Institute of Science and Technology for Brain-inspired Intelligence, Fudan University, Shanghai, People's Republic of China.
Department of Radiology, Ruijin Hospital, Shanghai JiaoTong University School of Medicine, Shanghai, People's Republic of China.
Phys Med Biol. 2021 Apr 16;66(8). doi: 10.1088/1361-6560/abf2f8.
Early detection of hepatocellular carcinoma (HCC) is crucial for clinical management. Current studies have reported large HCC detections using automatic algorithms, but there is a lack of research on automatic detection of small HCCs (sHCCs). This study is to investigate the feasibility of automatic detection of sHCC (≤2 cm) based on pattern matching and deep learning (PM-DL) model.. A retrospective study included 5376 image sets from 56 cirrhosis patients (28 sHCC patients with 32 pathologically confirmed lesions and 28 non-HCC cirrhosis patients) in the training-validation cohort to build and validate the model through five-fold cross-validation. In addition, an external test cohort including 6144 image sets from 64 cirrhosis patients (32 sHCC patients with 38 lesions and 32 non-HCC cirrhosis patients) was applied to further verify the generalization ability of the model. The proposed PM-DL model consisted of three main steps: 3D co-registration and liver segmentation, screening of suspicious lesions on diffusion-weighted imaging images based on pattern matching algorithm, and identification/segmentation of sHCC lesions on dynamic contrast-enhanced images with convolutional neural network.The PM-DL model achieved a sensitivity of 89.74% and a positive predictive value of 85.00% in the external test cohort for per-lesion analysis. No significant difference was observed in volumes (= 0.13) and the largest sizes (= 0.89) between manually delineated and segmented lesions. The DICE coefficient reached 0.77 ± 0.16. Similar performances were identified in the validation cohort. Moreover, the PM-DL model outperformed Liver Imaging Reporting and Data System (LI-RADS) in sensitivity (probable HCCs: LR-5 or LR-4,= 0.18; definite HCCs: LR-5,< 0.001), with a similar high specificity for per-patient analysis.. The PM-DL model may be feasible for accurate automatic detection of sHCC in cirrhotic liver.
肝细胞癌 (HCC) 的早期检测对于临床管理至关重要。目前的研究已经报道了使用自动算法对大 HCC 进行检测，但对于小 HCC（sHCC）的自动检测研究较少。本研究旨在探讨基于模式匹配和深度学习（PM-DL）模型对 sHCC（≤2cm）进行自动检测的可行性。一项回顾性研究纳入了 56 例肝硬化患者（28 例 sHCC 患者，32 个经病理证实的病灶；28 例非 HCC 肝硬化患者）的 5376 个图像集，用于构建和验证模型，通过五重交叉验证。此外，还应用了一个包含 64 例肝硬化患者（32 例 sHCC 患者，38 个病灶；32 例非 HCC 肝硬化患者）的 6144 个图像集的外部测试队列，以进一步验证模型的泛化能力。所提出的 PM-DL 模型由三个主要步骤组成：3D 配准和肝脏分割、基于模式匹配算法在弥散加权成像图像上筛选可疑病灶、以及使用卷积神经网络在动态对比增强图像上识别/分割 sHCC 病灶。在外部测试队列中，对病灶进行分析，PM-DL 模型的敏感度为 89.74%，阳性预测值为 85.00%。手动勾画和分割病灶的体积（=0.13）和最大尺寸（=0.89）无显著差异。DICE 系数达到 0.77±0.16。在验证队列中也得到了类似的性能。此外，PM-DL 模型在敏感度方面优于肝脏影像报告和数据系统（LI-RADS）（可能 HCCs：LR-5 或 LR-4，=0.18；明确 HCCs：LR-5，<0.001），对于每位患者的分析具有相似的高特异性。PM-DL 模型可能是肝硬化中 sHCC 准确自动检测的一种可行方法。
