摘要
目的探讨人工智能S-Detect技术联合多模态超声诊断乳腺黏液癌的价值。方法回顾性分析2022年1月至2024年1月经手术病理证实的125例乳腺黏液癌患者及159例乳腺纤维腺瘤患者的临床资料,所有结节均为先行常规超声检查判断BI-RADS分级,再由人工智能S-Detect技术判断分级,接着行SWE检查,根据弹性模量最大值(Emax)在人工智能S-Detect辅助诊断系统基础上调整分级,以病理结果为金标准,比较两次分级的诊断效能。结果乳腺黏液癌患者年龄大于纤维腺瘤患者(P<0.05)。乳腺黏液癌结节的弹性模量Emax大于乳腺纤维腺瘤(P<0.05)。人工智能辅助诊断系统联合多模态超声诊断的敏感度、特异度及准确性均高于单独常规超声(P<0.05)。结论乳腺黏液癌与乳腺纤维腺瘤在二维超声声像图部分超声特征相似,人工智能S-Detect技术联合多模态超声可提高乳腺黏液癌的诊断效能,对临床早诊断具有重要意义。
Objective To evaluate the diagnostic value of artificial intelligence S-Detect system combined with multimodal ultrasound in breast mucinous carcinoma.Methods The data of 125 patients with mucinous carcinoma of the breast and 159 patients with fibladenoma of the breast confirmed by surgery and pathology in our hospital from January 2022 to January 2024 were retrospectively analyzed.All nodars were evaluated by routine ultrasonography first to determine the BI-RADS grade.Then the classification was judged by the artificial intelligence S-Detect technology,followed by SWE examination,and the classification was adjusted on the basis of the artificial intelligence S-Detect auxiliary diagnosis system according to the elastic modulus Emax value.The diagnostic efficiency of the two classifications was compared with the pathological results as the gold standard.Results The age of patients with mucinous carcinoma of breast was higher than that of patients with fibroadenoma(P<0.05).The maximum elastic modulus Emax of breast mucinous carcinoma nodules was greater than that of breast fibroadenoma(P<0.05).The sensitivity,specificity and accuracy of AI-assisted diagnosis system combined with multimodal ultrasound were higher than those of conventional ultrasound alone(P<0.05).Conclusion The ultrasonic characteristics of breast mucinous carcinoma and breast fibronenoma are similar in two-dimensional ultrasonography.The combination of artificial intelligence system assisted diagnosis system and multimodal ultrasound can improve the diagnostic efficiency of breast mucinous carcinoma,which is of great significance for early clinical diagnosis.
出处
《浙江临床医学》
2025年第7期1067-1069,共3页
Zhejiang Clinical Medical Journal
基金
金华市科技计划项目(2022-4-129)。
关键词
人工智能辅助诊断系统
乳腺黏液癌
多模态超声
联合诊断
Artificial intelligence aided diagnosis system
Breast mucinous carcinoma
Multimode ultrasound
Combined diagnosis
