• Journal of Gastric Cancer
• /
• v.3 no.4
• /
• pp.195-200
• /
• 2003

Purpose: Advancement of computed tomography (CT) hardware and software has allowed thin section scanning and reconstruction of fascinating 2-dimentional (2D) and 3- dimentional (3D) images. Especially, the reconstruction of 3D images of gastrointestinal tract has been used in the detection and diagnosis of pre-malignant and malignant diseases. To compare the efficacy of CT gastrography with conventional upper gastrointenstinal series (UGIs) in gastric cancer patients. Materials and Methods: During Nov. 2002 and Mar. 2003, twenty-seven patients who had gastric cancer received both double contrast upper GI series and CT gastrography prior to radical surgery. Among these patients, nineteen had early gastric cancer (EGC) and 8 had advanced gastric cancer (AGC). Fifteen patients were male and 12 were female. The mean age was 54 yrs (range, $27\∼75$ yrs). The patients were placed on NPO and Stomach was distended with gas in fasting state prior to CT scanning. Double contrast upper GI series were performed as routine manual. CT scan was conducted in all patients using 8 or 16-channel multidetector CT in this study. The collimation and reconstruction for CT scanning were set at 2.5 mm and 1.25 mm, respectively. CT scanning was performed in the supine position. For image processing, CT gastrography, in which raysum and surface rendering images were constructed, virtual and 2D image in coronal and sagittal images were performed. The detectability of gastric cancer was assessed between UGIs and CT gastrography. Results: In AGCs, the detection rate of cancer using CT gastrography and virtual gastroscopy was higher than EGC cases. However, CT gastrography and virtual gastroscopy showed less favorable results than UGIs. Even though only a small number of cases had been studied, we might conclude that CT gastrography and virtual gastroscopy could replace UGIs in the detection of AGC cases. Conclusion: The detection rate used with CT gastrography and Virtual gastroscopy is not better than that of UGIs in early gastric cancer, however, in advanced gastric cancer cases, it is nearly equal to that of UGIs.

• Smart Media Journal
• /
• v.9 no.3
• /
• pp.59-70
• /
• 2020

This paper presents a fully automatic tool to recognize the liver region from CT images based on a deep learning model, namely Multiple Filter U-net, MFUnet. The advantages of both U-net and Multiple Filters were utilized to construct an autoencoder model, called MFUnet for segmenting the liver region from computed tomograph. The MFUnet architecture includes the autoencoding model which is used for regenerating the liver region, the backbone model for extracting features which is trained on ImageNet, and the predicting model used for liver segmentation. The LiTS dataset and Chaos dataset were used for the evaluation of our research. This result shows that the integration of Multiple Filter to U-net improves the performance of liver segmentation and it opens up many research directions in medical imaging processing field.

• The KIPS Transactions:PartB
• /
• v.10B no.5
• /
• pp.509-514
• /
• 2003

The virtual bronchoscopy was implemented using chest CT images to visualize inside of tracheo-bronchial wall. The optical endoscopy procedures are invasive, uncomfortable for patients and sedation or anesthesia may be required. Also, they have serious side effects such as perforation, infection and hemorrhage. In order to determine the navigation path, we segmented the tracheo-bronchial wall from the chest CT image. We used the coordinates as a navigation path for virtual camera that were calculated from medial axis transformation. We used the perspective projection and marching cube algorithm to render the surface from volumetric CT image data. The tracheobronchial disease was classified into tracheobronchial stenosis causing from inflammation or lung cancer, bronchiectasis and bronchial cancer. The virtual bronchoscopy is highly recommended as a diagnosis tool with which the specific place of tracheobronchial disease can be identified and the degree of tracheobronchial disease can be measured qualitatively, Also, the virtual bronchoscopy can be used as an education and training tool for endoscopist and radiologist.

• Journal of Biomedical Engineering Research
• /
• v.18 no.4
• /
• pp.365-373
• /
• 1997

In this paper, a new method of the 3D(dimensional) image reconstruction is proposed to build up the 3D image from 2D images using digital image processing techniques and computer graphics. First, the new feature extraction algorithm that doesn't need various input parameters and is not affected by threshold is adopted This new algorithm extracts feature points by eliminating some undesirable points on the ground of the connectivity. Second, as the cast function to reconstruct surfaces using extracted feature points, the minimum distance measure between two plane images has been adopted According to this measure, the surface formation algorithm doesn't need complex calculation and takes the form of triangle or trapezoid To investigate usefulness, this approach has been applied to a head CT image and compared with other methods. Experimental comparisons show that the suggested algorithm yields better performance on feature extraction than others. In contrast with the other methods, the complex calculation for surface formation in the proposed algorithm is not necessary.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2011.10a
• /
• pp.554-556
• /
• 2011

