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.

Removing outliers from the normative database improves regional atrophy detection in single-subject voxel-based morphometry.

PURPOSE: Single-subject voxel-based morphometry (VBM) compares an individual T1-weighted MRI to a sample of normal MRI in a normative database (NDB) to detect regional atrophy. Outliers in the NDB might result in reduced sensitivity of VBM. The primary aim of the current study was to propose a method for outlier removal ("NDB cleaning") and to test its impact on the performance of VBM for detection of Alzheimer's disease (AD) and frontotemporal lobar degeneration (FTLD). METHODS: T1-weighted MRI of 81 patients with biomarker-confirmed AD (n = 51) or FTLD (n = 30) and 37 healthy subjects with simultaneous FDG-PET/MRI were included as test dataset. Two different NDBs were used: a scanner-specific NDB (37 healthy controls from the test dataset) and a non-scanner-specific NDB comprising 164 normal T1-weighted MRI from 164 different MRI scanners. Three different quality metrics based on leave-one-out testing of the scans in the NDB were implemented. A scan was removed if it was an outlier with respect to one or more quality metrics. VBM maps generated with and without NDB cleaning were assessed visually for the presence of AD or FTLD. RESULTS: Specificity of visual interpretation of the VBM maps for detection of AD or FTLD was 100% in all settings. Sensitivity was increased by NDB cleaning with both NDBs. The effect was statistically significant for the multiple-scanner NDB (from 0.47 [95%-CI 0.36-0.58] to 0.61 [0.49-0.71]). CONCLUSION: NDB cleaning has the potential to improve the sensitivity of VBM for the detection of AD or FTLD without increasing the risk of false positive findings.

BrainLossNet: a fast, accurate and robust method to estimate brain volume loss from longitudinal MRI.

PURPOSE: MRI-derived brain volume loss (BVL) is widely used as neurodegeneration marker. SIENA is state-of-the-art for BVL measurement, but limited by long computation time. Here we propose "BrainLossNet", a convolutional neural network (CNN)-based method for BVL-estimation. METHODS: BrainLossNet uses CNN-based non-linear registration of baseline(BL)/follow-up(FU) 3D-T1w-MRI pairs. BVL is computed by non-linear registration of brain parenchyma masks segmented in the BL/FU scans. The BVL estimate is corrected for image distortions using the apparent volume change of the total intracranial volume. BrainLossNet was trained on 1525 BL/FU pairs from 83 scanners. Agreement between BrainLossNet and SIENA was assessed in 225 BL/FU pairs from 94 MS patients acquired with a single scanner and 268 BL/FU pairs from 52 scanners acquired for various indications. Robustness to short-term variability of 3D-T1w-MRI was compared in 354 BL/FU pairs from a single healthy men acquired in the same session without repositioning with 116 scanners (Frequently-Traveling-Human-Phantom dataset, FTHP). RESULTS: Processing time of BrainLossNet was 2-3 min. The median [interquartile range] of the SIENA-BrainLossNet BVL difference was 0.10% [- 0.18%, 0.35%] in the MS dataset, 0.08% [- 0.14%, 0.28%] in the various indications dataset. The distribution of apparent BVL in the FTHP dataset was narrower with BrainLossNet (p = 0.036; 95th percentile: 0.20% vs 0.32%). CONCLUSION: BrainLossNet on average provides the same BVL estimates as SIENA, but it is significantly more robust, probably due to its built-in distortion correction. Processing time of 2-3 min makes BrainLossNet suitable for clinical routine. This can pave the way for widespread clinical use of BVL estimation from intra-scanner BL/FU pairs.