RESUMEN
BACKGROUND@#Prenatal evaluation of fetal lung maturity (FLM) is a challenge, and an effective non-invasive method for prenatal assessment of FLM is needed. The study aimed to establish a normal fetal lung gestational age (GA) grading model based on deep learning (DL) algorithms, validate the effectiveness of the model, and explore the potential value of DL algorithms in assessing FLM.@*METHODS@#A total of 7013 ultrasound images obtained from 1023 normal pregnancies between 20 and 41 + 6 weeks were analyzed in this study. There were no pregnancy-related complications that affected fetal lung development, and all infants were born without neonatal respiratory diseases. The images were divided into three classes based on the gestational week: class I: 20 to 29 + 6 weeks, class II: 30 to 36 + 6 weeks, and class III: 37 to 41 + 6 weeks. There were 3323, 2142, and 1548 images in each class, respectively. First, we performed a pre-processing algorithm to remove irrelevant information from each image. Then, a convolutional neural network was designed to identify different categories of fetal lung ultrasound images. Finally, we used ten-fold cross-validation to validate the performance of our model. This new machine learning algorithm automatically extracted and classified lung ultrasound image information related to GA. This was used to establish a grading model. The performance of the grading model was assessed using accuracy, sensitivity, specificity, and receiver operating characteristic curves.@*RESULTS@#A normal fetal lung GA grading model was established and validated. The sensitivity of each class in the independent test set was 91.7%, 69.8%, and 86.4%, respectively. The specificity of each class in the independent test set was 76.8%, 90.0%, and 83.1%, respectively. The total accuracy was 83.8%. The area under the curve (AUC) of each class was 0.982, 0.907, and 0.960, respectively. The micro-average AUC was 0.957, and the macro-average AUC was 0.949.@*CONCLUSIONS@#The normal fetal lung GA grading model could accurately identify ultrasound images of the fetal lung at different GAs, which can be used to identify cases of abnormal lung development due to gestational diseases and evaluate lung maturity after antenatal corticosteroid therapy. The results indicate that DL algorithms can be used as a non-invasive method to predict FLM.
Asunto(s)
Femenino , Humanos , Lactante , Recién Nacido , Embarazo , Algoritmos , Aprendizaje Profundo , Edad Gestacional , Pulmón/diagnóstico por imagen , Redes Neurales de la ComputaciónRESUMEN
<p><b>OBJECTIVE</b>To investigate the role of activated brain regions in Parkinson's disease (PD) during tactile stimulation.</p><p><b>METHODS</b>Twenty-one patients with early PD[mean age (60.43 +/-9.65)y] and twenty-two age-matched healthy controls [mean age (59.23 +/-11.12)y] were enrolled in the study. All the patients were tested by the United Parkinson Disease Rating Scale (UPDRS) as the evaluation of the disease severity. A block design was used when the finger tactile stimulation was given to the subjects. The hypoactive and hyperactive regions of PD patients were confirmed first, which were identified as regions of interest (ROI). ROI analysis was performed to quantify BOLD signal changes when subjects were under tactile stimulation. The correlations of signal changes with disease severity, and correlations of hyperactive with hypoactive regions were analyzed.</p><p><b>RESULTS</b>Right primary sensory and motor cortex, right supplementary motor area (SMA), bilateral caudates, bilateral precuneus, bilateral occipital visual cortex and left middle temporal gyrus were hypoactivated in PD, while right prefrontal cortex (PFC) and right caudate were hyperactivated. The hypoactivation of right SMA was negatively correlated with disease severity. All the hypoactive and hyperactive regions were positively correlated with activation of caudates. There was a positive correlation between hyperactive PFC and hypoactive regions.</p><p><b>CONCLUSIONS</b>The signal change of SMA is directly related to disease severity in early PD, and caudates may play a significant role in PD tactile processing. The hyperactivation of PFC may be not a compensation but a pathophysiological change related to PD neural dysfunction.</p>
Asunto(s)
Anciano , Femenino , Humanos , Masculino , Persona de Mediana Edad , Encéfalo , Imagen por Resonancia Magnética , Mecanorreceptores , Fisiología , Enfermedad de Parkinson , Índice de Severidad de la Enfermedad , Factores de Tiempo , Tacto , Fisiología , Percepción del Tacto , FisiologíaRESUMEN
<p><b>OBJECTIVE</b>To examine the age, sex, and hemispheric differences in volume of the striatum by MRI in healthy adults.</p><p><b>METHODS</b>The volumes of the bilateral caudate nucleus and putamen were measured on MR images in 100 healthy right-handed adults (18-70 y).</p><p><b>RESULTS</b>The volume of bilateral caudate nucleus and putamen in healthy adults was (8.42 +/-0.88) cm(3) and (8.90 +/-0.89) cm(3), which were decreased with aging (for caudate nucleus r=-0.727, P<0.001; for putamen r=-0.709, P<0.001). The average annual shrinkage rate was 0.52 % in the caudate nucleus and 0.50 % in the putamen. There were no gender differences in the volume of the striatum, however, the age-related shrinkage of the striatum was more evident in men than that in women. The volume of the left caudate nucleus (t=4.43, P<0.001) and the putamen (t=4.88, P<0.001) was greater than that of its right counterpart.</p><p><b>CONCLUSION</b>Bilateral age-related shrinkage of the striatum is found in healthy adults, which is more evident in men than that in women. In both sexes, significant leftward asymmetry in volume of the caudate nucleus and the putamen is found.</p>