Radiomic signatures from postprocedural MRI thalamotomy lesion can predict long-term clinical outcome in patients with tremor after MRgFUS: a pilot study

TL;DR

This study shows that analyzing MRI images after a brain treatment can predict if tremors will return in patients, especially those with Parkinson's disease.

Contribution

The study introduces radiomic features from post-treatment MRI as a novel predictor of long-term tremor recurrence after MRgFUS thalamotomy.

Findings

Radiomic features from post-treatment MRI predicted tremor recurrence with 72% accuracy.

Texture-based GLCM metrics were the most predictive features for recurrence.

Predictive performance was higher in Parkinson's disease than in essential tremor patients.

Abstract

Magnetic resonance-guided focused ultrasound (MRgFUS) thalamotomy is an effective treatment for essential tremor (ET) and tremor-dominant Parkinson's disease (PD), yet a substantial proportion of patients experience tremor recurrence over time. Reliable imaging biomarkers to predict long-term outcomes are lacking. The purpose of the study was to evaluate whether radiomic features extracted from 24-h post-treatment MRI can predict clinically relevant tremor recurrence at 12 months after MRgFUS thalamotomy, using a machine learning (ML) approach.

Retrospective, single-center study included 120 patients (61 ET, 59 PD) treated with unilateral MRgFUS Vim thalamotomy between February 2018 and June 2023. Tremor severity was assessed using part A of the Fahn–Tolosa–Marin Tremor Rating Scale (FTM-TRS) at baseline and 12 months. Recurrence was defined as an FTM-TRS part A score ≥ 3 at 12 months. Lesions were manually segmented on 24-h post-treatment T2-weighted MRI. Forty radiomic features (18 first-order, 22 texture GLCM from Laplacian of Gaussian–filtered images) were extracted. A linear Support Vector Classifier with leave-one-out cross-validation was used for classification. Model explainability was assessed using SHapley Additive exPlanations (SHAP).

Clinically relevant tremor recurrence occurred in 23 patients (19%). For the full cohort, the ML model achieved a balanced accuracy of 0.720, weighted F1-score of 0.737, and comparable sensitivity and specificity across classes. Performance was higher in PD (BA = 0.808, F1 = 0.793) than in ET (BA = 0.580, F1 = 0.696). The most predictive features were texture-derived GLCM metrics, particularly from edge-enhanced images, with first-order features contributing complementary information. No significant correlations were found between radiomic features and procedural parameters.

Radiomic analysis of MRgFUS lesions on 24-h post-treatment MRI can provide early prediction of 12-month tremor recurrence, with higher predictive value in PD than in ET. Texture-based features may capture microstructural characteristics linked to treatment durability. This approach could inform post-treatment monitoring and individualized management strategies.

Figures