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.

中文翻译：

---

在基于深度学习的多巴胺转运蛋白 SPECT 分类中自动识别不确定病例，以提高临床实用性和接受度

目的

深度卷积神经网络（CNN）有望用于多巴胺转运蛋白（DAT）-SPECT 图像的自动分类。非常需要报告基于 CNN 的决策的确定性，以标记可能被错误分类的案例，因此需要用户特别仔细的检查。当前研究的目的是设计和验证基于 CNN 的系统，用于识别不确定情况。

方法

结合五个 CNN 的网络集成（NE）经过训练，可将 [ ¹²³ I]FP-CIT DAT-SPECT 图像进行高精度二元分类为“正常”或“神经退行性变典型减少”（NE 用于分类，NEfC）。通过组合两个额外的 NE 获得了不确定性检测模块 (UDM)，其中一个经过训练，用于检测“还原”DAT-SPECT，具有高灵敏度，另一个具有高特异性。如果“高敏感性”NE 和“高特异性”NE 不一致，则该病例被视为“不确定”。1740 张临床 DAT-SPECT 图像的内部“开发”数据集用于训练 ( n  = 1250) 和测试 ( n  = 490)。具有不同图像特征的两个独立数据集仅用于测试（n  = 640、645）。使用三种已建立的不确定性检测方法（S形、dropout、模型平均）进行比较。

结果

在开发数据集的测试数据中，NEfC 的准确率达到了 98.0%。4.3% 的测试用例被 UDM 标记为“不确定”：2.5% 的正确分类案例和 90% 的错误分类案例。“某些”案例中的 NEfC 准确度为 99.8%。三种比较方法在将错误分类的案例标记为“不确定”方面效果较差（40-80%）。这些发现在两个附加测试数据集中得到了证实。

结论

UDM 可以可靠地识别具有高错误分类风险的不确定的 [ ¹²³ I]FP-CIT SPECT。我们建议将 [ ¹²³ I]FP-CIT SPECT 图像的自动分类与 UDM 相结合，以提高临床实用性和接受度。所提出的 UDM 方法（“高灵敏度与高特异性”）也可能适用于其他配体的 DAT 成像以及其他二元分类任务。