Use of radiomic features and support vector machine to distinguish Parkinson’s disease cases from normal controls

Abstract

Background: Parkinson's disease (PD) is an irreversible neurodegenerative disease. The diagnosis of PD based on neuroimaging is usually with low-level or deep learning features, which results in difficulties in achieving precision classification or interpreting the clinical significance. Herein, we aimed to extract highorder features by using radiomics approach and achieve acceptable diagnosis accuracy in PD. Methods: In this retrospective multicohort study, we collected 18 F-fluorodeoxyglucose positron emission tomography ( 18 F-FDG PET) images and clinical scale [the Unified Parkinson's Disease Rating Scale (UPDRS) and Hoehn & Yahr scale (H&Y)] from two cohorts. One cohort from Huashan Hospital had 91 normal controls (NC) and 91 PD patients (UPDRS: 22.7±11.7, H&Y: 1.8±0.8), and the other cohort from Wuxi 904 Hospital had 26 NC and 22 PD patients (UPDRS: 20.9±11.6, H&Y: 1.7±0.9). The Huashan cohort was used as the training and test sets by 5-fold cross-validation and the Wuxi cohort was used as another separate testset. After identifying regions of interests (ROIs) based on the atlas-based method, radiomic features were extracted and selected by using autocorrelation and fisher score algorithm. A support vector machine (SVM) was trained to classify PD and NC based on selected radiomic features. In the comparative experiment, we compared our method with the traditional voxel values method. To guarantee the robustness, above processes were repeated in 500 times.Results: Twenty-six brain ROIs were identified. Six thousand one hundred and ten radiomic features were extracted in total. Among them 30 features were remained after feature selection. The accuracies of the proposed method achieved 90.97%±4.66% and 88.08%±5.27% in Huashan and Wuxi test sets, respectively.Conclusions: This study showed that radiomic features and SVM could be used to distinguish between PD and NC based on 18F-FDG PET images.

An Integrative Nomogram for Identifying Early-Stage Parkinson's Disease Using Non-motor Symptoms and White Matter-Based Radiomics Biomarkers From Whole-Brain MRI

“…In our results, the diagnostic efficiency of the radiomic biomarker based on MRI was 83.8%, much higher than the value for other nonmotor symptoms. Nonetheless, the diagnostic efficiency of radiomic biomarkers was lower in the present study than that the study by Wu et al (2019), who showed that the diagnostic efficiency of radiomic biomarkers based on 18F-FDG PET images was 90.97%. However, because PET is not widely used in routine Integrative nomogram used to detect PD.…”

Aberrant functional connectivity and activity in Parkinson’s disease and comorbidity with depression based on radiomic analysis

“…As once said by Robert Gilles et al, “Images are more than pictures, they are data” (Gillies et al., 2016) radiomic approaches based on data‐characterization algorithms have been widely applied to disease prediction and diagnosis especially in oncology and genetic fields. A random forest‐based radiomics analysis combining both nonimaging and imaging variables found the longitudinal DAT‐SPECT images significantly improved the prediction accuracy of PD, and exhibited great potentials toward development of effective prognostic biomarkers in PD (Wu et al., 2019). In recent years, a computer‐based technique utilizing CNN (Ortiz et al., 2019; Shinde et al., 2019) to create prognostic and diagnostic biomarkers has been widely adopted and attracted lots of attention.…”

A machine learning-based classification approach on Parkinson’s disease diffusion tensor imaging datasets

“…Advancements in the multivariate interpretation of neuroimaging data have already been proven useful in a plethora of neuropsychiatric [16] and neurodegenerative diseases [11,12]. Besides, the employment of machine-learning algorithms to Parkinson's disease datasets has offered unique advancements in interpreting distinct neuroimaging modalities [3,4,20,23]. MKL also yields the opportunity to concatenate different imaging modalities.…”