文献速递甲状腺与浅表头颈US

超声计算机辅助诊断软件与不同经验水平放射科医师对甲状腺恶性病变诊断性能比较:多中心前瞻性研究

Diagnostic Performance of Ultrasound Computer-Aided Diagnosis Software Compared with That of Radiologists with Different Levels of Expertise for Thyroid Malignancy: A Multicenter Prospective Study.
PubMed 文献 · Ultrasound Med Biol · 2020-10-23

该多中心前瞻性研究纳入2019年1月至9月四家医院的494例患者(565个甲状腺结节),以病理结果为参考标准,比较超声甲状腺计算机辅助诊断(CAD)软件与不同经验水平放射科医师的诊断性能。CAD敏感度与高年资放射科医师相当(90.51% vs. 88.47%,p>0.05),AUC与低年资放射科医师相当(0.748 vs. 0.739,p>0.05),但特异度仅49.63%,低于三位放射科医师。低年资放射科医师借助CAD后敏感度和AUC分别从72.20%升至89.93%、从0.739升至0.816(均p<0.05),特异度从75.56%略降至73.33%(差异无统计学意义,p>0.05)。

要点

  • CAD敏感度90.51%与高年资医师88.47%相当,但特异度仅49.63%,低于低、中、高年资医师的75.56%、85.93%和90.37%。
  • 低年资医师借助CAD后敏感度从72.20%升至89.93%、AUC从0.739升至0.816(均p<0.05),特异度从75.56%降至73.33%(p>0.05)。
  • CAD对低年资放射科医师的辅助价值显著,但其临床应用于甲状腺恶性病变诊断的价值尚待明确。

核心结论

  • CAD敏感度与高年资放射科医师相当,AUC与低年资放射科医师相当,但特异度仅49.63%,低于三位放射科医师。
  • 低年资放射科医师借助CAD后敏感度和AUC显著提高,特异度略降但差异无统计学意义。
  • 作者认为CAD的临床应用价值有前景,对低年资放射科医师的辅助价值显著。

研究设计与样本

  • 多中心前瞻性研究,纳入2019年1月至2019年9月四家医院的494例患者(565个甲状腺结节),均在超声检查后接受手术或活检。
  • 以病理结果为参考标准,计算并比较不同阅片者的诊断性能指标。

诊断标准与关键数值

  • CAD敏感度90.51%,与高年资放射科医师88.47%相比差异无统计学意义(p>0.05)。
  • CAD的AUC为0.748,与低年资放射科医师0.739相比差异无统计学意义(p>0.05)。
  • CAD特异度49.63%,低于低年资、中年资和高年资放射科医师的75.56%、85.93%和90.37%。
  • 低年资医师联合CAD后敏感度从72.20%升至89.93%、AUC从0.739升至0.816(均p<0.05),阳性预测值从76.3%升至78.6%、阴性预测值从82.0%升至86.8%、κ系数从0.394升至0.511。
  • 低年资医师联合CAD后特异度从75.56%降至73.33%,差异无统计学意义(p>0.05)。

临床应用与阅片要点

  • CAD可作为低年资放射科医师提高甲状腺恶性病变检出敏感度的辅助工具,但其特异度较低,需结合医师判读。
  • CAD对高年资放射科医师的增益有限,其敏感度与高年资医师相当而特异度明显更低。

局限性

  • 原文未报告局限性。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

英文原文(摘要)· 点击展开

The aim of the work described here was to evaluate the diagnostic performance of ultrasound thyroid computer-aided diagnosis (CAD) software. This multicenter prospective study included 494 patients (565 thyroid nodules) who underwent surgery or biopsy after ultrasonography at four hospitals from January 2019 to September 2019. The diagnostic performance metrics of different readers were calculated and compared with the pathologic results. The sensitivity of CAD was outstanding and was equivalent to that of a senior radiologist (90.51% vs. 88.47%, p > 0.05). The area under the curve of CAD was equivalent to that of a junior radiologist (0.748 vs. 0.739, p > 0.05). However, the specificity was only 49.63%, which was lower than those of the three radiologists (75.56%, 85.93% and 90.37% for the junior, intermediate and senior radiologists, respectively). The diagnostic performance of the junior radiologist was significantly improved with the aid of CAD (junior + CAD). The sensitivity and area under the curve of junior + CAD were improved from 72.20% to 89.93% and from 0.739 to 0.816, respectively (both p values <0.05), and the positive predictive value, negative predictive value and κ coefficient improved from 76.3% to 78.6%, 82.0% to 86.8% and 0.394 to 0.511, respectively. Though specificity slightly decreased from 75.56% to 73.33%, the difference was not statistically significant (p > 0.05). In general, the clinical application value of CAD is promising, and its instrumental value for junior radiologists is significant.

来源:Ultrasound Med Biol,查看原文。版权归原作者所有。

引用

  1. Ye FY, Lyu GR, Li SQ, et al. Diagnostic Performance of Ultrasound Computer-Aided Diagnosis Software Compared with That of Radiologists with Different Levels of Expertise for Thyroid Malignancy: A Multicenter Prospective Study. Ultrasound Med Biol. 2020. PMID: 33239154. doi:10.1016/j.ultrasmedbio.2020.09.019

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。