The occurrence of various vascular diseases due to the need for accurate and rapid diagnosis was emphasized. Several limitations to the presence of pulmonary vascular angiography for chest CT imaging was aware of the need for diversity in medical image processing with Insight Toolkit(ITK) suggested pulmonary vascular division. In this paper, by contrast, based on the value of a two-step partitioning of the lungs and blood vessels to perform the process of splitting. Lung area segmentation of each stage image enhancement, threshold value, resulting in areas of interest cut image acquisition and acquired pulmonary vascular division in lung area obtained by applying the fill area. Partitioned on the basis of pulmonary vascular imaging to obtain three-dimensional visualization image of the pulmonary vascular analysis and diagnosis of a variety of perspectives are considered possible.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.38 no.2
• /
• pp.179-190
• /
• 2001

In this proposed study, observing and analyzing contrast enhanced abdominal CT images, we segmented the liver automatically. We computed the ratio of each gray value from the estimated gray value range. With the average value of mesh image, we distinguished the liver from the noise parts. We divided the region based on immersion simulation. The threshold value is determined from the mesh image which is generated from each gray value portion of the liver and is used in dividing the liver to the noise region. To get the outline of the liver, we generated template image which represents the lump of the liver, and subtracted it from the binary image. With the results we use the proposed algorithm using 8-connectivity instead of the present opening algorithm, to reduce the processing time. We computed the volume from the segmented organ size and presented a clinical demonstration with the animal experiment

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.13 no.10
• /
• pp.2163-2170
• /
• 2009

We present an automated, energy minimized-based method for Lung parenchyma segmenting Chest Computed Tomography(CT) datasets. Deformable model is used for energy minimized segmentation. Quantitative knowledge including expected volume, shape of Chest CT provides more feature constrain to diagnosis or surgery operation planning. Segmentation subdivides an lung image into its consistent regions or objects. Depends on energy-minimizing, the level detail image of subdivision is carried. Segmentation should stop when the objects or region of interest in an application have been detected. The deformable model that has attracted the most attention to date is popularly known as snakes. Snakes or deformable contour models represent a special case of the general multidimensional deformable model theory. This is used extensively in computer vision and image processing applications, particularly to locate object boundaries, in the mean time a new type of external force for deformable models, called gradient vector flow(GVF) was introduced by Xu. Our proposed algorithm of deformable model is new external energy of GVF for exact segmentation. In this paper, Clinical material for experiments shows better results of proposal algorithm in Lung parenchyma segmentation on Chest CT.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2009.04a
• /
• pp.106-109
• /
• 2009

Recently, image matching becomes important in Computer Aided Diagnosis (CAD) due to the huge amount of medical images. Specially, texture feature is useful in medical image matching. However, texture features such as co-occurrence matrices can't describe well the spatial distribution of gray levels of the neighborhood pixels. In this paper we propose a frequency domain-based texture feature extractor that describes the local spatial distribution for medical image retrieval. This method is based on 2D Local Discrete Fourier transform of local images. The features are extracted from local Fourier histograms that generated by four Fourier images. Experimental results using 40 classes Brodatz textures and 1 class of Emphysema CT images show that the average accuracy of retrieval is about 93%.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2004.05a
• /
• pp.699-702
• /
• 2004

단층촬영에 의해 획득된 흉부영상의 폐 영역은 기관지, 폐동맥, 폐정맥으로 구성된 복잡한 형태를 가지고 있다. 또한 이들 조직과 폐 영역 내에 존재하는 악성 종양과 같은 질병들 사이의 공간정보의 유사성으로 인해 방사선 전문의조차도 질병을 간단히 구분 해내는데 많은 어려움이 따른다. 따라서 본 논문에서는 이러한 유사한 공간정보를 갖는 폐 영역을 수리형태학 필터인 모폴로지(morphology)와 국부적인 워터쉐드(watershed) 알고리즘을 이용하여 분할하고, 분할된 폐 영역으로부터 색전 또는 종양 등의 결절(nodule)의 정보를 가지고 있는 혈관들을 추출하는 효과적인 알고리즘을 제안한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2024.05a
• /
• pp.702-704
• /
• 2024

최근 사회적으로 근감소증에 대한 관심이 높아지면서 노인성 근감소증 시장이 골다공증 시장을 뛰어 넘을 것으로 전망하고 있다. 진단 방법으로 의료영상기반으로 근육량을 인공지능 기술로 측정하여 근감소증 진단에 적용하는 연구가 활발하게 진행되고 있다. 본 논문에서는 복부 CT 영상에서 L3 부위의 근육량을 기반으로 한 진단 기준을 이용하여 아시아 피험자의 T-score를 기반으로 근감소증 진단을 자동화하였다. 특히 복부 CT영상의 업로드와 함께 자동으로 근육량을 측정하여 개인별 상태를 확인할 수 있도록하여 근감소증 진단을 지원 할 수 있도록 개발하였다. 그리고 이를 기반으로 4가지 간 질환 환자의 L3 부위 근육량을 측정하여 근감소증과의 상관성을 확인하였다. 이는 다양한 기저 질환과 근감소증과의 연관성 연구에 도움이 될 것으로 기대한다.