深度学习在平扫多序列MRI上自动分割与检出肝脏局灶病变
该研究评估了基于3D V-Net的AI模型在多序列平扫MRI上自动分割和检出肝脏局灶病变的表现。模型在外部验证集中经序列间交叉核实后的检出敏感度达0.972–0.978,患者水平敏感度达0.987。DWI高b值序列对恶性病变、fsT2WI对良性病变显示出一定优势。
要点
- 平扫多序列MRI的AI检出敏感度高,可作为无对比剂场景下的辅助筛查工具。
- DWI高b值对<10 mm恶性病变敏感度更高,fsT2WI对良性病变更优。
- 模型对≥40 mm病灶的检出敏感度受序列影响,阅片时应结合多序列综合判断。
核心结论
- 深度学习AI模型可在平扫MRI上实现肝脏局灶病变的自动分割与检出,在不同病灶大小间表现可接受。
- 经序列间交叉核实后,外部验证集敏感度在T1WI、fsT2WI和DWI高b值分别达到0.978、0.978和0.972。
研究设计与样本
- 研究类型为深度学习模型开发与验证,纳入1010例平扫MRI为训练集,144例连续MRI为留出验证集。
- 使用公开数据集LLDMMRI-2023和CHAOS作为外部验证集,序列包括T1WI、fsT2WI和高b值DWI。
- 以放射科医生在单序列上的标注作为参考标准,采用两阶段顺序3D V-Net进行病灶分割。
关键影像表现/征象
- 模型输出为病灶分割掩膜,当预测掩膜与参考标准之间的Dice系数大于0时判定该病灶为检出。
- 病灶大小按20 mm切分并进一步分为<10 mm、10-20 mm、20-40 mm和≥40 mm四组分析。
诊断标准与关键数值
- 训练集、留出集和外部验证集的平均Dice系数分别为0.535、0.590和0.596。
- 留出集各序列敏感度为0.794–0.882,核实后敏感度均>0.93,单序列假阳性病灶为0.50、1.94、1.42。
- 外部验证集单序列假阳性病灶数分别为0.60、1.66和0.90,患者水平敏感度为0.988和0.987。
- DWI高b值对<20 mm与≥40 mm病灶间敏感度差异有统计学意义(p<0.001),<10 mm亚组恶性病变敏感度更高(p<0.001)。
临床应用与阅片要点
- 该模型可用于无对比剂平扫MRI的肝脏病灶初筛,尤其适合肾功能不全或对比剂禁忌患者。
- DWI高b值对恶性小病灶敏感度高,fsT2WI对良性病灶检出更优,报告时可结合序列优势综合评估。
局限性
- 外部验证集中良性恶性对比仅基于外部数据集,原文未提供外部验证集病灶性质的确切病理证实方式。
- 病灶检出判定依赖预测掩膜与参考标注的Dice系数大于0,可能高估对小病灶的检出性能。
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
PURPOSE: To evaluate the performance of a deep learning-based artificial intelligence (AI) model for the multi-sequence automated segmentation and detection of focal liver lesions (FLLs) on non-contrast MRI (NC-MRI).
METHODS: A total of 1010 NC-MRI were included as the training set, and 144 consecutive MRI were collected as the hold-out set. The publicly available LLDMMRI-2023 and CHAOS datasets were utilized for external validation. T1WI, fat-saturated T2WI (fsT2WI), and high-b-value DWI (DWI_High) were included. Radiologist annotations on individual sequences served as the reference standard. A two-stage sequential 3D V-Net was implemented for FLLs segmentation. Segmentation performance was assessed using Dice similarity coefficient (DSC). A lesion was considered detected if the DSC between model-predicted mask and reference standard exceeded zero. Detection performance was evaluated using sensitivity at the lesion and patient level, and false-positive lesion per sequence. For verified sensitivity, a lesion on one sequence was considered a true positive if detected on any other sequence for the same patient. Subgroup analyses were performed according to lesion size. Lesions were first split using a 20 mm cutoff, then classified into four size groups: <10 mm, 10-20 mm, 20-40 mm, and ≥ 40 mm. Subgroup analyses comparing benign and malignant lesions were performed in the external validation set.
RESULTS: Mean DSC for FLLs segmentation were 0.535, 0.590 and 0.596 for the training, hold-out and external validation sets. Sensitivities in the hold-out set ranged from 0.794 to 0.882 across T1WI, fsT2WI, and DWI_High, with all verified sensitivities > 0.93. In the external validation set, sensitivities were 0.688 (0.640-0.732), 0.864 (0.833-0.891) and 0.918 (0.889-0.941), while verified sensitivities reached 0.978, 0.978 and 0.972, respectively. Per-sequence false positive lesions were 0.50, 1.94, 1.42 for the hold-out set and 0.60, 1.66, 0.90 for the external validation set. Patient-level sensitivity was 0.988 and 0.987 across the two datasets. In the external validation set, DWI_High showed a statistically significant difference in sensitivity between lesions in < 20 mm and ≥ 40 mm subgroups (p < 0.001). For fsT2WI, benign lesions achieved superior detection sensitivity, with significant differences in 10-20 mm (p < 0.001) and 20-40 mm subgroups (p < 0.05). For DWI_High, malignant lesions yielded higher sensitivity in < 10 mm subgroups (p < 0.001).
CONCLUSION: The deep learning-based AI model enables automated segmentation and detection of FLLs on NC-MRI, with acceptable performance across different lesion sizes.
引用
- Zhang, Wang, Wu, et al. Deep learning-based segmentation and detection of focal liver lesions on multi-sequence non-contrast MRI. Abdom Radiol (NY). 2026. PMID: 42726132. doi:10.1007/s00261-026-05785-7
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。