Back to all papers

Support vector machine classification of <sup>18</sup>F-FDG PET scans across subtypes of amyotrophic lateral sclerosis.

December 22, 2025pubmed logopapers

Authors

Tang C,Foucher J,Öijerstedt L,Ombelet F,Ingre C,Van Damme P,Van Laere K,De Vocht J,Koole M

Affiliations (5)

  • Nuclear Medicine and Molecular Imaging, Imaging and Pathology, KU Leuveny, Leuven, Belgium. [email protected].
  • Department of Clinical Neuroscience, Karolinska Institutet, Department of Neurology, Karolinska University Hospital, Stockholm, Sweden.
  • Laboratory of Neurobiology, Department of Neurosciences, Leuven Brain Institute (LBI), KU Leuven, Neurology department, University Hospitals, Leuven, Belgium.
  • Nuclear Medicine and Molecular Imaging, Imaging and Pathology, KU Leuveny, Leuven, Belgium.
  • Department of Nuclear Medicine, University Hospitals UZ Leuven, Leuven, Belgium.

Abstract

While <sup>18</sup>F-FDG PET imaging has demonstrated diagnostic value in people with Amyotrophic Lateral Sclerosis (PwALS) and group-level differences were identified between different disease subtypes (e.g., genetic and clinical variants), refining and validating a machine-learning-based subject-level diagnostic algorithm may improve the general applicability and reliability of <sup>18</sup>F-FDG PET as a diagnostic tool in ALS. In this study, we employed support vector machines (SVM) to further explore the diagnostic potential of <sup>18</sup>F-FDG PET in ALS, alongside its ability to classify between different genetic subtypes or clinical phenotypes. <sup>18</sup>F-FDG PET data of 36 healthy volunteers (HV), 25 people with ALS-mimicking diseases (Mimics), and 167 PwALS, grouped by genetic status (e.g., sporadic (sALS) or carrying a C9orf72 hexanucleotide repeat expansion (ALS<sup>C9orf72RE</sup>) and onset (bulbar or spinal) type, acquired with Biograph 'TruePoint' PET/CT scanner, were included in the study (Dataset 1). A second dataset of 183 PwALS and 31 Mimics acquired with Biograph 'HiRez' scanner was included as an independent cross-validation set (Dataset 2). PET images were spatially normalised to MNI space to fit linear SVMs with cross-validation. Only age-matched groups were considered to eliminate age-related effects. For Dataset 1, the linear SVM resulted in an average accuracy of 0.86 for the classification of ALS vs. HV, 0.53 for ALS vs. Mimics, 0.83 for ALS<sup>C9orf72RE</sup> vs. sALS, and 0.58 for bulbar vs. spinal onset. These findings were corroborated with Dataset2, with an accuracy of up to 0.76 for ALS<sup>C9orf72RE</sup> vs. sALS, and 0.59 for bulbar vs. spinal. <sup>18</sup>F-FDG brain PET imaging, combined with SVM and age-matching, can distinguish between ALS<sup>C9orf72RE</sup> and sALS with good accuracy, but lacks sufficient discriminative power to differentiate between ALS and Mimics and between different sites of onset.

Topics

Journal Article

Ready to Sharpen Your Edge?

Subscribe to join 7,500+ peers who rely on RadAI Slice. Get the essential weekly briefing that empowers you to navigate the future of radiology.

We respect your privacy. Unsubscribe at any time.