Computer-aided diagnosis prior to conventional interpretation of prostate mpMRI: an international multi-reader study

Computer-aided diagnosis prior to conventional interpretation of prostate mpMRI: an international multi-reader study
复制标题

DOI:
10.1007/s00330-018-5374-6
复制
发表时间:
2018-10-01
期刊:
影响因子:
5.9
通讯作者:
Turkbey, Baris
Turkbey, Baris
中科院分区:
医学2区
文献类型:
--
作者:
Greer, Matthew D.;Lay, Nathan;Turkbey, Baris

文献摘要

被引文献

相似文献

目的评价计算机辅助诊断(CAD)先于前列腺癌多参数磁共振成像(MpMRI)能否提高诊断的敏感性和医师间的一致性。自2012年4月至2015年6月,共163例患者接受了3-T mpMRI检查,其中110例肿瘤患者行mpMRI后行前列腺癌切除术,53例患者在mpMRI上无病变,TRUS引导下活检阴性。读者对所有结果都是盲目的,并根据mpMRI上的PI-RADSv2检测到病变。5周后,读者重新评估使用CAD检测病变的患者。在MRI上登记的前列腺切除标本是基本真实的,病理上定义了指标性病变。计算每个患者、病变平面、周围区(PZ)和移行区(TZ)的敏感度、特异度和符合率。结果单用mpMRI和CAD辅助mpMRI的指数病变敏感度分别为78.2%和86.3%(p=0.013)。TZ病变的敏感性相似(78.7%vs 78.1%;p=0.929);CAD改善了PZ病变的敏感性(84%vs 94%;p=0.003)。皮损敏感性的改善来自PI-RADS<3分,皮损敏感性与PI-RADS 3相当(77.6%vs78.1%;p=0.859)。每名患者对冠心病的特异性为57.1%,对mpMRI的特异性为70.4%(p=0.003)。CAD提高了所有读者之间的符合率(56.9%比71.8%;p<0.001)。结论CAD辅助mpMRI提高了不同经验的放射科医生之间的敏感度和一致性,但降低了特异度。中心点计算机辅助诊断帮助临床医生在MRI上检测前列腺癌。中心点计算机辅助诊断提高了放射科医生在检测前列腺癌病变方面的一致性。中心点计算机辅助诊断系统导致更多的假阳性,特别是对于经验较少的临床医生和过渡区。中心点计算机辅助诊断帮助放射科医生发现MRI漏诊的癌症,为提高诊断信心提供了一条途径。
ObjectivesTo evaluate if computer-aided diagnosis (CAD) prior to prostate multi-parametric MRI (mpMRI) can improve sensitivity and agreement between radiologists.MethodsNine radiologists (three each high, intermediate, low experience) from eight institutions participated. A total of 163 patients with 3-T mpMRI from 4/2012 to 6/2015 were included: 110 cancer patients with prostatectomy after mpMRI, 53 patients with no lesions on mpMRI and negative TRUS-guided biopsy. Readers were blinded to all outcomes and detected lesions per PI-RADSv2 on mpMRI. After 5 weeks, readers re-evaluated patients using CAD to detect lesions. Prostatectomy specimens registered to MRI were ground truth with index lesions defined on pathology. Sensitivity, specificity and agreement were calculated per patient, lesion level and zoneperipheral (PZ) and transition (TZ).ResultsIndex lesion sensitivity was 78.2% for mpMRI alone and 86.3% for CAD-assisted mpMRI (p = 0.013). Sensitivity was comparable for TZ lesions (78.7% vs 78.1%; p = 0.929); CAD improved PZ lesion sensitivity (84% vs 94%; p = 0.003). Improved sensitivity came from lesions scored PI-RADS < 3 as index lesion sensitivity was comparable at PI-RADS 3 (77.6% vs 78.1%; p = 0.859). Per patient specificity was 57.1% for CAD and 70.4% for mpMRI (p = 0.003). CAD improved agreement between all readers (56.9% vs 71.8%; p < 0.001).ConclusionsCAD-assisted mpMRI improved sensitivity and agreement, but decreased specificity, between radiologists of varying experience.Key Points center dot Computer-aided diagnosis (CAD) assists clinicians in detecting prostate cancer on MRI.center dot CAD assistance improves agreement between radiologists in detecting prostate cancer lesions.center dot However, this CAD system induces more false positives, particularly for less-experienced clinicians and in the transition zone.center dot CAD assists radiologists in detecting cancer missed on MRI, suggesting a path for improved diagnostic confidence.