Impact of a combination of quantitative indices representing uptake intensity, shape, and asymmetry in DAT SPECT using machine learning: comparison of different volume of interest settings

Abstract

BackgroundWe sought to assess the machine learning-based combined diagnostic accuracy of three types of quantitative indices obtained using dopamine transporter single-photon emission computed tomography (DAT SPECT)—specific binding ratio (SBR), putamen-to-caudate ratio (PCR)/fractal dimension (FD), and asymmetry index (AI)—for parkinsonian syndrome (PS). We also aimed to compare the effect of two different types of volume of interest (VOI) settings from commercially available software packages DaTQUANT (Q) and DaTView (V) on diagnostic accuracy.MethodsSeventy-one patients with PS and 40 without PS (NPS) were enrolled. Using SPECT images obtained from these patients, three quantitative indices were calculated at two different VOI settings each. SBR-Q, PCR-Q, and AI-Q were derived using the VOI settings from DaTQUANT, whereas SBR-V, FD-V, and AI-V were derived using those from DaTView. We compared the diagnostic value of these six indices for PS. We incorporated a support vector machine (SVM) classifier for assessing the combined accuracy of the three indices (SVM-Q: combination of SBR-Q, PCR-Q, and AI-Q; SVM-V: combination of SBR-V, FD-V, and AI-V). A Mann-Whitney U test and receiver-operating characteristics (ROC) analysis were used for statistical analyses.ResultsROC analyses demonstrated that the areas under the curve (AUC) for SBR-Q, PCR-Q, AI-Q, SBR-V, FD-V, and AI-V were 0.978, 0.837, 0.802, 0.906, 0.972, and 0.829, respectively. On comparing the corresponding quantitative indices between the two types of VOI settings, SBR-Q performed better than SBR-V (p = 0.006), whereas FD-V performed better than PCR-Q (p = 0.0003). No significant difference was observed between AI-Q and AI-V (p = 0.56). The AUCs for SVM-Q and SVM-V were 0.988 and 0.994, respectively; the two different VOI settings displayed no significant differences in terms of diagnostic accuracy (p = 0.48).ConclusionThe combination of the three indices obtained using the SVM classifier improved the diagnostic performance for PS; this performance did not differ based on the VOI settings and software used.

A diagnostic strategy for Parkinsonian syndromes using quantitative indices of DAT SPECT and MIBG scintigraphy: an investigation using the classification and regression tree analysis

“…Although several studies have evaluated the utility of the combined use of DAT SPECT and MIBG scintigraphy [23,[29][30][31][32][33], no study has applied the six quantitative indices in differentiating patients with NPS, PD, DLB, PSP, and MSA. Some patients included in this study overlapped with those included in our previous study [6]. In the previous study, we assessed the utility of the support vector machine to combine the quantitative indices of DAT SPECT for differential diagnosis between NPS and PS; however, we did not use MIBG scintigraphy in the assessment, and the differentiation among PD, DLB, PSP, and MSA was not determined.…”

“…Patients who were not clinically diagnosed with a degenerative disease and had essential tremor and drug-induced Parkinsonism that improved during follow-up were included in the without PS (NPS) group. Among a total of 463 patients, 97 overlapped with those from our previous study [ 6 ].

Fig.

…”

“…The template is based on the large European multi-centre database of healthy controls for the DAT SPECT (ENC-DAT trial) [ 18 ]. This software enables the automatic calculation of the following three types of quantitative indices: the SBR, PCR, and AI [ 6 ]. The SBR is defined as mean counts of the striatal VOI (background-subtracted) divided by mean counts of the occipital lobe VOI and represents the count ratio.…”

“…index (AI) are quantitative indices calculated from DAT SPECT [4][5][6][7]. The SBR represents the strength of striatal radioisotope uptake, the PCR represents a change in the shape of striatal uptake, and the AI represents the laterality of striatal uptakes.…”

A Shape Approximation for Medical Imaging Data

“…The selected images are superimposed into a single 2D image, which is called a 2D-combined image hereafter, for disease diagnosis. For example, Prashanth et al [ 1 ], Taylor et al [ 2 ], Oliveira et al [ 3 ], Nicastro et al [ 4 ], and Iwabuchi et al [ 5 ] constructed classifiers for identifying Parkinson’s disease (PD) by extracting features from 2D-combined SPECT images. However, this approach may lose some useful information or features for classification since a 2D-combined image is a projection of the original 3D structure on a specific 2D space.…”