Diagnostic accuracy and reliability of susceptibility map-weighted imaging in patients with clinically uncertain parkinsonian syndromes
Year: 2026
Type: article
Study design: Observational Study
Abstract: OBJECTIVES: Parkinson's disease (PD) is characterized by degeneration of dopaminergic neurons in the substantia nigra, accompanied by increased iron accumulation, particularly in the nigrosome-1 subregion. Differentiating neurodegenerative disorders like PD from non-neurodegenerative causes of parkinsonism can be challenging. In clinically uncertain parkinsonian syndrome (CUPS), dopamine transporter (DAT)-single-photon emission computed tomography (SPECT) can aid diagnosis. However, susceptibility map-weighted imaging (SMWI) provides a promising magnetic resonance imaging (MRI) alternative. We evaluated the diagnostic accuracy and reliability of visual SMWI assessment by radiologists in CUPS and the added value of artificial intelligence (AI)-driven diagnostic software. MATERIALS AND METHODS: Patients with CUPS who underwent DAT-SPECT between January 2019 and July 2023 were included. Four radiologists, blinded to clinical symptoms and diagnosis, visually rated nigrosome-1 on axial SMWI reconstructions as normal, unclear, or abnormal. After the initial assessment, the radiologists re-evaluated the scans with AI-driven software assistance, designed to classify and quantify nigrosome-1 integrity. The reference standard was the final clinical diagnosis incorporating DAT-SPECT results. RESULTS: One hundred eighty patients were included (mean age 67.9, range 31-86, 120 males), 84 with neurodegenerative and 96 with non-neurodegenerative parkinsonism. Mean diagnostic accuracy was 80% (range 73-83%), with substantial inter-rater reliability (Fleiss κ 0.65). With software assistance, diagnostic accuracy improved to 87% (range 85-91%), and inter-rater agreement increased to almost perfect (Fleiss κ 0.86). CONCLUSION: SMWI, particularly with AI-driven software assistance, is a promising and accessible MRI-based technique that may support the diagnostic workup in clinically uncertain parkinsonism, aiding the distinction between neurodegenerative and non-neurodegenerative causes. KEY POINTS: Question Can susceptibility map-weighted imaging (SMWI) reliably differentiate neurodegenerative from non-neurodegenerative parkinsonism in clinically uncertain cases, and does artificial intelligence (AI)-driven software assistance improve radiologist performance? Findings Visual assessment had an accuracy of 80%, with substantial inter-rater reliability. AI-driven software assistance increased accuracy to 87% and improved inter-rater reliability. Relevance statement SMWI can differentiate neurodegenerative from non-neurodegenerative parkinsonism in clinically uncertain cases and may support the diagnostic process by offering an accessible MRI-based technique, facilitating an efficient diagnostic workup, and enabling early diagnosis in clinically uncertain parkinsonism.
Source: European Radiology Experimental
Language: English
Subfield: Clinical Neurology
Field: Medicine
Domain: Health Sciences
Open Access status: gold
Estimated APC paid: $2,990
OpenAlex ID: W7229748507
