Impact of injected dose and acquisition time on a normal database by use of 3D-SSP in SPECT images: quantitative simulation studies

[Accuracy of Classification of Cerebral Blood Flow Reduction Patterns Using Statistical Analysis Images Generated with Simulated SPECT Datasets via Deep Learning]

PURPOSE

The aim of this study was to evaluate the classification accuracy of specific blood flow reduction patterns in clinical images by deep learning using simulation data.

METHODS

We obtained Z-score maps for 100 cases each of simulated Alzheimer's disease (AD), simulated dementia with Lewy bodies (DLB), and simulated normal cognition (NC) by performing statistical analysis of the simulation data that provided defects and healthy patient data. The clinical images were determined by reference to radiological reports, and Z-score maps of AD (n=33), DLB (n=20), and NC (n=28) were used. A network was constructed with reference to AlexNet, 4-fold cross-validation was performed using only simulation data, and classification accuracy was evaluated. We also trained the model using the simulation data and classified the clinical images.

RESULTS

The accuracy rate of classification between simulations was 96.2% and that of the clinical images was 84.2%.

CONCLUSION

Through deep learning using simulation data, clinical images may be classified with an accuracy of 84.2%.

Echolalia in patients with primary progressive aphasia

OBJECTIVE

This study aimed to examine echolalia and its related symptoms and brain lesions in primary progressive aphasia (PPA).

METHODS

Forty-five patients with PPA were included: 19 nonfluent/agrammatic variant PPA (nfvPPA), 5 semantic variant PPA, 7 logopenic variant PPA, and 14 unclassified PPA patients. We detected echolalia in unstructured conversations. An evaluation of language function and the presence of parkinsonism, grasp reflex, imitation behaviour, and disinhibition were assessed. We also measured regional cerebral blood flow (rCBF) using single-photon emission computed tomography.

RESULTS

Echolalia was observed in 12 nfvPPA and 2 unclassified PPA patients. All patients showed mitigated echolalia. We compared nfvPPA patients with echolalia (echolalia group) to those without echolalia (non-echolalia group). The median age of the echolalia group was significantly lower than that of the non-echolalia group, and the echolalia group showed a significantly worse auditory comprehension performance than the non-echolalia group. In contrast, the performance of repetition tasks was not different between the two groups. The prevalence of imitation behaviour in the echolalia group was significantly higher than that in the non-echolalia group. The rCBFs in the bilateral pre-supplementary motor area and bilateral middle cingulate cortex in the echolalia group were significantly lower than those in the non-echolalia group.

CONCLUSIONS

These findings suggest that echolalia is characteristic of nfvPPA patients with impaired comprehension. Reduced inhibition of the medial frontal cortex with release activity of the anterior perisylvian area account for the emergence of echolalia.