Interpretation of basal nuclei in brain dopamine transporter scans using a deep convolutional neural network
Bibliographic record
Abstract
OBJECTIVE: Functional imaging using the dopamine transporter (DAT) as a biomarker has proven effective in assessing dopaminergic neuron degeneration in the striatum. In assessing the neuron degeneration, visual and semiquantitative methods are used to interpret DAT single-photon emission tomography (SPECT) scans based on striatal to background activity, striatal shape, and symmetry. Visual analysis, however, is subjective and reviewer dependent, whereas semiquantitative methods are operator dependent. Our goal in the current study was to derive results via deep learning to facilitate the clinical diagnosis of Parkinson's disease (PD). METHODS: This retrospective study collected data from 416 patients with clinically uncertain Parkinsonian syndrome who underwent DAT SPECT via 99m Tc-TRODAT-1 ([2-[[2-[[[3-(4-chlorophenyl)-8-methyl-8-azabicyclo[3,2,1]oct-2-yl]methyl](2-mercaptoethyl)amino]ethyl]amino]ethanethiolato (3-)- N2,N2',S2,S2' ]oxo-[1 R -( exo - exo )]). Transfer learning was used to estimate the degree of dopaminergic neuron degeneration in the caudate and putamen for use in classifying images according to stage. Three pretrained models - Xception, InceptionV3, and ResNet101 - were retrained and tested after undergoing transfer learning for the classification of striatum dopaminergic neuron degeneration. RESULTS: Overall, the performance of Xception exceeded that of InceptionV3 and ResNet101. The accuracy, macro F1 score, and kappa value of the proposed caudate classification model were 81.93%, 0.70, and 0.64, respectively. The accuracy, macro F1 score, and kappa value of the proposed putamen classification model were 88.75%, 0.64, and 0.61, respectively. CONCLUSION: The proposed deep convolutional neural network provided a good model by which to interpret DAT SPECT of basal nuclei. We believe that the model could be used as an auxiliary tool to facilitate image interpretation and enhance accuracy in the diagnosis of PD.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".