ObjectiveTo investigate the correlation of MRI features and phenotypes and genetic mutations in Pelizaeus-Merzbacher disease.Methods Sixteen boys with clinical diagnosis of PelizaeusMerzbacher disease (PMD) were included in this study.Their ages ranged from 22 months to 9 years.They were examined by pediatric neurologists,and clinical classification was made according to the symptoms and physical signs.An experienced radiologist reviewed the cranial MRI images and analyzed the brain involvement,including pallidus globus,pyramidal tract,corpus callosum,cerebellar white matter,semiovale centrum,brain atrophy and ‘ tigroid sign’.ResultsThere were 8 patients with classic form,7 patients with transitional form and one patient with connatal form.They all showed diffuse delayed myelination in the white matter,with involvement of pallidus globus in 13 cases,pyramidal tract in 7 cases,corpus callosum in 11 cases,cerebellar white matter in 7 cases,semiovale centrum in 12 cases.Cerebral atrophy was found in 5 patients and eerebellar atrophy was found in one patient.Five cases depicted ' tigroid sign'.In patients with PLP1 gene point mutation,pyramidal tract and cerebellar white matter involvement showed a high incidence.Cerebellar white matter lesions were relatively frequent in children with transitional form and connatal form.In contrast,‘ tigroid sign' was often related to classic form,which indicated a better myelination and outcome.ConclusionPMD patients show distinct imaging features in their brains,which may be correlated with the phenotype and genetic mutation.

Humans ; Male ; Middle Aged ; Polypropylenes ; Reconstructive Surgical Procedures ; Respiratory Tract Fistula ; surgery ; Surgical Mesh

Carotid Artery, Internal, Dissection ; therapy ; Humans ; Male ; Middle Aged ; Treatment Outcome

A convolutional neural network-based algorithm is proposed for calculating lower limb joint angle in X-ray films.After identifying the region of interest of a specific category in X-ray films through Yolov5 object detection model,U-Net model is used to perform heat map regression for identifying the key feature points,and then the lower limb joint angle is calculated.The results show that the proposed algorithm has higher accuracy than the previous algorithms and can obtain accurate and reliable results,providing references for clinical research and practice.