Diagnostic performance of elastography for breast non-mass lesions: A systematic review and meta-analysis

Value of sonoelastography for diagnosis of breast non-mass lesions and comparison with BI-RADS: A systematic review and meta-analysis

BACKGROUND

Not all the breast lesions were mass-like, some were non-mass-like at ultrasonography. In these lesions, conventional ultrasonography had a high sensitivity but a low specificity. Sonoelastography can evaluate tissue stiffness to differentiate malignant masses from benign ones. Then what about the non-mass lesions? The aim of this study was to evaluate the current accuracy of sonoelastography in the breast non-mass lesions and compare the results with those of the American College of Radiology breast Imaging-Reporting and Data System (BI-RADS).

METHODS

An independent literature search of English medical databases, including PubMed, Web of Science, Embase & MEDLINE (Embase.com) and Cochrane Library, was performed by 2 researchers. The accuracy of sonoelastography was calculated and compared with those of BI-RADS.

RESULTS

Fourteen relevant studies including 1058 breast non-mass lesions were included. Sonoelastography showed a pooled sensitivity of 0.74 (95% CI: 0.70-0.78), specificity of 0.89 (95% CI: 0.85-0.91), diagnostic odds ratio (DOR) of 25.22 (95% CI: 17.71-35.92), and an area under the curve of 0.9042. Eight articles included both sonoelastography and BI-RADS. The pooled sensitivity, specificity, DOR and AUC were 0.69 versus 0.91 (P < .01), 0.90 versus 0.68 (P < .01), 19.65 versus 29.34 (P > .05), and 0.8685 versus 0.9327 (P > .05), respectively.

CONCLUSIONS

Sonoelastography has a higher specificity and a lower sensitivity for differential diagnosis between malignant and benign breast non-mass lesions compared with BI-RADS, although there were no differences in AUC between them.

Beyond BI-RADS: Nonmass Abnormalities on Breast Ultrasound

Abnormalities on breast ultrasound (US) images which do not meet the criteria for masses are referred to as nonmass lesions. These features and outcomes have been investigated in several studies conducted by Asian researchers. However, the term "nonmass" is not included in the American College of Radiology (ACR) Breast Imaging Reporting and Data System (BI-RADS) 5th edition for US. According to the Japan Association of Breast and Thyroid Sonology guidelines, breast lesions are divided into mass and nonmass. US findings of nonmass abnormalities are classified into five subtypes: abnormalities of the ducts, hypoechoic areas in the mammary glands, architectural distortion, multiple small cysts, and echogenic foci without a hypoechoic area. These findings can be benign or malignant; however, focal or segmental distributions and presence of calcifications suggest malignancy. Intraductal, invasive ductal, and lobular carcinomas can present as nonmass abnormalities. For the nonmass concept to be included in the next BI-RADS and be widely accepted in clinical practice, standardized terminologies, an interpretation algorithm, and outcome-based evidence are required for both screening and diagnostic US.

Artificial intelligence for non-mass breast lesions detection and classification on ultrasound images: a comparative study

BACKGROUND

This retrospective study aims to validate the effectiveness of artificial intelligence (AI) to detect and classify non-mass breast lesions (NMLs) on ultrasound (US) images.

METHODS

A total of 228 patients with NMLs and 596 volunteers without breast lesions on US images were enrolled in the study from January 2020 to December 2022. The pathological results served as the gold standard for NMLs. Two AI models were developed to accurately detect and classify NMLs on US images, including DenseNet121_448 and MobileNet_448. To evaluate and compare the diagnostic performance of AI models, the area under the curve (AUC), accuracy, specificity and sensitivity was employed.

RESULTS

A total of 228 NMLs patients confirmed by postoperative pathology with 870 US images and 596 volunteers with 1003 US images were enrolled. In the detection experiment, the MobileNet_448 achieved the good performance in the testing set, with the AUC, accuracy, sensitivity, and specificity were 0.999 (95%CI: 0.997-1.000),96.5%,96.9% and 96.1%, respectively. It was no statistically significant compared to DenseNet121_448. In the classification experiment, the MobileNet_448 model achieved the highest diagnostic performance in the testing set, with the AUC, accuracy, sensitivity, and specificity were 0.837 (95%CI: 0.990-1.000), 70.5%, 80.3% and 74.6%, respectively.

CONCLUSIONS

This study suggests that the AI models, particularly MobileNet_448, can effectively detect and classify NMLs in US images. This technique has the potential to improve early diagnostic accuracy for NMLs.