Decoding the dopamine transporter imaging for the differential diagnosis of parkinsonism using deep learning

Abstract

Purpose This work attempts to decode the discriminative information in dopamine transporter (DAT) imaging using deep learning for the differential diagnosis of parkinsonism. Methods This study involved 1017 subjects who underwent DAT PET imaging ([11C]CFT) including 43 healthy subjects and 974 parkinsonian patients with idiopathic Parkinson’s disease (IPD), multiple system atrophy (MSA) or progressive supranuclear palsy (PSP). We developed a 3D deep convolutional neural network to learn distinguishable DAT features for the differential diagnosis of parkinsonism. A full-gradient saliency map approach was employed to investigate the functional basis related to the decision mechanism of the network. Furthermore, deep-learning-guided radiomics features and quantitative analysis were compared with their conventional counterparts to further interpret the performance of deep learning. Results The proposed network achieved area under the curve of 0.953 (sensitivity 87.7%, specificity 93.2%), 0.948 (sensitivity 93.7%, specificity 97.5%), and 0.900 (sensitivity 81.5%, specificity 93.7%) in the cross-validation, together with sensitivity of 90.7%, 84.1%, 78.6% and specificity of 88.4%, 97.5% 93.3% in the blind test for the differential diagnosis of IPD, MSA and PSP, respectively. The saliency map demonstrated the most contributed areas determining the diagnosis located at parkinsonism-related regions, e.g., putamen, caudate and midbrain. The deep-learning-guided binding ratios showed significant differences among IPD, MSA and PSP groups (P < 0.001), while the conventional putamen and caudate binding ratios had no significant difference between IPD and MSA (P = 0.24 and P = 0.30). Furthermore, compared to conventional radiomics features, there existed average above 78.1% more deep-learning-guided radiomics features that had significant differences among IPD, MSA and PSP. Conclusion This study suggested the developed deep neural network can decode in-depth information from DAT and showed potential to assist the differential diagnosis of parkinsonism. The functional regions supporting the diagnosis decision were generally consistent with known parkinsonian pathology but provided more specific guidance for feature selection and quantitative analysis.

High clinical diagnostic accuracy of combined salivary gland and myocardial metaiodobenzylguanidine scintigraphy in the diagnosis of Parkinson’s disease

“…In addition, artificial intelligence technology includes machine learning such as e classification and regression tree (CART), support vector machines (SVM) and random forest (RF) classifier, plays a certain role in assisting to determine the cutoff values and further diagnosing Parkinson’s syndrome by combing MIBG scintigraphy, and its effectiveness has been well demonstraed in previous studies( Nuvoli et al, 2017 , 2020 ; Iwabuchi et al, 2021 ). Besides, some studies have applied deep learning to DAT PET and FDG PET scans to analyze multiple regions as well as their correlation, which proved that it was helpful for the early diagnosis of Parkinson’s disease ( Wu et al, 2022 ; Zhao et al, 2022 ). In future studies, we can also refer to the above methods to simultaneously analyze MIBG uptake in sympathetic distributed organs including salivary glands and heart from SPECT/CT imaging, so as to improve the combined multiorgan MIBG imaging for the differential diagnosis of Parkinson’s disease.…”

“…a: the left parotid gland uptake ratio in early images; b: the left submandibular gland uptake ratio in early images; c: the right submandibular gland uptake ratio in early images; d: the left submandibular gland uptake ratio in delayed images; e: the heart uptake ratio in early images; f: the heart uptake ratio in delayed images. Frontiers in Aging 08 frontiersin.org of Parkinson's disease (Wu et al, 2022;Zhao et al, 2022). In future studies, we can also refer to the above methods to simultaneously analyze MIBG uptake in sympathetic distributed organs including salivary glands and heart from SPECT/CT imaging, so as to improve the combined multiorgan MIBG imaging for the differential diagnosis of Parkinson's disease.…”

Radiomics insight into the neurodegenerative “hot” brain: A narrative review from the nuclear medicine perspective

“…In a study with DAT PET, Zhao et al, found differences in basal ganglia relative binding ratios among patients with different parkinsonisms but failed to demonstrate differences between PD and MSA (33). Despite the authors extracting conventional radiomics features which were significantly different among atypical parkinsonisms no predictive model was built for the differential diagnosis, because the study was centered on deep learning-based applications.…”

Clinical and neuroimaging features of the progressive supranuclear palsy- corticobasal degeneration continuum

“…Striatal uptake on dopamine transporter (DAT) scans is usually abnormal in parkinsonian disorders but does not typically differentiate between parkinsonian disorders. However, machine learning approaches using deep neural networks and regional values have shown that classification of PSP-RS from PD and MSA can be improved (sensitivity ¼ 82%, specificity ¼ 94%) [27,28]. Imaging also been used to investigate the cholinergic system in PSP.…”