To investigate the application value of ultrasound artificial intelligence S-Detect technology in the differential diagnosis of benign and malignant breast nodules.
Methods
Suspicious breast nodules were examined using S-Detect technology, conventional ultrasound (US), and contrast-enhanced ultrasound (CEUS). The differential diagnoses were compared with final pathological results to analyze the diagnostic efficacy of these three techniques in distinguishing benign from malignant breast nodules.
Results
The accuracy of S-Detect in diagnosing benign and malignant breast nodules was 0.859, with a sensitivity of 0.915, specificity of 0.839, and an area under the ROC curve (AUC) of 0.877. The value of AUC was significantly higher than that of US (0.727, P < 0.01), but lower than US + CEUS (0.908, P < 0.05). According to the final pathological classification, S-Detect demonstrated higher accuracy in distinguishing benign from malignant lesions in complex cysts, hyperplastic nodules, and adenomas compared to US (P < 0.05), with no significant difference when compared to US + CEUS. In differentiating malignant breast tumors, there was no significant difference in accuracy between S-Detect and US.
Conclusion
Ultrasound artificial intelligence S-Detect technology exhibits high diagnostic efficacy in the differential diagnosis of benign and malignant breast nodules.
SungHFerlayJSiegelRL, et al.Global cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J Clin2021; 71: 209–249.
2.
ArnoldMMorganERumgayH, et al.Current and future burden of breast cancer: global statistics for 2020 and 2040. Breast2022; 66: 15–23.
3.
WuCLiMMengH, et al.Analysis of status and countermeasures of cancer incidence and mortality in China. Sci China Life Sci2019; 62: 640–647.
4.
GuoRLuGQinB, et al.Ultrasound imaging technologies for breast cancer detection and management: a review. Ultrasound Med Biol2018; 44: 37–70.
5.
YuMQZhangLLJiangLP, et al.The value of contrast-enhanced ultrasound in the diagnosis of BI-RADS-US 4a lesions less than 2 cm in diameter. Clin Hemorheol Microcirc2023; 83: 195–205.
6.
YiJKangHKKwonJH, et al.Technology trends and applications of deep learning in ultrasonography: image quality enhancement, diagnostic support, and improving workflow efficiency. Ultrasonography2021; 40: 7–22.
7.
MariniTJCastanedaBParkerK, et al.No sonographer, no radiologist: assessing accuracy of artificial intelligence on breast ultrasound volume sweep imaging scans. PLOS Digit Health2022; 1: e0000148.
8.
O'ConnellAMBartolottaTVOrlandoA, et al.Diagnostic performance of an artificial intelligence system in breast ultrasound. J Ultrasound Med2022; 41: 97–105.
9.
SunPFengYChenC, et al.An AI model of sonographer's evaluation + S-detect + elastography + clinical information improves the preoperative identification of benign and malignant breast masses. Front Oncol2022; 12: 1022441.
10.
XingBChenXWangY, et al.Evaluating breast ultrasound S-detect image analysis for small focal breast lesions. Front Oncol2022; 12: 1030624.
11.
ChenJLiCXShaoSH, et al.The association between conventional ultrasound and contrast-enhanced ultrasound appearances and pathological features in small breast cancer. Clin Hemorheol Microcirc2022; 80: 413–422.
12.
HuQWangXYZhuSY, et al.Meta-analysis of contrast-enhanced ultrasound for the differentiation of benign and malignant breast lesions. Acta Radiol2015; 56: 25–33.
13.
WenPLiuLPanL, et al.Evaluating diagnostic significance: the utilization of elastography and contrast-enhanced ultrasound for differential diagnosis in breast lesions. Clin Hemorheol Microcirc2024; 88: 81–95.
14.
JiangTJiangYChenW, et al.Chinese Association of ultrasound in medicine and engineering, superficial organs and peripheral vessels committee expert consensus on clinical frequently asked questions in breast ultrasonography, June 2018. J Cancer Res Ther2018; 14: 1463–1468.
