检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
作 者:李琪 李丰章 刘天笑 LI Qi;LI Fengzhang;LIU Tianxiao(Department of Imaging,Pingxiang People's Hospital,Pingxiang 337000,China)
出 处:《中国医学创新》2024年第24期139-142,共4页Medical Innovation of China
摘 要:目的:观察乳腺人工智能(AI)与钼靶在乳腺结节定性诊断及术前指导中的应用价值。方法:选取2019年1月—2023年6月萍乡市人民医院收治的乳腺结节患者164例,对所有患者行乳腺AI检查及乳腺钼靶检查,以病理诊断结果为金标准,比较乳腺AI、钼靶及两者联合对乳腺结节定性诊断及术前指导的价值。结果:164例患者中,经手术病理结果发现174个乳腺结节,共136个良性病变(纤维腺瘤54例,乳腺病26例,肉芽肿性小叶性乳腺炎52例,单纯性囊肿4例),38个恶性病变(浸润性导管癌14例,乳头状癌12例,导管原位癌12例)。乳腺AI检查定性诊断乳腺结节的敏感度、特异度及准确性分别为73.68%、91.17%及87.36%;乳腺钼靶检查为57.89%、85.29%及79.31%;两者联合敏感度及准确性分别为89.47%、91.95%,均显著高于单独诊断,差异均有统计学意义(P<0.05)。结论:乳腺AI联合钼靶检测能显著提高乳腺结节定性诊断效能,对于乳腺结节术前评估价值较高。Objective:To observe the application value of breast artificial intelligence(AI)and mammography in qualitative diagnosis and preoperative guidance of breast nodules.Method:A total of 164 patients with breast nodules admitted to Pingxiang People's Hospital from January 2019 to June 2023 were selected,and all patients underwent breast AI and mammography.The pathological diagnosis results were used as the gold standard.The value of breast AI,mammography and their combination in qualitative diagnosis and preoperative guidance of breast nodules were compared.Result:Among 164 patients,174 breast nodules were found through surgical pathology,with a total of 136 benign lesions(54 fibroadenomas,26 breast diseases,52 granulomatous lobular mastitis and 4 simple cysts)and 38 malignant lesions(14 invasive ductal carcinoma,12 papillary carcinoma and 12 ductal carcinoma in situ).The sensitivity,specificity and accuracy of qualitative diagnosis of breast nodules using breast AI examination were 73.68%,91.17%and 87.36%,respectively;those of breast molybdenum target examination was 57.89%,85.29%and 79.31%;the combined sensitivity and accuracy of the two methods were 89.47%and 91.95%,respectively,which were significantly higher than those of individual diagnosis,the differences were statistically significant(P<0.05).Conclusion:Breast AI combined with mammography can significantly improve the qualitative diagnostic efficiency of breast nodules,and has high value in preoperative evaluation of breast nodules.
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:216.73.216.49