• 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.

• Journal of Digital Convergence
• /
• v.10 no.9
• /
• pp.351-356
• /
• 2012

This paper presents the 2D/3D conversion technique using depth map which is generated based on the haze and relative height cue. In cases that only the conventional haze information is used, errors in image without haze could be generated. To reduce this kind of errors, a new approach is proposed combining the haze information with depth map which is constructed based on the relative height cue. Also the gray scale image from Mean Shift Segmentation is combined with depth map of haze information to sharpen the object's contour lines, upgrading the quality of 3D image. Left and right view images are generated by DIBR(Depth Image Based Rendering) using input image and final depth map. The left and right images are used to generate red-cyan 3D image and the result is verified by measuring PSNR between the depth maps.

• Proceedings of the Korean Information Science Society Conference
• /
• 2002.04b
• /
• pp.634-637
• /
• 2002

오늘날 CT나 MR등을 통한 의학 영상 기술과 컴퓨터 성능의 향상으로 인체 내부 장기의 영상을 비교적 용이하게 얻을 수 있으며 얻어진 영상 정보는 컴퓨터로 수치와 되므로 데이터의 조작 및 가공이 용이하다. 그러나, 이 데이터는 2D 슬라이스들의 연속으로 표현되므로 이것을 보다 편리하게 가시화. 조작, 분석이 용이한 상태로 바꾸기 위해서는 3차원 구조로의 재구성이 필요하게 된다. 이것을 위하여 무엇보다도 먼저 CT나 MR을 통하여 얻어진 영상을 분석하여 특정 장기의 영상 부분를 다른 조직의 영상부분으로부터 분리(segmentation)할 필요가 있다. 이러한 Segmentation방법에는 여러가지가 있는데, 수작업의 결합 등으로 인해서 비효율적인 문제점을 가지고 있다. 이에 본 논문은 보다 효율적인 segmentation의 처리를 위하여 region-based 기법을 응용하여 새로운 segmentation 방법을 개발하였다. 그리하여, 본 논문이 제안한 알고리즘을 슬라이스 간격이 큰 2차원 복부 CT 영상에 적용시켜 간(liver)의 추출을 시도하였고 향상된 성능을 확인할 수 있었다.

• The Transactions of the Korea Information Processing Society
• /
• v.13 no.7
• /
• pp.335-347
• /
• 2024

Open-vocabulary 3D point cloud instance segmentation (OV-3DIS) is a challenging visual task to segment a 3D scene point cloud into object instances of both base and novel classes. In this paper, we propose a novel model Open3DME for OV-3DIS to address important design issues and overcome limitations of the existing approaches. First, in order to improve the quality of class-agnostic 3D masks, our model makes use of T3DIS, an advanced Transformer-based 3D point cloud instance segmentation model, as mask proposal module. Second, in order to obtain semantically text-aligned visual features of each point cloud segment, our model extracts both 2D and 3D features from the point cloud and the corresponding multi-view RGB images by using pretrained CLIP and OpenSeg encoders respectively. Last, to effectively make use of both 2D and 3D visual features of each point cloud segment during label assignment, our model adopts a unique feature ensemble method. To validate our model, we conducted both quantitative and qualitative experiments on ScanNet-V2 benchmark dataset, demonstrating significant performance gains.

• Proceedings of the KIPE Conference
• /
• 2001.10a
• /
• pp.104-108
• /
• 2001

In this paper, the 3-D measurement method of moving object with a laser and one camera system for image processing method is presented. The method of segmentation image in conventional method, the error are generated by the threshold values. In this paper, to improve these problem for segmentation image, the calculation of weighting factor using brightness distribution by histogram of stored images are proposed. Therefore the image erosion and spread are improved, the correct and reliable informations can be measured. In this paper, the system of 3-D extracting information using the proposed algorithm can be applied to manufactory automation, building automation, security guard system, and detecting information system for all of the industry areas.

