文献速递神经核医学

基于深度学习的多巴胺转运体SPECT分类中不确定病例的自动识别以提高临床效用与接受度

Automated identification of uncertain cases in deep learning-based classification of dopamine transporter SPECT to improve clinical utility and acceptance.
PubMed 文献 · Eur J Nucl Med Mol Imaging · 2023-12-22

本研究设计并验证了一种基于卷积神经网络集成的系统,用于自动分类[123I]FP-CIT DAT-SPECT图像并识别不确定病例。在1740例内部开发数据集(训练1250例、测试490例)及两个独立测试集(n=640、645)中,不确定检测模块将4.3%的测试病例标记为不确定,其中正确分类病例中占2.5%、误分类病例中占90%,分类网络在确定病例中的准确率达99.8%。作者推荐将自动分类与不确定检测模块结合使用。

要点

  • 不确定检测模块将90%的误分类病例标记为不确定,仅2.5%的正确分类病例被标记。
  • 分类网络在测试数据中准确率98.0%,在确定病例中准确率99.8%。
  • 作者推荐将[123I]FP-CIT SPECT自动分类与不确定检测模块结合以提高临床效用和接受度。

核心结论

  • 不确定检测模块能可靠识别误分类高风险的[123I]FP-CIT SPECT病例。
  • 作者推荐将[123I]FP-CIT SPECT图像的自动分类与不确定检测模块结合,以提高临床效用和接受度。
  • 所提出的不确定检测方法(高灵敏度对比高特异性)可能也适用于其他配体的DAT显像及其他二分类任务。

研究设计与样本

  • 研究训练了一个由五个卷积神经网络组成的网络集成,用于[123I]FP-CIT DAT-SPECT图像的二分类(正常或神经退行性典型减低),并构建不确定检测模块。
  • 不确定检测模块由两个额外网络集成组合而成,一个以高灵敏度检测DAT-SPECT减低,另一个以高特异性检测,两者判断不一致的病例被视为不确定。
  • 内部开发数据集共1740例临床DAT-SPECT图像,其中1250例用于训练、490例用于测试;另有两个图像特征不同的独立数据集仅用于测试(n=640、645)。
  • 采用三种已有不确定检测方法(sigmoid、dropout、模型平均)作为比较。

主要发现

  • 在开发数据集的测试数据中,分类网络集成准确率达98.0%。
  • 不确定检测模块将全部测试病例的4.3%标记为不确定,其中正确分类病例中占2.5%、误分类病例中占90%。
  • 分类网络集成在确定病例中的准确率为99.8%。
  • 三种比较方法将误分类病例标记为不确定的效果较差(40-80%)。
  • 上述发现在两个额外测试数据集中得到验证。

临床怎么用

  • 作者推荐将[123I]FP-CIT SPECT图像的自动分类与不确定检测模块结合,以提高临床效用和接受度。

局限性

  • 原文未报告局限性。

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: Deep convolutional neural networks (CNN) are promising for automatic classification of dopamine transporter (DAT)-SPECT images. Reporting the certainty of CNN-based decisions is highly desired to flag cases that might be misclassified and, therefore, require particularly careful inspection by the user. The aim of the current study was to design and validate a CNN-based system for the identification of uncertain cases. METHODS: A network ensemble (NE) combining five CNNs was trained for binary classification of [123I]FP-CIT DAT-SPECT images as "normal" or "neurodegeneration-typical reduction" with high accuracy (NE for classification, NEfC). An uncertainty detection module (UDM) was obtained by combining two additional NE, one trained for detection of "reduced" DAT-SPECT with high sensitivity, the other with high specificity. A case was considered "uncertain" if the "high sensitivity" NE and the "high specificity" NE disagreed. An internal "development" dataset of 1740 clinical DAT-SPECT images was used for training (n = 1250) and testing (n = 490). Two independent datasets with different image characteristics were used for testing only (n = 640, 645). Three established approaches for uncertainty detection were used for comparison (sigmoid, dropout, model averaging). RESULTS: In the test data from the development dataset, the NEfC achieved 98.0% accuracy. 4.3% of all test cases were flagged as "uncertain" by the UDM: 2.5% of the correctly classified cases and 90% of the misclassified cases. NEfC accuracy among "certain" cases was 99.8%. The three comparison methods were less effective in labelling misclassified cases as "uncertain" (40-80%). These findings were confirmed in both additional test datasets. CONCLUSION: The UDM allows reliable identification of uncertain [123I]FP-CIT SPECT with high risk of misclassification. We recommend that automatic classification of [123I]FP-CIT SPECT images is combined with an UDM to improve clinical utility and acceptance. The proposed UDM method ("high sensitivity versus high specificity") might be useful also for DAT imaging with other ligands and for other binary classification tasks.

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

引用

  1. Budenkotte T, Apostolova I, Opfer R, et al. Automated identification of uncertain cases in deep learning-based classification of dopamine transporter SPECT to improve clinical utility and acceptance. Eur J Nucl Med Mol Imaging. 2023. PMID: 38133688. doi:10.1007/s00259-023-06566-w

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。