Improvement of classification performance of Parkinson’s disease using shape features for machine learning on dopamine transporter single photon emission computed tomography

Abstract

Objective To assess the classification performance between Parkinson's disease (PD) and normal control (NC) when semi-quantitative indicators and shape features obtained on dopamine transporter (DAT) single photon emission computed tomography (SPECT) are combined as a feature of machine learning (ML). Methods A total of 100 cases of both PD and normal control (NC) from the Parkinson's Progression Markers Initiative database were evaluated. A summed image was generated and regions of interests were set to the left and right striata. Area, equivalent diameter, major axis length, minor axis length, perimeter and circularity were calculated as shape features. Striatum binding ratios (SBR putamen and SBR caudate) were used as comparison features. The classification performance of the PD and NC groups according to receiver operating characteristic analysis of the shape features was compared in terms of SBRs. Furthermore, we compared the classification performance of ML when shape features or SBRs were used alone and in combination. Results The shape features (except minor axis length) and SBRs indicated significant differences between the NC and PD groups (p < 0.05). The top five areas under the curves (AUC) were as follows: circularity (0.972), SBR putamen (0.972), major axis length (0.945), SBR caudate (0.928) and perimeter (0.896). When classification was done using ML, AUC was as follows: circularity and SBRs (0.995), circularity alone (0.990), and SBRs (0.973). The classification

Faster Region-Based Convolutional Neural Network in the Classification of Different Parkinsonism Patterns of the Striatum on Maximum Intensity Projection Images of [18F]FP-CIT Positron Emission Tomography

“…Studies using DAT-SPECT scans and various computational techniques have shown excellent performance with high accuracy in the classification of parkinsonism patterns [ 22 , 23 , 24 , 25 , 26 ]. The accuracy of the Faster R-CNN in distinguishing the PD pattern from other patterns was comparable to previous findings.…”

“…Recent machine-learning studies using quantitative parameters, such as the striatal binding ratio of DAT-SPECT, showed high accuracy in the classification of PD [ 24 , 25 , 30 ]. The use of quantitative analysis is more objective than relying on visual analysis alone.…”

“…However, there are some general limitations to the use of quantitative data, because they may be affected by image data processing, imaging equipment, and clinical factors, such as the age and sex of patients [ 7 , 31 ]. Recent studies reported that the visual assessment of shape features provides valuable information in PD diagnosis [ 10 , 24 ]. We could not perform quantitative analysis because information essential for quantitative analysis is lost during the transformation of the images.…”

Will Artificial Intelligence Outperform the Clinical Neurologist in the Near Future? Yes

“…Indeed, recent studies have provided promising results demonstrating that ML improves classification performance of dopamine transporter single photon emission computed tomography images for the differentiation of PD from other parkinsonian disorders, potentially shortening the diagnostic delay in our case of YOPD. 11,12 This application could be implemented in underserved regions assisting a remote radiologist to interpret advanced neuroimages, leading to an earlier and more accurate diagnosis of PD, especially in the early stage when characteristic features to confirm or refute the diagnosis are quite subtle and neither sensitive enough to be observed by clinical examination (eg, subtle red flags) nor specific enough for clinical interpretation (eg, a less defined dopaminergic response). 13…”

Machine learning and deep learning for clinical data and PET/SPECT imaging in Parkinson's disease: a review

“…Recently, in 2020 Shiiba et al [86] present an approach to classify PD patients and HC subjects based on SBRs, shape and intensity features from DAT-SPECT images. These features are combined and used as input for the SVM classifier.…”