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 99mTc-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-[1R-(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.