• Journal of Advanced Information Technology and Convergence
• /
• v.10 no.1
• /
• pp.25-36
• /
• 2020

Motivation: Fibers as the extracellular filamentous structures determine the shape of the cytoskeletal structures. Their characterization and reconstruction from a 3D cellular image represent very useful quantitative information at the cellular level. In this paper, we presented a novel automatic method to extract fiber diameter distribution through a pipeline to reconstruct fibers from 3D fluorescence confocal images. The pipeline is composed of four steps: segmentation, skeletonization, template fitting and fiber tracking. Segmentation of fiber is achieved by defining an energy based on tensor voting framework. After skeletonizing segmented fibers, we fit a template for each seed point. Then, the fiber tracking step reconstructs fibers by finding the best match of the next fiber segment from the previous template. Thus, we define a fiber as a set of templates, based on which we calculate a diameter distribution of fibers.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.496-498
• /
• 2023

Brain tumor segmentation problem has challenges in the tumor diversity of location, imbalance, and morphology. Attention mechanisms have recently been used widely to tackle medical segmentation problems efficiently by focusing on essential regions. In contrast, the fusion approaches enhance performance by merging mutual benefits from many models. In this study, we proposed a 3D dual fusion attention network to combine the advantages of fusion approaches and attention mechanisms by residual self-attention and local blocks. Compared to fusion approaches and related works, our proposed method has shown promising results on the BraTS 2018 dataset.

• The KIPS Transactions:PartB
• /
• v.11B no.2
• /
• pp.133-140
• /
• 2004

Recently, the dental information systems were rapidly developed in order to store and process the data of patients. But, these systems should serve a doctor a good quality information against disease for diagnostic and surgery purpose so as to success in this field. This function of the system it important to persuade patients to undergo proper surgical operation they needed. Hence, 3D teeth model capable of simulating the dental surgery and treatment is necessary Teeth manipulation of dentistry is performed on individual tooth in dental clinic. io, 3D teeth reconstruction system should have the techniques of segmentation and 3D reconstruction adequate for individual tooth. In this paper, we propose the techniques of adaptive optimal segmentation to segment the individual area of tooth, and reconstruction method of tooth based on contour-based method. Each tooth can be segmented from neighboring teeth and alveolar bone in CT images using adaptive optimal threshold computed differently on tooth. Reconstruction of individual tooth using results of segmentation can be manipulated according to user's input and make the simulation of dental surgery and treatment possible.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.17 no.2
• /
• pp.447-452
• /
• 2013

Microfluidic devices can offer precise control for a verity of tasks involving biological specimen. In this paper, we propose an integrated system consisting of a microfluidic device along with a digital holographic microscope and present three-dimensional (3D) sensing and segmentation of biological microorganisms. When the individual microorganisms are inputted into the microfluidic channel, the holographic microscope records their holograms. The holograms are computationally reconstructed in 3D using Fresnel transform and the reconstructed phase images are used to search the position of microorganisms. Optical experiments are carried out and experimental results are presented to illustrate the usefulness of the proposed system.

• The KIPS Transactions:PartA
• /
• v.9A no.1
• /
• pp.83-92
• /
• 2002

The segmentation of target objects from three dimensional volume images is an essential step for visualization and volume measurement. In this paper, we present a method to detect the surface of objects by improving the widely used levoy filtering for volume visualization. Using morphological operators we generate completely closed surfaces and selectively segment objects using the volume growing algorithm. The presented method was applied to 3-D artificial sphere images and angiocardiograms. We quantitatively compared this method with the conventional levoy filtering using artificial sphereimages, and the results showed that our method is better in the aspect of voxel errors. The results of visual comparison using angiocardiograms also showed that our method is more accurate. The presented method in this paper is very effective for segmentation of volume data because segmentation, visualization and measurement are frequently used together for 3-D image processing and they can be easily related in our method.