RESUMEN
Brain extraction is an important prerequisite for the automated diagnosis of intracranial lesions and determines, to a certain extent, the accuracy of subsequent lesion identification, localization, and segmentation. To address the problem that the current traditional image segmentation methods are fast in extraction but poor in robustness, while the Full Convolutional Neural Network (FCN) is robust and accurate but relatively slow in extraction, this paper proposes an adaptive mask-based brain extraction method, namely AMBBEM, to achieve brain extraction better. The method first uses threshold segmentation, median filtering, and closed operations for segmentation, generates a mask for the first time, then combines the ResNet50 model, region growing algorithm, and image properties analysis to further segment the mask, and finally complete brain extraction by multiplying the original image and the mask. The algorithm was tested on 22 test sets containing different lesions, and the results showed MPA = 0.9963, MIoU = 0.9924, and MBF = 0.9914, which were equivalent to the extraction effect of the Deeplabv3+ model. However, the method can complete brain extraction of approximately 6.16 head CT images in 1 second, much faster than Deeplabv3+, U-net, and SegNet models. In summary, this method can achieve accurate brain extraction from head CT images more quickly, creating good conditions for subsequent brain volume measurement and feature extraction of intracranial lesions.
Asunto(s)
Encéfalo , Cabeza , Encéfalo/diagnóstico por imagen , Encéfalo/patología , Redes Neurales de la Computación , Algoritmos , Procesamiento de Imagen Asistido por Computador/métodos , Tomografía Computarizada por Rayos X/métodosRESUMEN
Introduction: Chronic fatigue syndrome (CFS) is a clinical disease that affects multiple body systems. It is characterized by persistent or recurring fatigue, which may be linked to immune, neuroendocrine, and energy metabolism dysfunctions. Individuals with CFS may experience pain, sleep disorders, anxiety, and depression. This research analyzed the fundamental characteristics of anxiety/depression symptoms in patients with CFS and investigated the association between these symptoms and the P50 SG (sensory gate) ratio. Methods: Two hundred and forty-nine subjects fulfilled the CDC-1994 criteria for CFS and were included in the study. The subjects successively completed the Symptom CheckList-90-Revised (SCL-90-R), Hamilton Anxiety Rating Scale-14 (HAMA-14), and Hamilton Depression Rating Scale-24 (HAMD-24). Auditory-evoked potential P50 were measured using the 128-lead-electroencephalograph. Result: According to HAMA and HAMD, 17.3% (n = 43) of the patients did not exhibit anxiety/depression, with a threshold score of 7 and 7 for HAMA and HAMD. When the threshold score was 14 and 20 respectively, 43.3% (n = 108) of the patients did not exhibit anxiety/depression. The SCL-90-R results indicated that 69.5% (n = 173) of these individuals with the score arranging from 0 to 160 did not present mental problems. There was a correlation between somatization scores and P50 SG ratio in the overall sample and no anxiety or depression (NAOD) group delimited by 14 and 20, respectively, (p < 0.05). Regression analysis showed that anxiety and depression were risk factors associated with an abnormal P50 SG ratio. Discussion: A significant correlation exists between the P50 SG ratio and clinical symptoms such as fatigue, anxiety, and depression. Abnormalities in brain function among patients with CFS may play a crucial role in the pathogenesis of the condition, leading to their classification as being prone to functional neurological disorders. The P50 SG ratio cannot be used as a diagnostic marker for CFS but show some significance on the mechanism, classification, treatment, and prognosis of CFS.