• Journal of the Korean Institute of Intelligent Systems
• /
• v.17 no.2
• /
• pp.265-269
• /
• 2007

In this paper, we propose an automatic extraction method of gastric cancer region from electronic endoscopic images. We use the brightness and saturation of HSI in removing noises by illumination and shadows by the crookedness occurring in the endoscopic process. We partition the image into several areas with similar pigments of hemoglobin using IHb. The candidate areas for gastric cancer are defined as the areas that have high hemoglobin pigments and high value in every channel of RGB. Then the morphological characteristics of gastric cancer are used to decide the target region. In experiment, our method is sufficiently accurate in that it correctly identifies most cases (18 out of 20 cases) from real electronic endoscopic images, obtained by expert endoscopists.

• Proceedings of the KIEE Conference
• /
• 2002.07d
• /
• pp.2715-2717
• /
• 2002

Image segmentation is an essential technique of image analysis. In spite of the issues in contour initialization and boundary concavities, active contour models(snakes) are popular and successful methods for the segmentation. In this paper, we present a new active contour model, GGF snake, for segmentation of endoscopic image. The GGF snake is less sensitive to contour initialization and ensures high accuracy, large capture range, and fast CPU time for computing external force. It was observed that the GGF snake produced more reasonable results in various image types, such as simple synthetic images, commercial digital camera images, and endoscopic images than previous snakes did.

• Journal of Trauma and Injury
• /
• v.24 no.2
• /
• pp.136-142
• /
• 2011

Purpose: Blunt pancreatic injury has a high mortality rate, especially if adequate management is delayed. Although many guidelines exist for diagnosis and treatment, there is no consensus to date. Therefore, we analyzed the role of endoscopic retrograde cholangiopancreatography (ERCP) as a diagnostic and therapeutic tool for the treatment of traumatic pancreatic injury. Methods: We retrospectively reviewed the electronic medical records (EMR) database at Asan Medical Center (Seoul, South Korea) to identify all patients diagnosed with trauma to the pancreas between June 2003 and December 2010. Clinical and operative findings, CT (computed tomography) images, and ERCP findings were assessed. Results: A total of 40 patients were evaluated in this study. Of these, 14 patients underwent diagnostic ERCP, and 26 did not. Of the 14 patients who underwent diagnostic ERCP, 5 were found to have normal pancreatic ducts, thereby preventing a needless laparotomy in these patients. Of the patients diagnosed with ductal injury, four were treated with endoscopic intervention, and four underwent an exploratory laparotomy. The remaining patient was treated with radiologic intervention (percutaneous drainage) to manage pancreatic pseudocyst formation. Conclusion: Our findings suggest that ERCP is a beneficial diagnostic and therapeutic modality for the treatment of traumatic pancreatic injury.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.67 no.7
• /
• pp.928-933
• /
• 2018

Nowadays, gastropathy is a common disease. As endoscopic equipment are developed and used widely, it is possible to provide a large number of endoscopy images. Computer-aided Diagnosis (CADx) systems aim at helping physicians to identify possibly malignant abnormalities more accurately. In this paper, we present a CADx system to detect and classify the abnormalities of gastric lesions which include bleeding, ulcer, neuroendocrine tumor and cancer. We used an Inception module based deep learning model. And we used data augmentation for learning. Our preliminary results demonstrated promising potential for automatically labeled region of interest for endoscopy doctors to focus on abnormal lesions for subsequent targeted biopsy, with Az values of Receiver Operating Characteristic(ROC) curve was 0.83. The proposed CADx system showed reliable performance.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2006.05a
• /
• pp.322-326
• /
• 2006

본 논문에서는 내시경 영상에 대해 위암 영역을 자동으로 추출하는 방법을 제안한다. 본 논문에서는 내시경 영상을 획득하는 과정에서 발생하는 조명에 의한 잡음과 굴곡에 의해 발생하는 그림자에 의한 잡음 부분을 해결하기 위해서 HSI의 채도와 밝기 값을 이용하여 잡음 영역을 제거한다. 그리고 헤모글로빈 색소 정보를 나타내는 IHb값을 이용하여 전자 내시경 영상에서 유사한 헤모글로빈 색소 정보를 가지는 영역으로 분할한다. 분할된 영역들 중에서 RGB의 각 채널과 헤모글로빈 색소가 높게 나타나면 후보 영역으로 설정한다. 설정된 후보 영역 중에서 위암 영역의 형태학적인 특징 정보를 이용하여 위암 영역을 추출한다. 실제 전문의가 제공한 20개의 내시경 영상을 대상으로 실험한 결과, 제안된 위암 추출 방법으로 17개가 정확히 추출되었고 3개의 내시경 영상에서는 위암 영역이 정확히 추출되지 않았다.