for approximately 10% of the screening population and face an increased lifetime risk of developing breast cancer. At the same time, the sensitivity of mammography, the first-line screening modality, is significantly reduced in this breast density group, owing to the masking effect of the abundant fibroglandular tissue. Consequently, this population has garnered increasing scientific attention due to the unique diagnostic challenge they present. Several research initiatives have attempted to address this diagnostic challenge by incorporating supplemental imaging modalities such as ultrasound, MRI, and contrast-enhanced mammography. Each of these modalities offers different benefits as well as limitations, both clinically and practically, including considerations of availability and costs. The purpose of this article is to critically review the background, latest scientific evidence, and future directions for the use of the various supplemental screening techniques for women with extremely dense breasts.

Prevalence and outcomes of nonmass lesions detected on screening breast ultrasound based on ultrasound features

PURPOSE

To determine how often non-mass lesions are seen in screening breast ultrasounds, and analyze their ultrasound features according to the ultrasound lexicon to find features suggestive of malignant non-mass lesions.

METHODS

This study is a single center retrospective study for nonmass lesions on screening breast ultrasound. Among 21,604 patients who underwent screening breast US, there were 279 patients with nonmass lesions. Of these lesions, 242 lesions were included for analysis. To distinguish between benign and malignant nonmass lesions, univariate analysis was performed on size, echogenicity, distribution, orientation, and associated ultrasound features. Additionally, Fisher's exact test was performed for mammographic density and abnormalities.

RESULTS

279 patients with nonmass lesions were included (mean age 53.7 ± 9.7 years, all women). The incidence of nonmass lesions on screening breast ultrasound was 1.29% with positive predictive value of 5.78%. The most common malignant nonmass lesion was ductal carcinoma in situ. Nonparallel orientation (p = 0.002), echogenic rim (p = 0.005), architectural distortion (p = 0.0004), posterior shadowing (p = 0.007), vascularity (p < 0.001), and calcifications (p < 0.001) were indicators of malignant lesions. Additionally, mammographic abnormalities were significantly associated with malignant lesions (p < 0.001).

CONCLUSION

The incidence of nonmass lesions on screening breast ultrasound was 1.29%, with a positive predictive value of 5.78%. Mammographic abnormalities, nonparallel orientation, architectural distortion, posterior shadowing, vascularity, and calcifications were associated with malignant nonmass lesions.

Screening Outcomes of Mammography with AI in Dense Breasts: A Comparative Study with Supplemental Screening US

Background Comparative performance between artificial intelligence (AI) and breast US for women with dense breasts undergoing screening mammography remains unclear. Purpose To compare the performance of mammography alone, mammography with AI, and mammography plus supplemental US for screening women with dense breasts, and to investigate the characteristics of the detected cancers. Materials and Methods A retrospective database search identified consecutive asymptomatic women (≥40 years of age) with dense breasts who underwent mammography plus supplemental whole-breast handheld US from January 2017 to December 2018 at a primary health care center. Sequential reading for mammography alone and mammography with the aid of an AI system was conducted by five breast radiologists, and their recall decisions were recorded. Results of the combined mammography and US examinations were collected from the database. A dedicated breast radiologist reviewed marks for mammography alone or with AI to confirm lesion identification. The reference standard was histologic examination and 1-year follow-up data. The cancer detection rate (CDR) per 1000 screening examinations, sensitivity, specificity, and abnormal interpretation rate (AIR) of mammography alone, mammography with AI, and mammography plus US were compared. Results Among 5707 asymptomatic women (mean age, 52.4 years ± 7.9 [SD]), 33 (0.6%) had cancer (median lesion size, 0.7 cm). Mammography with AI had a higher specificity (95.3% [95% CI: 94.7, 95.8], P = .003) and lower AIR (5.0% [95% CI: 4.5, 5.6], P = .004) than mammography alone (94.3% [95% CI: 93.6, 94.8] and 6.0% [95% CI: 5.4, 6.7], respectively). Mammography plus US had a higher CDR (5.6 vs 3.5 per 1000 examinations, P = .002) and sensitivity (97.0% vs 60.6%, P = .002) but lower specificity (77.6% vs 95.3%, P < .001) and higher AIR (22.9% vs 5.0%, P < .001) than mammography with AI. Supplemental US alone helped detect 12 cancers, mostly stage 0 and I (92%, 11 of 12). Conclusion Although AI improved the specificity of mammography interpretation, mammography plus supplemental US helped detect more node-negative early breast cancers that were undetected using mammography with AI. © RSNA, 2024 Supplemental material is available for this article. See also the editorial by Whitman and Destounis in this issue.

Diagnostic performance with and without artificial intelligence assistance in real-world screening mammography

Purpose

To evaluate artificial intelligence-based computer-aided diagnosis (AI-CAD) for screening mammography, we analyzed the diagnostic performance of radiologists by providing and withholding AI-CAD results alternatively every month.

Methods

This retrospective study was approved by the institutional review board with a waiver for informed consent. Between August 2020 and May 2022, 1819 consecutive women (mean age 50.8 ± 9.4 years) with 2061 screening mammography and ultrasound performed on the same day in a single institution were included. Radiologists interpreted screening mammography in clinical practice with AI-CAD results being provided or withheld alternatively by month. The AI-CAD results were retrospectively obtained for analysis even when withheld from radiologists. The diagnostic performances of radiologists and stand-alone AI-CAD were compared and the performances of radiologists with and without AI-CAD assistance were also compared by cancer detection rate, recall rate, sensitivity, specificity, accuracy and area under the receiver-operating-characteristics curve (AUC).

Results

Twenty-nine breast cancer patients and 1790 women without cancers were included. Diagnostic performances of the radiologists did not significantly differ with and without AI-CAD assistance. Radiologists with AI-CAD assistance showed the same sensitivity (76.5%) and similar specificity (92.3% vs 93.8%), AUC (0.844 vs 0.851), and recall rates (8.8% vs. 7.4%) compared to standalone AI-CAD. Radiologists without AI-CAD assistance showed lower specificity (91.9% vs 94.6%) and accuracy (91.5% vs 94.1%) and higher recall rates (8.6% vs 5.9%, all p < 0.05) compared to stand-alone AI-CAD.

Conclusion

Radiologists showed no significant difference in diagnostic performance when both screening mammography and ultrasound were performed with or without AI-CAD assistance for mammography. However, without AI-CAD assistance, radiologists showed lower specificity and accuracy and higher recall rates compared to stand-alone AI-CAD.