Stereotactical normalization with multiple templates representative of normal and Parkinson-typical reduction of striatal uptake improves the discriminative power of automatic semi-quantitative analysis in dopamine transporter SPECT

Unrealistic Data Augmentation Improves the Robustness of Deep Learning-Based Classification of Dopamine Transporter SPECT Against Variability Between Sites and Between Cameras

We propose strongly unrealistic data augmentation to improve the robustness of convolutional neural networks (CNNs) for automatic classification of dopamine transporter SPECT against the variability between sites and between cameras. Methods: A CNN was trained on a homogeneous dataset comprising 1,100 123I-labeled 2β-carbomethoxy-3β-(4-iodophenyl)-N-(3-fluoropropyl)nortropane SPECT images using strongly unrealistic data augmentation based on gaussian blurring and additive noise. Strongly unrealistic data augmentation was compared with no augmentation and intensity-based nnU-Net augmentation on 2 independent datasets with lower (n = 645) and considerably higher (n = 640) spatial resolution. Results: The CNN trained with strongly unrealistic augmentation achieved an overall accuracy of 0.989 (95% CI, 0.978-0.996) and 0.975 (95% CI, 0.960-0.986) in the independent test datasets, which was better than that without (0.960, 95% CI, 0.942-0.974; 0.953, 95% CI, 0.934-0.968) and with nnU-Net augmentation (0.972, 95% CI, 0.956-0.983; 0.950, 95% CI, 0.930-0.966) (all McNemar P < 0.001). Conclusion: Strongly unrealistic data augmentation results in better generalization of CNN-based classification of 123I-labeled 2β-carbomethoxy-3β-(4-iodophenyl)-N-(3-fluoropropyl)nortropane SPECT images to unseen acquisition settings. We hypothesize that this can be transferred to other nuclear imaging applications.

Automated identification of uncertain cases in deep learning-based classification of dopamine transporter SPECT to improve clinical utility and acceptance

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.

Dopamine Transporter SPECT with 12-Minute Scan Duration Using Multiple-Pinhole Collimators

This study evaluated the potential to reduce the scan duration in dopamine transporter (DAT) SPECT when using a second-generation multiple-pinhole (MPH) collimator designed for brain SPECT with improved count sensitivity and improved spatial resolution compared with parallel-hole and fanbeam collimators. Methods: The retrospective study included 640 consecutive clinical DAT SPECT studies that had been acquired in list mode with a triple-head SPECT system with MPH collimators and a 30-min net scan duration after injection of 181 ± 10 MBq of [123I]FP-CIT. Raw data corresponding to scan durations of 20, 15, 12, 8, 6, and 4 min were obtained by restricting the events to a proportionally reduced time interval of the list-mode data for each projection angle. SPECT images were reconstructed iteratively with the same parameter settings irrespective of scan duration. The resulting 5,120 SPECT images were assessed for a neurodegeneration-typical reduction in striatal signal by visual assessment, conventional specific binding ratio analysis, and a deep convolutional neural network trained on 30-min scans. Results: Regarding visual interpretation, image quality was considered diagnostic for all 640 patients down to a 12-min scan duration. The proportion of discrepant visual interpretations between 30 and 12 min (1.2%) was not larger than the proportion of discrepant visual interpretations between 2 reading sessions of the same reader at a 30-min scan duration (1.5%). Agreement with the putamen specific binding ratio from the 30-min images was better than expected for 5% test-retest variability down to a 10-min scan duration. A relevant change in convolutional neural network-based automatic classification was observed at a 6-min scan duration or less. Conclusion: The triple-head SPECT system with MPH collimators allows reliable DAT SPECT after administration of about 180 MBq of [123I]FP-CIT with a 12-min scan duration.