深度学习分类肝脂肪变性的原始超声数据表示比较研究
本研究在31例确诊或疑似非酒精性脂肪性肝病患者中,以MRI脂肪分数为参考标准,比较基于原始超声射频数据不同表示形式的深度学习分类评分。结果显示,射频数据及功率谱表示的患者水平AUROC分别为0.994和0.998,优于临床B模式图像的0.938及传统定量超声指标(AUROC=0.986),且深度学习模型准确率(0.989)高于放射科医生标注(0.914)。
要点
- 原始射频数据深度学习分类肝脂肪变性优于临床B模式图像。
- 功率谱表示收敛更快且AUROC高于传统定量超声指标。
- 相位信息虽常被丢弃,仍提供较高分类性能(AUROC=0.988)。
核心结论
- 利用原始超声数据结合人工智能技术可能为定量组织诊断提供优于常规超声图像的机会。
研究设计与样本
- 研究纳入31例确诊或疑似非酒精性脂肪性肝病患者,以MRI脂肪分数截断值分层脂肪变性。
- 采集超声射频帧(原始数据)和临床B模式图像,并建模中间图像形成阶段、功率谱表示和相位表示。
- 使用配准图像块独立训练1-D、2-D和3-D卷积神经网络,并通过交叉验证比较分类评分。
- 2-D/3-D分类可用67,800个图像块,1-D分类可用1,830,600个图像块。
- 结果与放射科医生B模式标注及定量超声指标进行比较。
诊断标准与关键数值
- 患者水平AUROC:射频数据0.994,临床B模式图像0.938。
- 功率谱表示与射频数据联合训练的深度学习模型AUROC=0.998,传统定量超声指标及其多参数组合AUROC=0.986。
- 相位信息提供的患者水平AUROC=0.988。
- 图像块分类AUROC沿图像形成连续阶段显著降低(p < 0.001)。
- 深度学习模型分类准确率0.989,放射科医生标注准确率0.914(参考标准为MRI质子密度脂肪分数)。
临床应用与阅片要点
- 日常阅片可关注原始射频数据及功率谱表示在肝脂肪变性定量评估中的潜在优势。
- B模式图像深度学习分类性能低于原始数据,提示报告时需注意图像形成过程造成的信息损失。
局限性
- 样本量较小(N=31),可能影响结论的泛化性。
- 单中心研究设计,未提及外部验证。
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
Adiposity accumulation in the liver is an early-stage indicator of non-alcoholic fatty liver disease. Analysis of ultrasound (US) backscatter echoes from liver parenchyma with deep learning (DL) may offer an affordable alternative for hepatic steatosis staging. The aim of this work was to compare DL classification scores for liver steatosis using different data representations constructed from raw US data. Steatosis in N = 31 patients with confirmed or suspected non-alcoholic fatty liver disease was stratified based on fat-fraction cutoff values using magnetic resonance imaging as a reference standard. US radiofrequency (RF) frames (raw data) and clinical B-mode images were acquired. Intermediate image formation stages were modeled from RF data. Power spectrum representations and phase representations were also calculated. Co-registered patches were used to independently train 1-, 2- and 3-D convolutional neural networks (CNNs), and classifications scores were compared with cross-validation. There were 67,800 patches available for 2-D/3-D classification and 1,830,600 patches for 1-D classification. The results were also compared with radiologist B-mode annotations and quantitative ultrasound (QUS) metrics. Patch classification scores (area under the receiver operating characteristic curve [AUROC]) revealed significant reductions along successive stages of the image formation process (p < 0.001). Patient AUROCs were 0.994 for RF data and 0.938 for clinical B-mode images. For all image formation stages, 2-D CNNs revealed higher patch and patient AUROCs than 1-D CNNs. CNNs trained with power spectrum representations converged faster than those trained with RF data. Phase information, which is usually discarded in the image formation process, provided a patient AUROC of 0.988. DL models trained with RF and power spectrum data (AUROC = 0.998) provided higher scores than conventional QUS metrics and multiparametric combinations thereof (AUROC = 0.986). Radiologist annotations indicated lower hepatic steatosis classification accuracies (Acc = 0.914) with respect to magnetic resonance imaging proton density fat fraction that DL models (Acc = 0.989). Access to raw ultrasound data combined with artificial intelligence techniques may offer superior opportunities for quantitative tissue diagnostics than conventional sonographic images.
引用
- Sanabria, Pirmoazen, Dahl, et al. Comparative Study of Raw Ultrasound Data Representations in Deep Learning to Classify Hepatic Steatosis. Ultrasound Med Biol. 2022. PMID: 35914993. doi:10.1016/j.ultrasmedbio.2022.05.031
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。