文献速递神经核医学

深度卷积神经网络可实现多中心FP-CIT SPECT的自动稳健分类

Automatic classification of dopamine transporter SPECT: deep convolutional neural networks can be trained to be robust with respect to variable image characteristics.
PubMed 文献 · Eur J Nucl Med Mol Imaging · 2019-08-31

本研究基于PPMI的645例FP-CIT SPECT(207例健康对照、438例帕金森病患者),比较深度卷积神经网络(CNN)与纹状体特异性结合比值(SBR)在原始、平滑及混合图像设置下的分类效能。结果显示CNN在各PPMI设置下准确率相近,而SBR在混合设置下准确率下降;在独立临床样本中仅CNN在混合设置训练后表现可接受。

要点

  • CNN在混合、原始、平滑PPMI设置下准确率分别为0.967±0.018、0.972±0.014、0.955±0.009。
  • SBR在混合设置下准确率低于纯设置,如AAL-SBR为0.900±0.029 vs 0.957±0.017和0.952±0.015。
  • 混合设置训练后仅CNN在独立临床样本中表现可接受。

核心结论

  • 深度CNN可训练出对多中心、多相机及扫描相关图像特征变化稳健的FP-CIT SPECT分类模型,且诊断准确率较单中心/单相机设置无明显损失。

研究设计与样本

  • 研究纳入PPMI的645例FP-CIT SPECT(207例健康对照、438例帕金森病患者),图像经18-mm高斯核平滑形成原始、平滑和混合三种设置。
  • 采用含2,872,642个参数的深度CNN,每种设置以10次随机划分按60/20/20%进行训练、验证和测试。
  • SBR基于MNI空间预定义解剖ROI(AAL图谱)或最热体素(HV)分析计算,并以ROC分析、Youden准则用相同随机划分训练。
  • 混合PPMI设置训练的CNN和SBR另在独立临床样本(149例非神经退行性、149例神经退行性帕金森综合征)中测试。

主要发现

  • SBR在混合PPMI设置下表现差于纯设置,例如AAL-SBR准确率在混合设置为0.900±0.029,在原始和平滑设置分别为0.957±0.017和0.952±0.015(均p<0.01)。
  • CNN在各PPMI设置下准确率相近:混合0.967±0.018、原始0.972±0.014、平滑0.955±0.009。
  • 临床样本中获得相似结果,混合PPMI设置训练后仅CNN提供可接受的性能。

关键数值与推荐

  • CNN在混合、原始、平滑PPMI设置下的准确率分别为0.967±0.018、0.972±0.014、0.955±0.009。
  • AAL-SBR在混合、原始、平滑PPMI设置下的准确率分别为0.900±0.029、0.957±0.017、0.952±0.015,混合设置与两纯设置比较均p<0.01。

临床怎么用

  • 单一CNN有望在仅需轻微协调采集和重建协议的情况下,支持不同站点、不同采集硬件和/或重建软件的FP-CIT SPECT解读。

局限性

  • 原文未明确报告研究局限性。

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)。

原文

PURPOSE: This study investigated the potential of deep convolutional neural networks (CNN) for automatic classification of FP-CIT SPECT in multi-site or multi-camera settings with variable image characteristics. METHODS: The study included FP-CIT SPECT of 645 subjects from the Parkinson's Progression Marker Initiative (PPMI), 207 healthy controls, and 438 Parkinson's disease patients. SPECT images were smoothed with an isotropic 18-mm Gaussian kernel resulting in 3 different PPMI settings: (i) original (unsmoothed), (ii) smoothed, and (iii) mixed setting comprising all original and all smoothed images. A deep CNN with 2,872,642 parameters was trained, validated, and tested separately for each setting using 10 random splits with 60/20/20% allocation to training/validation/test sample. The putaminal specific binding ratio (SBR) was computed using a standard anatomical ROI predefined in MNI space (AAL atlas) or using the hottest voxels (HV) analysis. Both SBR measures were trained (ROC analysis, Youden criterion) using the same random splits as for the CNN. CNN and SBR trained in the mixed PPMI setting were also tested in an independent sample from clinical routine patient care (149 with non-neurodegenerative and 149 with neurodegenerative parkinsonian syndrome). RESULTS: Both SBR measures performed worse in the mixed PPMI setting compared to the pure PPMI settings (e.g., AAL-SBR accuracy = 0.900 ± 0.029 in the mixed setting versus 0.957 ± 0.017 and 0.952 ± 0.015 in original and smoothed setting, both p < 0.01). In contrast, the CNN showed similar accuracy in all PPMI settings (0.967 ± 0.018, 0.972 ± 0.014, and 0.955 ± 0.009 in mixed, original, and smoothed setting). Similar results were obtained in the clinical sample. After training in the mixed PPMI setting, only the CNN provided acceptable performance in the clinical sample. CONCLUSIONS: These findings provide proof of concept that a deep CNN can be trained to be robust with respect to variable site-, camera-, or scan-specific image characteristics without a large loss of diagnostic accuracy compared with mono-site/mono-camera settings. We hypothesize that a single CNN can be used to support the interpretation of FP-CIT SPECT at many different sites using different acquisition hardware and/or reconstruction software with only minor harmonization of acquisition and reconstruction protocols.

来源:Eur J Nucl Med Mol Imaging,查看原文。版权归原作者所有。

引用

  1. Wenzel M, Milletari F, Krüger J, et al. Automatic classification of dopamine transporter SPECT: deep convolutional neural networks can be trained to be robust with respect to variable image characteristics. Eur J Nucl Med Mol Imaging. 2019. PMID: 31473800. doi:10.1007/s00259-019-04502-5

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。