Moga Tudor Voicu, Popescu Alina, Sporea Ioan, Danila Mirela, David Ciprian, Gui Vasile, Iacob Nicoleta, Miclaus Gratian, Sirli Roxana
University of Medicine and Pharmacy "Victor Babes" Timisoara. Department of Gastroenterology and Hepatology at the County Hospital Timisoara.
University of Medicine and Pharmacy "Victor Babes" Timisoara. Department of Gastroenterology and Hepatology at the County Hospital Timisoara..
Med Ultrason. 2017 Aug 23;19(3):252-258. doi: 10.11152/mu-936.
Contrast enhanced ultrasound (CEUS) improved the characterization of focal liver lesions (FLLs), but is an operatordependent method. The goal of this paper was to test a computer assisted diagnosis (CAD) prototype and to see its benefit in assisting a beginner in the evaluation of FLLs.
Our cohort included 97 good quality CEUS videos[34% hepatocellular carcinomas (HCC), 12.3% hypervascular metastases (HiperM), 11.3% hypovascular metastases (HipoM), 24.7% hemangiomas (HMG), 17.5% focal nodular hyperplasia (FNH)] that were used to develop a CAD prototype based on an algorithm that tested a binary decision based classifier. Two young medical doctors (1 year CEUS experience), two experts and the CAD prototype, reevaluated 50 FLLs CEUS videos (diagnosis of benign vs. malignant) first blinded to clinical data, in order to evaluate the diagnostic gap beginner vs. expert.
The CAD classifier managed a 75.2% overall (benign vs. malignant) correct classification rate. The overall classification rates for the evaluators, before and after clinical data were: first beginner-78%; 94%; second beginner-82%; 96%; first expert-94%; 100%; second expert-96%; 98%. For both beginners, the malignant vs. benign diagnosis significantly improved after knowing the clinical data (p=0.005; p=0,008). The expert was better than the beginner (p=0.04) and better than the CAD (p=0.001). CAD in addition to the beginner can reach the expert diagnosis.
The most frequent lesions misdiagnosed at CEUS were FNH and HCC. The CAD prototype is a good comparing tool for a beginner operator that can be developed to assist the diagnosis. In order to increase the classification rate, the CAD system for FLL in CEUS must integrate the clinical data.
超声造影（CEUS）改善了肝脏局灶性病变（FLLs）的特征描述，但这是一种依赖操作者的方法。本文的目的是测试一种计算机辅助诊断（CAD）原型，并观察其在协助初学者评估FLLs方面的益处。
我们的队列包括97个高质量的CEUS视频[34%为肝细胞癌（HCC），12.3%为高血供转移瘤（HiperM），11.3%为低血供转移瘤（HipoM），24.7%为血管瘤（HMG），17.5%为局灶性结节性增生（FNH）]，这些视频被用于基于测试二元决策分类器的算法开发一个CAD原型。两名年轻医生（有1年CEUS经验）、两名专家以及CAD原型，首先在对临床数据不知情的情况下重新评估50个FLLs的CEUS视频（诊断良性与恶性），以评估初学者与专家之间的诊断差距。
CAD分类器的总体（良性与恶性）正确分类率为75.2%。临床数据前后评估者的总体分类率分别为：第一位初学者-78%；94%；第二位初学者-82%；96%；第一位专家-94%；100%；第二位专家-96%；98%。对于两位初学者而言，了解临床数据后恶性与良性诊断均有显著改善（p=0.005；p=0.008）。专家比初学者表现更好（p=0.04），且比CAD更好（p=0.001）。CAD与初学者一起可以达到专家诊断水平。
CEUS误诊最常见的病变是FNH和HCC。CAD原型对于初学者操作员是一个很好的比较工具，可以进一步开发以协助诊断。为了提高分类率，CEUS中用于FLL的CAD系统必须整合临床数据。
