• Korean Chemical Engineering Research
• /
• v.57 no.2
• /
• pp.274-282
• /
• 2019

In recent years, big data analysis has been expanded to include automatic control through reinforcement learning as well as prediction through modeling. Research on the utilization of image data is actively carried out in various industrial fields such as chemical, manufacturing, agriculture, and bio-industry. In this paper, we applied NASNet, which is an AutoML reinforced learning algorithm, to DeepU-Net neural network that modified U-Net to improve image semantic segmentation performance. We used BRATS2015 MRI data for performance verification. Simulation results show that DeepU-Net has more performance than the U-Net neural network. In order to improve the image segmentation performance, remove dropouts that are typically applied to neural networks, when the number of kernels and filters obtained through reinforcement learning in DeepU-Net was selected as a hyperparameter of neural network. The results show that the training accuracy is 0.5% and the verification accuracy is 0.3% better than DeepU-Net. The results of this study can be applied to various fields such as MRI brain imaging diagnosis, thermal imaging camera abnormality diagnosis, Nondestructive inspection diagnosis, chemical leakage monitoring, and monitoring forest fire through CCTV.

• Proceedings of the KOSOMBE Conference
• /
• v.1997 no.05
• /
• pp.116-118
• /
• 1997

In hippocampal morphology Abnormalities, including unilateral or bilateral volume loss, are known to occur in epilepsy, Alzheimer's disease, and in certain amnestic syndromes. To detect such abnormalities in hippocampal morphology, we present a method that combines region growing and dynamic contour model to detect hippocampus from MRI brain data. The segmentation process is performed two steps. First region growing with a seed point is performed in the region of hippocampus and the initial contour of dynamic contour model is obtained. Second, the initial contour is modified on the basis of criteria that integrate energy with contour smoothness and the image gradient along the contour. As a result, this method improves fairly sensitivity to the choice of the initial seed point, which is often seen by conventional contour model. The power and practicality of this method have been tested on two brain datasets. Thus, we have developed an effective algorithm to extract hippocampus from MRI brain data.

• Journal of Korea Multimedia Society
• /
• v.18 no.2
• /
• pp.120-127
• /
• 2015

Mild Cognitive Impairment(MCI) is a prior step to Alzheimer's Disease(AD). It is different from AD which is seriously affecting daily life. Particularly, the hippocampus could be charged a crucial function for forming memory. MCI has a high risk about progress to AD. Our investigated research for a relationship between hippocampus and AD has been studied. The measurement of hippocampus volumetric is one of the most commonly used method. The three dimensional reconstructed medical images could be passible to interpret and its examination in various aspects but the cost of brain research with the medical equipment is very high. In this study, 3D visualization was performed from a series of brain Magnetic Resonance Images(MRI) and we have designed and implemented a competitive software tool based on the open libraries of Visualization ToolKit(VTK). Consequently, our visualization software tool could be useful to various medical fields and specially prognosis and diagnosis for MCI patients.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.474-476
• /
• 2021

Glioblastoma is the most common brain malignancies arising from glial cells. Early diagnosis and treatment plan establishment are important, and cancer is diagnosed mainly through T1CE imaging through injection of a contrast agent. However, the risk of injection of gadolinium-based contrast agents is increasing recently. Region segmentation that marks cancer regions in medical images plays a key role in CAD systems, and deep neural network models for synthesizing new images are also being studied. In this study, we propose a model that simultaneously learns the generation of T1CE images and segmentation of cancer regions. The performance of the proposed model is evaluated using similarity measurements including mean square error and peak signal-to-noise ratio, and shows average result values of 21 and 39 dB.

• Journal of the Institute of Convergence Signal Processing
• /
• v.12 no.4
• /
• pp.267-273
• /
• 2011

In this paper, we proposed the method to detect brain tumor region in MR images. Our method is composed of 3 parts, detection of tumor slice, detection of tumor region and tumor boundary detection. In the tumor slice detection step, a slice which contains tumor regions is distinguished using symmetric analysis in 3D brain volume. The tumor region detection step is the process to segment the tumor region in the slice distinguished as a tumor slice. And tumor region is finally detected, using spatial feature and symmetric analysis based on the cluster information. The process for detecting tumor slice and tumor region have advantages which are robust for noise and requires less computational time, using the knowledge of the brain tumor and cluster-based on symmetric analysis. And we use the level set method with fast marching algorithm to detect the tumor boundary. It is performed to find the tumor boundary for all other slices using the initial seeds derived from the previous or later slice until the tumor region is vanished. It requires less computational time because every procedure is not performed for all slices.

• Journal of Korea Multimedia Society
• /
• v.24 no.8
• /
• pp.979-987
• /
• 2021

Multiple Sclerosis (MS) can be early diagnosed by detecting lesions in brain magnetic resonance images (MRI). Unsupervised anomaly detection methods based on autoencoder have been recently proposed for automated detection of MS lesions. However, these autoencoder-based methods were developed only for 2D images (e.g. 2D cross-sectional slices) of MRI, so do not utilize the full 3D information of MRI. In this paper, therefore, we propose a novel 3D autoencoder-based framework for detection of the lesion volume of MS in MRI. We first define a 3D convolutional neural network (CNN) for full MRI volumes, and build each encoder and decoder layer of the 3D autoencoder based on 3D CNN. We also add a skip connection between the encoder and decoder layer for effective data reconstruction. In the experimental results, we compare the 3D autoencoder-based method with the 2D autoencoder models using the training datasets of 80 healthy subjects from the Human Connectome Project (HCP) and the testing datasets of 25 MS patients from the Longitudinal multiple sclerosis lesion segmentation challenge, and show that the proposed method achieves superior performance in prediction of MS lesion by up to 15%.

• Investigative Magnetic Resonance Imaging
• /
• v.19 no.3
• /
• pp.168-177
• /
• 2015

Purpose: Brain surface intensity model (BSIM)-based cortical thickness analysis does not require complicated 3D segmentation of brain gray/white matters. Instead, this technique uses the local intensity profile to compute cortical thickness. The aim of the present study was to evaluate intra-rater and inter-rater reliability of BSIM-based cortical thickness analysis using images from elderly participants. Materials and Methods: Fifteen healthy elderly participants (ages, 55-84 years) were included in this study. High-resolution 3D T1-spoiled gradient recalled-echo (SPGR) images were obtained using 3T MRI. BSIM-based processing steps included an inhomogeneity correction, intensity normalization, skull stripping, atlas registration, extraction of intensity profiles, and calculation of cortical thickness. Processing steps were automatic, with the exception of semiautomatic skull stripping. Individual cortical thicknesses were compared to a database indicating mean cortical thickness of healthy adults, in order to produce Z-score thinning maps. Intra-class correlation coefficients (ICCs) were calculated in order to evaluate inter-rater and intra-rater reliabilities. Results: ICCs for intra-rater reliability were excellent, ranging from 0.751-0.940 in brain regions except the right occipital, left anterior cingulate, and left and right cerebellum (ICCs = 0.65-0.741). Although ICCs for inter-rater reliability were fair to excellent in most regions, poor inter-rater correlations were observed for the cingulate and occipital regions. Processing time, including manual skull stripping, was $17.07{\pm}3.43min$. Z-score maps for all participants indicated that cortical thicknesses were not significantly different from those in the comparison databases of healthy adults. Conclusion: BSIM-based cortical thickness measurements provide acceptable intra-rater and inter-rater reliability. We therefore suggest BSIM-based cortical thickness analysis as an adjunct clinical tool to detect cortical atrophy.

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.101-106
• /
• 2004

In this paper, a blood vessel in an angiographic image, which plays an importance role in the diagnose diseases including in the eyes, brain and heart, is enhanced by using a directed diffusion technique. A fundamental component of the angiographic analysis is vessel segmentation that the proposed method provides a preprocessing of the image into a form suitable for human analysis, or more importantly, for machine analysis such the segmentation. Vessel enhancement is a challenging problem due to the complex nature of vascular trees and to imaging imperfections. Some parts of the inherent imperfections in angiography are the intensity inhomogeneity between the larger and smaller vessels, and another imperfection is the leakage of contrast agent into the background tissue that provides to low contrast between vessels and tissue. In the proposed scheme, the directed diffusion solves the problem by formulating a local geometric structure, which consists of direction and scale of the blood vessels. The diffusion process uses the local structure to enhance by a diffusivity tensor. The proposed algorithm can be applied to maintain sharpness and coherence-smooth the intra-regions into homogeneity better than traditional diffusion methods, which are Gaussian regulation and coherence enhancing diffusion.

• Journal of the Korean Society of Radiology
• /
• v.15 no.4
• /
• pp.507-518
• /
• 2021

Magnetic resonance imaging (MRI) is a key technology that has been seeing increasing use in studying the structural and functional innerworkings of the brain. Analyzing the variability of brain connectome through tractography analysis has been used to increase our understanding of disease pathology in humans. However, there lacks standardization of analysis methods for small animals such as mice, and lacks scientific consensus in regard to accurate preprocessing strategies and atlas-based neuroinformatics for images. In addition, it is difficult to acquire high resolution images for mice due to how significantly smaller a mouse brain is compared to that of humans. In this study, we present an Allen Mouse Brain Atlas-based image data analysis pipeline for structural connectivity analysis involving structural region segmentation using mouse brain structural images and diffusion tensor images. Each analysis method enabled the analysis of mouse brain image data using reliable software that has already been verified with human and mouse image data. In addition, the pipeline presented in this study is optimized for users to efficiently process data by organizing functions necessary for mouse tractography among complex analysis processes and various functions.

• Korean Journal of Radiology
• /
• v.23 no.7
• /
• pp.720-731
• /
• 2022

Objective: We aimed to develop and test a deep learning algorithm (DLA) for fully automated measurement of the volume and signal intensity (SI) of the liver and spleen using gadoxetic acid-enhanced hepatobiliary phase (HBP)-magnetic resonance imaging (MRI) and to evaluate the clinical utility of DLA-assisted assessment of functional liver capacity. Materials and Methods: The DLA was developed using HBP-MRI data from 1014 patients. Using an independent test dataset (110 internal and 90 external MRI data), the segmentation performance of the DLA was measured using the Dice similarity score (DSS), and the agreement between the DLA and the ground truth for the volume and SI measurements was assessed with a Bland-Altman 95% limit of agreement (LOA). In 276 separate patients (male:female, 191:85; mean age ± standard deviation, 40 ± 15 years) who underwent hepatic resection, we evaluated the correlations between various DLA-based MRI indices, including liver volume normalized by body surface area (LV_BSA), liver-to-spleen SI ratio (LSSR), MRI parameter-adjusted LSSR (aLSSR), LSSR × LV_BSA, and aLSSR × LV_BSA, and the indocyanine green retention rate at 15 minutes (ICG-R15), and determined the diagnostic performance of the DLA-based MRI indices to detect ICG-R15 ≥ 20%. Results: In the test dataset, the mean DSS was 0.977 for liver segmentation and 0.946 for spleen segmentation. The Bland-Altman 95% LOAs were 0.08% ± 3.70% for the liver volume, 0.20% ± 7.89% for the spleen volume, -0.02% ± 1.28% for the liver SI, and -0.01% ± 1.70% for the spleen SI. Among DLA-based MRI indices, aLSSR × LV_BSA showed the strongest correlation with ICG-R15 (r = -0.54, p < 0.001), with area under receiver operating characteristic curve of 0.932 (95% confidence interval, 0.895-0.959) to diagnose ICG-R15 ≥ 20%. Conclusion: Our DLA can accurately measure the volume and SI of the liver and spleen and may be useful for assessing functional liver capacity using gadoxetic acid-enhanced HBP-MRI.