Miura Daisuke, Suenaga Hiromi, Hiwatashi Rino, Mabu Shingo
Department of Ultrasound and Clinical Laboratory, Fukuoka Tokushukai Hospital, Fukuoka, 816-0864, Japan.
Department of Laboratory Science, Yamaguchi University Graduate School of Medicine, Yamaguchi, 755-8508, Japan.
BMC Med Imaging. 2025 Jan 7;25(1):8. doi: 10.1186/s12880-024-01531-x.
Monitoring fibrosis in patients with chronic liver disease (CLD) is an important management strategy. We have already reported a novel stacked microvascular imaging (SMVI) technique and an examiner scoring evaluation method to improve fibrosis assessment accuracy and demonstrate its high sensitivity. In the present study, we analyzed the effectiveness and objectivity of SMVI in diagnosing the liver fibrosis stage based on artificial intelligence (AI).
This single-center, cross-sectional study included 517 patients with CLD who underwent ultrasonography and liver stiffness testing between August 2019 and October 2022. A convolutional neural network model was constructed to evaluate the degree of liver fibrosis from stacked microvascular images generated by accumulating high-sensitivity Doppler (i.e., high-definition color) images from these patients. In contrast, as a method of judgment by the human eye, we focused on three hallmarks of intrahepatic microvessel morphological changes in the stacked microvascular images: narrowing, caliber irregularity, and tortuosity. The degree of liver fibrosis was classified into five stages according to etiology based on liver stiffness measurement: F0-1Low (< 5.0 kPa), F0-1High (≥ 5.0 kPa), F2, F3, and F4.
The AI classification accuracy was 53.8% for a 5-class classification, 66.3% for a 3-class classification (F0-1Low vs. F0-1High vs. F2-4), and 83.8% for a 2-class classification (F0-1 vs. F2-4). The diagnostic accuracy for ≥ F2 was 81.6% in the examiner's score assessment, compared with 83.8% in AI assessment, indicating that AI achieved higher diagnostic accuracy. Similarly, AI demonstrated higher sensitivity and specificity of 84.2% and 83.5%, respectively. Comparing human judgement with AI judgement, the AI analysis was a superior model with a higher F1 score in the 2-class classification.
In detecting significant fibrosis (≥ F2) using the SMVI method, AI-based assessments are more accurate than human judgement; moreover, AI-based SMVI analysis eliminating human subjectivity bias and determining patients with objective fibrosis development is considered an important improvement.
监测慢性肝病（CLD）患者的纤维化是一项重要的管理策略。我们已经报道了一种新型的堆叠微血管成像（SMVI）技术和一种检查者评分评估方法，以提高纤维化评估的准确性并证明其高敏感性。在本研究中，我们基于人工智能（AI）分析了SMVI在诊断肝纤维化阶段的有效性和客观性。
这项单中心横断面研究纳入了517例CLD患者，这些患者在2019年8月至2022年10月期间接受了超声检查和肝脏硬度检测。构建了一个卷积神经网络模型，以从通过累积这些患者的高灵敏度多普勒（即高清彩色）图像生成的堆叠微血管图像中评估肝纤维化程度。相比之下，作为一种人眼判断方法，我们关注堆叠微血管图像中肝内微血管形态变化的三个特征：变窄、管径不规则和迂曲。根据肝脏硬度测量的病因，肝纤维化程度分为五个阶段：F0-1低（<5.0 kPa）、F0-1高（≥5.0 kPa）、F2、F3和F4。
在5类分类中，AI分类准确率为53.8%，在3类分类（F0-1低vs. F0-1高vs. F2-4）中为66.3%，在2类分类（F0-1 vs. F2-4）中为83.8%。在检查者评分评估中，≥F2的诊断准确率为81.6%，而在AI评估中为83.8%，这表明AI实现了更高的诊断准确率。同样，AI分别表现出更高的敏感性和特异性，分别为84.2%和83.5%。将人工判断与AI判断进行比较，在2类分类中，AI分析是一个具有更高F1分数的更优模型。
在使用SMVI方法检测显著纤维化（≥F2）时，基于AI的评估比人工判断更准确；此外，基于AI的SMVI分析消除了人为主观偏差并确定了具有客观纤维化进展的患者，被认为是一项重要的改进。
