S-DetectTM分类技术诊断BI-RADS 4类乳腺肿块

目的 观察S-Detect^TM分类技术鉴别诊断BI-RADS 4类乳腺良恶性肿块的价值。方法 对94例经二维超声诊断为BI-RADS 4类乳腺肿块患者（共104个肿块）行S-Detect^TM分类技术检查，以手术或穿刺活检病理结果作为金标准，评价S-Detect^TM分类技术、BI-RADS分类及二者联合应用诊断乳腺BI-RADS 4类良恶性肿块的价值。结果 104个乳腺肿块，经病理确诊为良性41个、恶性63个。S-Detect^TM分类技术诊断乳腺BI-RADS 4a类乳腺肿块的敏感度（SE）66.67%，特异度（SP）89.29%、阳性预测值（PPV）57.14%、阴性预测值（NPV）92.59%；对乳腺BI-RADS 4b类肿块分别为90.91%、60.00%、88.24%及66.67%；对乳腺BI-RADS 4c类肿块分别为95.83%、66.67%、95.83%及66.67%。S-Detect^TM分类技术联合BI-RADS分类诊断乳腺肿块的SE、SP、准确率明显均高于单独运用（P均<0.05）。结论 S-Detect^TM分类技术判断乳腺BI-RADS 4a类良性肿块、BI-RADS 4b类及BI-RADS 4c类恶性肿块均有较高价值。S-Detect^TM分类技术联合BI-RADS分类可明显提高鉴别BI-RADS 4类乳腺良恶性肿块的效能。

S-DetectTM classification technique in diagnosis of BI-RADS 4 breast masses

Objective To explore the diagnostic value of S-Detect^TM classification technique for benign and malignant breast imaging reporting and data system (BI-RADS) 4 breast masses. Methods Totally 94 patients with 104 two-dimensional ultrasound diagnosed BI-RADS 4 breast masses were examined using S-Detect^TM classification technique. Taken pathological results as the gold standards, the diagnostic values of S-Detect^TM classification technology, BI-RADS classification alone and the combination of them of benign and malignant breast BI-RADS 4 masses were observed. Results There were 41 benign and 63 malignant ones among all 104 BI-RADS 4 breast masses. The sensitivity (SE) of S-Detect^TM classification technique for diagnosing breast BI-RADS 4a mass was 66.67%, specificity (SP) was 89.29%, positive predictive value (PPV) was 57.14%, negative predictive value (NPV) was 92.59%, of BI-RADS 4b masses was 90.91%, 60.00%, 88.24% and 66.67%, of breast BI-RADS 4c mass was 95.83%, 66.67%, 95.83% and 66.67%, respectively. SE, SP and accuracy of combination of S-Detect^TM classification and BI-RADS classification for diagnosing breast masses were significantly higher than those of BI-RADS classification and S-Detect^TM classification technique alone (all P<0.05). Conclusion S-Detect^TM classification technique was valuable for judging BI-RADS 4a benign masses as well as BI-RADS 4b and BI-RADS 4c malignant masses. S-Detect^TM classification technology combined with BI-RADS classification could significantly improve the diagnostic value of identifying benign and malignant BI-RADS 4 breast masses.