Dataset Information

Magnetic resonance imaging reconstruction algorithm under complex convolutional neural network in diagnosis and prognosis of cerebral infarction.

ABSTRACT: This study was to explore the application value of magnetic resonance imaging (MRI) image reconstruction model based on complex convolutional neural network (CCNN) in the diagnosis and prognosis of cerebral infarction. Two image reconstruction methods, frequency domain reconstruction network (FDRN) and image domain reconstruction network (IDRN), were introduced based on the CCNN algorithm. In addition, they were integrated to form two new MRI image reconstruction models, namely D-FDRN and D-IDRN. The peak signal to noise ratio (PSNR) value and structural similarity index measure (SSIM) value of the image were compared and analyzed before and after the integration. The MRI images of patients with cerebral infarction in the dataset were undertaken as the data source, the average diffusion coefficient (DCavg) and apparent diffusion coefficient (ADC) values of different parts of the MRI image were measured, respectively. The correlation of the vein abnormality grading (VABG) to the infarct size and the degree of stenosis of the responsible vessel was analyzed in this study. The results showed that the PSNR and SSIM values of the MRI reconstructed image of the D-IDRN algorithm based on the CCNN algorithm in this study were higher than those of other algorithms. There was a positive correlation between the VABG and the infarct size (r = 0.48 and P = 0.002), and there was a positive correlation between the VABG the degree of stenosis of the responsible vessel (r = 0.58 and P < 0.0001). The ADC value of the central area of the infarct on the affected side was significantly greatly lower than that of the normal side (P < 0.01), and the DCavg value of the central area of the infarct was much lower in contrast to the normal side (P < 0.05). It indicated that an image reconstruction algorithm constructed in this study could improve the quality of MRI images. The ADC value and DCavg value changed in the infarct central area could be used as the basis for the diagnosis of cerebral infarction. If the vein was abnormal, the patient suffered from severe vascular stenosis, large infarction area, and poorer prognosis.

SUBMITTER: Dong J

PROVIDER: S-EPMC8128241 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Indices for diagnosis of hyperacute cerebral infarction (HACI) and prediction of prognosis are essential for timely and appropriate management. MicroRNAs(miRNAs) regulating gene expression following stroke have potential use as prognostic markers of HACI. Here, we explored whether concentrations of circulating miRNAs could be correlated with clinical outcomes and thus form the basis of a system of stroke stratification. Plasma samples from patients with HACI (n = 7) and age-matched healthy volunteers (HVT, n = 4) were screened by microarray to find differentially expressed miRNAs, which were further verified by quantitative reverse transcription polymerase chain reaction(qRT-PCR) (HACI:HVT = 33:23). The target genes of the miRNAs with verified differential expression were investigated by GO and KEEG analysis. Using the TOAST (OCSP) criteria and the 3-month modified Rankin Score(mRS), relationships between the expression patterns of specific miRNAs, stroke stratification，and clinical prognosis were determined. The microarray analysis revealed 12 differentially expressed miRNAs. Among seven selected miRNAs verified with qRT-PCR, miR-16 expression in the HACI group was the most significantly different from the HVT group (P < 0.01). Bioinformatics analysis showed that the potential target genes of miR-16 were mainly involved in programmed cell death and the p53 signaling pathways. Receiver operating characteristic(ROC) analysis showed that the area under curve(AUC) of miR-16 was 0.775 (sensitivity 69.7% and specificity 87%) and 0.952 (sensitivity 100% and specificity 91.3%) in overall patients and patients with large artery atherosclerosis (LAAS), respectively. Elevated miR-16 expression was associated with the stroke subtype of LAAS, total anterior circulation infarction, partial anterior circulation infarction, and poor prognosis (P < 0.05). A diagnostic method based on rapid measurement of plasma miR-16 has potential to identify hyperacute cerebral infarction with LAAS with high sensitivity and specificity, which would inform and improve early treatment decisions and disease management.

