Cerebral 18F-FDG PET in macrophagic myofasciitis: An individual SVM-based approach

Abstract

IntroductionMacrophagic myofasciitis (MMF) is an emerging condition with highly specific myopathological alterations. A peculiar spatial pattern of a cerebral glucose hypometabolism involving occipito-temporal cortex and cerebellum have been reported in patients with MMF; however, the full pattern is not systematically present in routine interpretation of scans, and with varying degrees of severity depending on the cognitive profile of patients. Aim was to generate and evaluate a support vector machine (SVM) procedure to classify patients between healthy or MMF 18F-FDG brain profiles.Methods18F-FDG PET brain images of 119 patients with MMF and 64 healthy subjects were retrospectively analyzed. The whole-population was divided into two groups; a training set (100 MMF, 44 healthy subjects) and a testing set (19 MMF, 20 healthy subjects). Dimensionality reduction was performed using a t-map from statistical parametric mapping (SPM) and a SVM with a linear kernel was trained on the training set. To evaluate the performance of the SVM classifier, values of sensitivity (Se), specificity (Sp), positive predictive value (PPV), negative predictive value (NPV) and accuracy (Acc) were calculated.ResultsThe SPM12 analysis on the training set exhibited the already reported hypometabolism pattern involving occipito-temporal and fronto-parietal cortices, limbic system and cerebellum. The SVM procedure, based on the t-test mask generated from the training set, correctly classified MMF patients of the testing set with following Se, Sp, PPV, NPV and Acc: 89%, 85%, 85%, 89%, and 87%.ConclusionWe developed an original and individual approach including a SVM to classify patients between healthy or MMF metabolic brain profiles using 18F-FDG-PET. Machine learning algorithms are promising for computer-aided diagnosis but will need further validation in prospective cohorts.

Macrophagic myofasciitis and subcutaneous pseudolymphoma caused by aluminium adjuvants

“…Couette et al reported the unexpected death during sleep of a 37-years-old MMF patient, but the cause of death was not defined because an autopsy was rejected 22 . Blanc-Durand et al verified the statistical significance of the uniquely localised cerebral hypometabolism in the temporo-occipital cortex and cerebellum of patients with MMF compared to healthy individuals, by performing computer-aided support vector machine (SVM) classification on large and multicentric 18 F-FDG-PET cohorts 25 .…”

Myalgia and chronic fatigue syndrome following immunization: macrophagic myofasciitis and animal studies support linkage to aluminum adjuvant persistency and diffusion in the immune system

“…Standard brain MRI was usually normal but functional neuroimaging alterations were conspicuously found, including: (1) focal brain perfusion defects assessed by SPECT (singlephoton emission computerized tomography), well correlated to both attention/memory alterations and inter-hemispheric dysconnexion [109]; (2) a characteristic pattern of posterior cerebral glucose hypometabolism assessed by FDG-PET (fluorodeoxyglucose -positron emission tomography) scanner, involving occipital cortex, hippocampus and cerebellum, and predictive of MMF detection at muscle biopsy [110][111][112][113][114].…”

“…(6) highly consistent functional neuroimaging changes (SPECT and FDG-PET scanner) in MMF patients, not attributable to chronic pain or depression, indicating that MMF is detected in an homogeneous subset of patients with stereotyped condition [109][110][111][112][113][114]; (7) perfect similarity of the MMF syndrome with the GWI multisymptom complex [116] defined by CDC [55] which has been uniquely associated with vaccine exposure in military personnel non-deployed in the Persian gulf [53].…”