Explainable AI to improve acceptance of convolutional neural networks for automatic classification of dopamine transporter SPECT in the diagnosis of clinically uncertain parkinsonian syndromes
Research output: Contribution to journal › Research article › Contributed › peer-review
Contributors
Abstract
PURPOSE: Deep convolutional neural networks (CNN) provide high accuracy for automatic classification of dopamine transporter (DAT) SPECT images. However, CNN are inherently black-box in nature lacking any kind of explanation for their decisions. This limits their acceptance for clinical use. This study tested layer-wise relevance propagation (LRP) to explain CNN-based classification of DAT-SPECT in patients with clinically uncertain parkinsonian syndromes.
METHODS: The study retrospectively included 1296 clinical DAT-SPECT with visual binary interpretation as "normal" or "reduced" by two experienced readers as standard-of-truth. A custom-made CNN was trained with 1008 randomly selected DAT-SPECT. The remaining 288 DAT-SPECT were used to assess classification performance of the CNN and to test LRP for explanation of the CNN-based classification.
RESULTS: Overall accuracy, sensitivity, and specificity of the CNN were 95.8%, 92.8%, and 98.7%, respectively. LRP provided relevance maps that were easy to interpret in each individual DAT-SPECT. In particular, the putamen in the hemisphere most affected by nigrostriatal degeneration was the most relevant brain region for CNN-based classification in all reduced DAT-SPECT. Some misclassified DAT-SPECT showed an "inconsistent" relevance map more typical for the true class label.
CONCLUSION: LRP is useful to provide explanation of CNN-based decisions in individual DAT-SPECT and, therefore, can be recommended to support CNN-based classification of DAT-SPECT in clinical routine. Total computation time of 3 s is compatible with busy clinical workflow. The utility of "inconsistent" relevance maps to identify misclassified cases requires further investigation.
Details
Original language | English |
---|---|
Pages (from-to) | 1176-1186 |
Number of pages | 11 |
Journal | European journal of nuclear medicine and molecular imaging |
Volume | 49 |
Issue number | 4 |
Publication status | Published - Mar 2022 |
Peer-reviewed | Yes |
External IDs
PubMedCentral | PMC8921148 |
---|---|
Scopus | 85117020918 |
unpaywall | 10.1007/s00259-021-05569-9 |
Mendeley | 9d10a0f6-0ea5-33bd-acc2-003e2971abce |
Keywords
Research priority areas of TU Dresden
ASJC Scopus subject areas
Keywords
- Dopamine Plasma Membrane Transport Proteins, Humans, Neural Networks, Computer, Parkinsonian Disorders/diagnostic imaging, Retrospective Studies, Tomography, Emission-Computed, Single-Photon, Explainable AI, Convolutional neural network, Dopamine transporter, Parkinson’s disease, Relevance propagation, SPECT