Project description:Brain tumors are a diverse group of neoplasms that are challenging to detect and classify due to their varying characteristics. Deep learning techniques have proven to be effective in tumor classification. However, there is a lack of studies that compare these techniques using a common methodology. This work aims to analyze the performance of convolutional neural networks in the classification of brain tumors. We propose a network consisting of a few convolutional layers, batch normalization, and max-pooling. Then, we explore recent deep architectures, such as VGG, ResNet, EfficientNet, or ConvNeXt. The study relies on two magnetic resonance imaging datasets with over 3000 images of three types of tumors -gliomas, meningiomas, and pituitary tumors-, as well as images without tumors. We determine the optimal hyperparameters of the networks using the training and validation sets. The training and test sets are used to assess the performance of the models from different perspectives, including training from scratch, data augmentation, transfer learning, and fine-tuning. The experiments are performed using the TensorFlow and Keras libraries in Python. We compare the accuracy of the models and analyze their complexity based on the capacity of the networks, their training times, and image throughput. Several networks achieve high accuracy rates on both datasets, with the best model achieving 98.7% accuracy, which is on par with state-of-the-art methods. The average precision for each type of tumor is 94.3% for gliomas, 93.8% for meningiomas, 97.9% for pituitary tumors, and 95.3% for images without tumors. VGG is the largest model with over 171 million parameters, whereas MobileNet and EfficientNetB0 are the smallest ones with 3.2 and 5.9 million parameters, respectively. These two neural networks are also the fastest to train with 23.7 and 25.4 seconds per epoch, respectively. On the other hand, ConvNext is the slowest model with 58.2 seconds per epoch. Our custom model obtained the highest image throughput with 234.37 images per second, followed by MobileNet with 226 images per second. ConvNext obtained the smallest throughput with 97.35 images per second. ResNet, MobileNet, and EfficientNet are the most accurate networks, with MobileNet and EfficientNet demonstrating superior performance in terms of complexity. Most models achieve the best accuracy using transfer learning followed by a fine-tuning step. However, data augmentation does not contribute to increasing the accuracy of the models in general.

Project description:BackgroundRight ventricular hypertrophy (RVH) provides a key remodeling index alterable by pulmonary hypertension. Although echocardiography commonly integrates linear wall thickness and chamber dimensions to quantify left ventricular remodeling, the utility of an equivalent right ventricular (RV)-based approach is unknown.MethodsThis was a retrospective analysis of 200 patients undergoing transthoracic echocardiography and cardiac magnetic resonance (CMR) within 30 days (median = 3 days; interquartile range, 15 days), stratified by echocardiography-quantified pulmonary artery systolic pressure (<35, 35 to <55, 55 to <75, or ≥75 mm Hg). Echocardiographic assessment included RV linear dimensions in parasternal long-axis and apical four-chamber views and wall thicknesses in parasternal long-axis, four-chamber, and subcostal views. Subcostal wall thickness was integrated with chamber diameters to calculate RV mass, which was tested in relation to CMR-quantified RV mass and all-cause mortality.ResultsEchocardiography-based quantification of all linear dimensions was feasible in 95% of patients (190 of 200). RV wall thicknesses in all orientations increased in relation to pulmonary artery systolic pressure (P < .001) and was greater among patients with, versus those without, CMR-evidenced RVH (P < .001 for all). Correlations between echocardiography and CMR were greatest for RV basal diameter (r = 0.73), RV subcostal wall thickness (r = 0.71), and global RV mass (r = 0.82; P < .001 for all). Echocardiography-derived global RV mass cutoffs were established in a derivation cohort and tested in a validation cohort. Results demonstrated good sensitivity and specificity (75.5% and 74.0%, respectively) in relation to CMR-quantified RVH. During follow-up (median, 4.2 years), 18% of patients (n = 36) died. Echocardiography-evidenced RVH (hazard ratio, 1.98; 95% CI, 1.09-3.88; P = .048) conferred similar mortality risk compared with RVH on CMR (hazard ratio, 2.41; 95% CI, 1.22-4.78; P = .01).ConclusionsEchocardiography-quantified RV parameters provide a robust index of RV afterload. Global RV mass calculated using a novel echocardiographic formula based on readily available linear indices yields good diagnostic performance for CMR-evidenced RVH and confers increased mortality risk.

Dataset Information

Magnetic resonance imaging reconstruction algorithm under complex convolutional neural network in diagnosis and prognosis of cerebral infarction.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets