• Proceedings of the IEEK Conference
• /
• 2002.07b
• /
• pp.802-805
• /
• 2002

In the three-dimensional domain image expressed with two-dimensional slice images, such as fMRI images and multi-slice CT images, we propose the three-dimensional domain automatic segmentation for the purpose of extracting region. In this paper, we segmented each domain from the fMRI images of the head of people and monkey. We used the neural network "Pulse-Coupled Neural Network" which is one of the models of visual cortex of the brain based on the knowledge from neurophysiology as the technique. By using this technique, we can segment the region without any learning. Then, we reported the result of division of each domain and extraction to the fMRI slice images of human's head using "three-dimensional Pulse-Coupled Neural Network" which is arranged and created the neuron in the shape of a three-dimensional lattice.

• Journal of Korea Multimedia Society
• /
• v.23 no.3
• /
• pp.468-475
• /
• 2020

In this paper, we proposed a three-dimensional visualization system for medical images in augmented reality based on deep learning. In the proposed system, the artificial neural network model performed fully automatic segmentation of the region of lung and pulmonary nodule from chest CT images. After applying the three-dimensional volume rendering method to the segmented images, it was visualized in augmented reality devices. As a result of the experiment, when nodules were present in the region of lung, it could be easily distinguished with the naked eye. Also, the location and shape of the lesions were intuitively confirmed. The evaluation was accomplished by comparing automated segmentation results of the test dataset to the manual segmented image. Through the evaluation of the segmentation model, we obtained the region of lung DSC (Dice Similarity Coefficient) of 98.77%, precision of 98.45%, recall of 99.10%. And the region of pulmonary nodule DSC of 91.88%, precision of 93.05%, recall of 90.94%. If this proposed system will be applied in medical fields such as medical practice and medical education, it is expected that it can contribute to custom organ modeling, lesion analysis, and surgical education and training of patients.

• Proceedings of the IEEK Conference
• /
• 2006.06a
• /
• pp.335-336
• /
• 2006

In this paper, we propose an active shape image segmentation method for three-dimensional(3-D) medical images using a generation method of the 3-D shape model. The proposed method generates the shape model using a distance transform and a tetrahedron method for landmarking. After generating the 3-D model, we extend the training and segmentation processes of 2-D active shape model(ASM) and improve the searching process. The proposed method provides comparative results to 2-D ASM, region-based or contour-based methods. Experimental results demonstrate that this algorithm is effective for a semi-automatic segmentation method of 3-D medical images.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.33B no.4
• /
• pp.111-123
• /
• 1996

In this paper, a new edge-based segmentation algorithm for range image using pseudo reflectance images (PRIs) is proposed. A model of pseudo reflectance which is useful in analyzing three dimensional scene and objects is introduced and then three PRIs are generated by the model. For generating three PRIs, bels and jain's differential window operator is selected and three different light source directions are determined. Three edge images are extracted from each PRI and a fused (logical ORing) edge image is constructed for the benefit of enhanced edge formation. The final segmentation results of the proposed algoritm are obtained after the processing of thinning, labeling and correcting erroeneous regions with the fused edge image. The good performance of edge detection and segmentation is confirmed via computer simulation with synthetic and real range images.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.16 no.3
• /
• pp.591-597
• /
• 2012

Medical device performance has been advanced while images are expected to be acquired with further higher quality and pertinent applicability as images have been increasing in importance in analyzing major organs. Recent high frequency of image processing by MATLAB in image analysis area accounts for the intent of this study to segment pulmonary vessels by means of MATLAB. This study is to consist of 3 phases including pulmonary region segmentation, pulmonary vessel segmentation and three dimensional connectivity assessment, in which vessel was segmented, using threshold level, from the pulmonary region segmented, vessel thickness was measured as two dimensional refining process and three dimensional connectivity was assessed as three dimensional refining process. It is expected that MATLAB-based image processing should contribute to diversity and reliability of medical image processing and that the study results may lay a foundation for chest CT images-related researches.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.31B no.10
• /
• pp.123-129
• /
• 1994

The segmentation of range image is essential to recognize the three dimensional object. Generally, surface curvature is well-known feature for segmentation and classification of the fange image, but it is sensitive to noies. In this paper, we propose the structure of hierarchical neural network using surface curvature for segmentation of range images. The hierarchical structure of neural networks is robust to noise and the result of segmentaion is better than conventional optimization method of single level.

• Journal of the Korean Data and Information Science Society
• /
• v.15 no.4
• /
• pp.817-823
• /
• 2004

This paper describes a three dimensional motion recognition algorithm and a system which adopts the algorithm for non-contact human-computer interaction. From sequence of stereos images, five feature regions are extracted with simple color segmentation algorithm and then those are used for three dimensional locus calculation precess. However, the result is not so stable, noisy, that we introduce principal component analysis method to get more robust motion recognition results. This method can overcome the weakness of conventional algorithms since it directly uses three dimensional information motion recognition.

• Progress in Medical Physics
• /
• v.32 no.4
• /
• pp.172-178
• /
• 2021

Purpose: This study aimed to develop a deep learning architecture combining two task models to generate synthetic computed tomography (sCT) images from low-tesla magnetic resonance (MR) images to improve metallic marker visibility. Methods: Twenty-three patients with cervical cancer treated with intracavitary radiotherapy (ICR) were retrospectively enrolled, and images were acquired using both a computed tomography (CT) scanner and a low-tesla MR machine. The CT images were aligned to the corresponding MR images using a deformable registration, and the metallic dummy source markers were delineated using threshold-based segmentation followed by manual modification. The deformed CT (dCT), MR, and segmentation mask pairs were used for training and testing. The sCT generation model has a cascaded three-dimensional (3D) U-Net-based architecture that converts MR images to CT images and segments the metallic marker. The performance of the model was evaluated with intensity-based comparison metrics. Results: The proposed model with segmentation loss outperformed the 3D U-Net in terms of errors between the sCT and dCT. The structural similarity score difference was not significant. Conclusions: Our study shows the two-task-based deep learning models for generating the sCT images using low-tesla MR images for 3D ICR. This approach will be useful to the MR-only workflow in high-dose-rate brachytherapy.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.24 no.1
• /
• pp.111-121
• /
• 2006

Recently, many studies have been performed to apply airborne LIDAR data to extracting urban models. In order to model efficiently the man-made objects which are the main components of these urban models, it is important to extract automatically planar patches from the set of the measured three-dimensional points. Although some research has been carried out for their automatic extraction, no method published yet is sufficiently satisfied in terms of the accuracy and completeness of the segmentation results and their computational efficiency. This study thus aimed to developing an efficient approach to automatic segmentation of planar patches from the three-dimensional points acquired by an airborne LIDAR system. The proposed method consists of establishing adjacency between three-dimensional points, grouping small number of points into seed patches, and growing the seed patches into surface patches. The core features of this method are to improve the segmentation results by employing the variable threshold value repeatedly updated through a statistical analysis during the patch growing process, and to achieve high computational efficiency using priority heaps and sequential least squares adjustment. The proposed method was applied to real LIDAR data to evaluate the performance. Using the proposed method, LIDAR data composed of huge number of three dimensional points can be converted into a set of surface patches which are more explicit and robust descriptions. This intermediate converting process can be effectively used to solve object recognition problems such as building extraction.

• Korean Journal of Radiology
• /
• v.22 no.6
• /
• pp.901-911
• /
• 2021

Objective: To evaluate the technical applicability of a semiautomatic three-dimensional (3D) hybrid CT segmentation method for the quantification of right ventricular mass in patients with cardiovascular disease. Materials and Methods: Cardiac CT (270 cardiac phases) was used to quantify right ventricular mass using a semiautomatic 3D hybrid segmentation method in 195 patients with cardiovascular disease. Data from 270 cardiac phases were divided into subgroups based on the extent of the segmentation error (no error; ≤ 10% error; > 10% error [technical failure]), defined as discontinuous areas in the right ventricular myocardium. The reproducibility of the right ventricular mass quantification was assessed. In patients with no error or < 10% error, the right ventricular mass was compared and correlated between paired end-systolic and end-diastolic data. The error rate and right ventricular mass were compared based on right ventricular hypertrophy groups. Results: The quantification of right ventricular mass was technically applicable in 96.3% (260/270) of CT data, with no error in 54.4% (147/270) and ≤ 10% error in 41.9% (113/270) of cases. Technical failure was observed in 3.7% (10/270) of cases. The reproducibility of the quantification was high (intraclass correlation coefficient = 0.999, p < 0.001). The indexed mass was significantly greater at end-systole than at end-diastole (45.9 ± 22.1 g/m² vs. 39.7 ± 20.2 g/m², p < 0.001), and paired values were highly correlated (r = 0.96, p < 0.001). Fewer errors were observed in severe right ventricular hypertrophy and at the end-systolic phase. The indexed right ventricular mass was significantly higher in severe right ventricular hypertrophy (p < 0.02), except in the comparison of the end-diastolic data between no hypertrophy and mild hypertrophy groups (p > 0.1). Conclusion: CT quantification of right ventricular mass using a semiautomatic 3D hybrid segmentation is technically applicable with high reproducibility in most patients with cardiovascular disease.