Predicting Motor Outcome of Subthalamic Nucleus Deep Brain Stimulation for Parkinson’s Disease Using Quantitative Susceptibility Mapping and Radiomics: A Pilot Study

Abstract

BackgroundEmerging evidence indicates that iron distribution is heterogeneous within the substantia nigra (SN) and it may reflect patient-specific trait of Parkinson’s Disease (PD). We assume it could account for variability in motor outcome of subthalamic nucleus deep brain stimulation (STN-DBS) in PD.ObjectiveTo investigate whether SN susceptibility features derived from radiomics with machine learning (RA-ML) can predict motor outcome of STN-DBS in PD.MethodsThirty-three PD patients underwent bilateral STN-DBS were recruited. The bilateral SN were segmented based on preoperative quantitative susceptibility mapping to extract susceptibility features using RA-ML. MDS-UPDRS III scores were recorded 1–3 days before and 6 months after STN-DBS surgery. Finally, we constructed three predictive models using logistic regression analyses: (1) the RA-ML model based on radiomics features, (2) the RA-ML+LCT (levodopa challenge test) response model which combined radiomics features with preoperative LCT response, (3) the LCT response model alone.ResultsFor the predictive performances of global motor outcome, the RA-ML model had 82% accuracy (AUC = 0.85), while the RA-ML+LCT response model had 74% accuracy (AUC = 0.83), and the LCT response model alone had 58% accuracy (AUC = 0.55). For the predictive performance of rigidity outcome, the accuracy of the RA-ML model was 80% (AUC = 0.85), superior to those of the RA-ML+LCT response model (76% accuracy, AUC = 0.82), and the LCT response model alone (58% accuracy, AUC = 0.42).ConclusionOur findings demonstrated that SN susceptibility features from radiomics could predict global motor and rigidity outcomes of STN-DBS in PD. This RA-ML predictive model might provide a novel approach to counsel candidates for STN-DBS.

Radiomic features of amygdala nuclei and hippocampus subfields help to predict subthalamic deep brain stimulation motor outcomes for Parkinson‘s disease patients

“…SN radiomic features have been employed in ML algorithms to discriminate between patients with PD and healthy subjects ( Li et al, 2019 ; Xiao et al, 2019 ; Xiao et al, 2021 ). The recent pilot study ( Liu et al, 2021 ) demonstrated that SN radiomic features combined with the binary logistic regression analyses could predict motor outcome of STN-DBS in PD with 82% accuracy (AUC = 0.85).…”

“…The recent growth of radiomics studies for different neurodegenerative brain disorders was also directed to PD and mostly to cortical and subcortical structures ( Wu et al, 2019 ). Recently, it was also found that substantia nigra susceptibility features from radiomics could predict global motor and rigidity outcomes of STN-DBS in PD and suggested a predictive machine learning model for STN-DBS patient selection ( Liu et al, 2021 ).…”

“…Significant advances have been achieved in the machine-learning (ML) based radiomic approach in recent years, aimed at improving the understanding of brain diseases and determining the most effective treatment options. Combining the extraction of radiomic features with ML methods can provide new non-invasive biomarkers for improved patient and disease characterization, and aid a better identification of DBS candidates ( Liu et al, 2021 ; Ren et al, 2021 ). In the present study, we hypothesize that preoperative brain magnetic resonance image (MRI) radiomic analysis of the amygdalar-hippocampal region, one of the PD pathophysiological sites, may help differentiate patients who benefit most from the STN- DBS surgery.…”

Relationship Between Iron Distribution in Deep Gray Matter Nuclei Measured by Quantitative Susceptibility Mapping and Motor Outcome After Deep Brain Stimulation in Patients With Parkinson's Disease

“…Quantitative susceptibility mapping (QSM) provides a direct measure of iron deposition by using a deconvolution method and it has been demonstrated as the most sensitive quantitative MRI technique for detecting significant increases in iron in PD subjects 16 . A previous study established a machine‐learning model on QSM radiomics in the SN and attempted to predict the effect of DBS using this model 17 . However, most studies report only mean value of the region of interest (ROI), and the relationship between the iron spatial distribution in deep gray matter nuclei and motor outcome is unclear.…”

“…16 A previous study established a machine-learning model on QSM radiomics in the SN and attempted to predict the effect of DBS using this model. 17 However, most studies report only mean value of the region of interest (ROI), and the relationship between the iron spatial distribution in deep gray matter nuclei and motor outcome is unclear.…”