A brain tumor is one of a deadly disease that needs high accuracy in its medical surgery. Brain tumor detection can be done through magnetic resonance imaging (MRI). Image segmentation for the MRI brain tumor aims to separate the tumor area (as the region of interest or ROI) with a healthy brain and provide a clear boundary of the tumor. This study classifies the ROI and non-ROI using fully convolutional network with new architecture, namely UNet-VGG16. This model or architecture is a hybrid of U-Net and VGG16 with transfer Learning to simplify the U-Net architecture. This method has a high accuracy of about 96.1% in the learning dataset. The validation is done by calculating the correct classification ratio (CCR) to comparing the segmentation result with the ground truth. The CCR value shows that this UNet-VGG16 could recognize the brain tumor area with a mean of CCR value is about 95.69%.

No abstract

No abstract

Introduction: Toxoplasma gondii is an intracellular pathogenic parasite with the majority of co-infections occurring in HIV/AIDS patients. This study assesses the head computed tomography (CT) images of cerebral toxoplasmosis in patients with HIV/AIDS.Methods: This study was a cross-sectional design using head CT images of 35 HIV/AIDS patients with suspected cerebral toxoplasmosis. Variables include lesion type, location, size, CD4 count, and therapeutic result with anti-cerebral toxoplasmosis. All data analysed descriptively.Results: From total 110, 35 patients met the inclusion criteria. 24 patients (68.6%) were male and 11 (31.4%) female, average age, was 36.1. 8 patients (22.3%) had lesions in cortical, 31 patients (88.6%) had < 1 cm lesion. Single lesions mainly calcified and found in the right centrum semiovale while multiple lesions were subcortical. A hypodense lesion with rim or nodular contrast enhancement is found in 75% of patients with CD4 > 200 in contrast to slight rim contrast enhancement and perifocal edema in patients with CD4 < 200. 20 patients (57.4%) had improved condition after anti-toxoplasmosis therapy.Conclusion: Cerebral toxoplasmosis lesions in HIV/AIDS patients have various types of imaging findings, mostly multiple, with most frequent location being cortical and diameter < 1 cm. Total recovery is achieved in the majority of patients with therapy.

MRI brain tumor segmentation is an important topic in medical image processing. Manual segmentation is risky and time-consuming when the MRI is in low quality. The automatic segmentation can be a solution to manage this problem. This paper proposed an improved modeling approach for unsupervised learning trough Spatially Variant Finite Mixture Model (SVFMM). The main contribution is the automation of the SVFMM algorithm to find the optimum number of clusters. This is achieved by employing the birth-death random process in Bayesian Reversible Jump MCMC. Validation of the proposed model is done by calculating the Correct Classification Ration (CCR) in comparison to the original SVFMM and Gaussian Mixture Model (GMM). The proposed model provides similar performance in image segmentation compared to the original SVFMM but is better than GMM. However, SVFMM-RJMCMC is faster and more efficient in finding the optimum number of clusters.