15.
DrudiFMCantisaniVGnecchiM, et al.Contrast-enhanced ultrasound examination of the breast: a literature review. Ultraschall Med2012; 33: E1–E7.
16.
ZhangYFowlkesB. Liposomes-based nanoplatform enlarges ultrasound-related diagnostic and therapeutic precision. Curr Med Chem2022; 29: 1331–1341.
17.
MandavaARavuriPRKonathanR. High-resolution ultrasound imaging of cutaneous lesions. Indian J Radiol Imaging2013; 23: 269–277.
18.
LeeSHChangJMKimWH, et al.Added value of shear-wave elastography for evaluation of breast masses detected with screening US imaging. Radiology2014; 273: 61–69.
19.
WangFWangWSunN, et al.Diagnostic value of multimodal ultrasound strategies in the differentiation of non-mass-like breast lesions. J Clin Ultrasound2023; 51: 848–856.
20.
ContiADuggentoAIndovinaI, et al.Radiomics in breast cancer classification and prediction. Semin Cancer Biol2021; 72: 238–250.
21.
WangWZhengYWuXF, et al.Value of contrast-enhanced ultrasound area ratio in identifying benign and malignant small breast masses. Gland Surg2020; 9: 1486–1494.
22.
ZhaoDHeNShaoYQ, et al.The diagnostic value of contrast-enhanced ultrasound for cervical tuberculous lymphadenitis. Clin Hemorheol Microcirc2022; 81: 69–79.
23.
TianYWangWHuY, et al.The size differences of breast cancer and benign tumors measured by two-dimensional ultrasound and contrast-enhanced ultrasound. J Ultrasound Med2024; 43: 1245–1250.
24.
ZhouSCLeJZhouJ, et al.The role of contrast-enhanced ultrasound in the diagnosis and pathologic response prediction in breast cancer: a meta-analysis and systematic review. Clin Breast Cancer2020; 20: e490–e509.
25.
DiaoXZhanJChenL, et al.Role of superb microvascular imaging in differentiating between malignant and benign solid breast masses. Clin Breast Cancer2020; 20: e786–e793.
26.
LiQHuMChenZ, et al.Meta-Analysis: contrast-enhanced ultrasound versus conventional ultrasound for differentiation of benign and malignant breast lesions. Ultrasound Med Biol2018; 44: 919–929.
27.
BeneIBDudeaSMCiureaAI. Contrast-Enhanced ultrasonography in the diagnosis and treatment modulation of breast cancer. J Pers Med2021; 11: 81.
28.
DuJWangLWanCF, et al.Differentiating benign from malignant solid breast lesions: combined utility of conventional ultrasound and contrast-enhanced ultrasound in comparison with magnetic resonance imaging. Eur J Radiol2012; 81: 3890–3899.
29.
FujiokaTKubotaKMoriM, et al.Distinction between benign and malignant breast masses at breast ultrasound using deep learning method with convolutional neural network. Jpn J Radiol2019; 37: 466–472.
30.
KimKSongMKKimEK, et al.Clinical application of S-Detect to breast masses on ultrasonography: a study evaluating the diagnostic performance and agreement with a dedicated breast radiologist. Ultrasonography2017; 36: 3–9.
31.
XiaoMZhaoCZhuQ, et al.An investigation of the classification accuracy of a deep learning framework-based computer-aided diagnosis system in different pathological types of breast lesions. J Thorac Dis2019; 11: 5023–5031.
32.
ChoiJSHanBKKoES, et al.Effect of a deep learning framework-based computer-aided diagnosis system on the diagnostic performance of radiologists in differentiating between malignant and benign masses on breast ultrasonography. Korean J Radiol2019; 20: 749–758.
33.
YongpingLZhouPJuanZ, et al.Performance of computer-aided diagnosis in ultrasonography for detection of breast lesions less and more than 2 cm: prospective comparative study. JMIR Med Inform2020; 8: e16334.
