• Proceedings of the Korean Nutrition Society Conference
• /
• 2001.11a
• /
• pp.84-84
• /
• 2001

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.97-99
• /
• 2022

For the early identification and treatment of colorectal cancer, accurate polyp segmentation is crucial. However, polyp segmentation is a challenging task, and the majority of current approaches struggle with two issues. First, the position, size, and shape of each individual polyp varies greatly (intra-class inconsistency). Second, there is a significant degree of similarity between polyps and their surroundings under certain circumstances, such as motion blur and light reflection (inter-class indistinction). U-net, which is composed of convolutional neural networks as encoder and decoder, is considered as a standard for tackling this task. We propose an updated U-net architecture replacing the encoder part with vision transformer network for polyp segmentation. The proposed architecture performed better than the standard U-net architecture for the task of polyp segmentation.

• 건강소식
• /
• v.35 no.11
• /
• pp.18-20
• /
• 2011

대장암은 결장과 직장에 생기는 약성의 종양을 말하며, 암이 발생하는 위치에 따라 결장에 생기는 암을 결장암, 직장에 생기는 암을 직장암이라고 하고, 이를 통칭하여 대장암 혹은 결장직장암이라고 한다. 대장암의 대부분은 대장의 점막에서 발생하는 선암이다. 선암의 대부분은 선종이라는 양성 종양(폴립, 용종)이 진행되어 발생하며 선암 이외에도 림프종, 육종, 편평상피암, 유암종 등이 발견된다.

• 대한예방의학회:학술대회논문집
• /
• 2001.10a
• /
• pp.233-233
• /
• 2001

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.396-398
• /
• 2022

The endoscopic pathological findings of gastrointestinal tract (GIT) are important in the early diagnosis of colorectal cancer. Deep learning based on convolutional nueral network (CNN) has been implemented to solve the subjective analysis problem and to increase the performance of early detection of pathological findings. However, the desired performance is yet to be achieved and CNNs are computationally complex. To solve these problems, in this paper, we propose a vision transformer based endoscopic pathological findings classification for the early detection of colorectal cancer. Publicly available endoscopic images with three pathological findings, including esophagitis, polyps, and ulcerative colitis, each with 1000 images were used. Using our approach, we have achieved a test accuracy of 98% in classifying the three pathological findings.

• 대한예방의학회:학술대회논문집
• /
• 1998.10b
• /
• pp.181-182
• /
• 1998

• 대한예방의학회:학술대회논문집
• /
• 1998.10b
• /
• pp.183-184
• /
• 1998

• Journal of Korea Association of Health Promotion
• /
• v.4 no.1
• /
• pp.49-59
• /
• 2006

"본 논문은 대한영상의학회지 2005년 제52권 제1호에 실렸던 논문으로 대한영상의학회의 승인을 득하고 본 협회지에 게재함. Purpose: We wished to compare CT colonography with conventional colonoscopy for the detection of colorectal poiypoid lesions, and we wanted to evaluate the role of IV contrast-enhanced CT colonography for the differentiation between benign polypoid lesions and malignant polypoid lesions. Materials and Methods: Thirty-four consecutive patients underwent CT colonography prior to conventional colonoscopy, Precontrast prone-position CT images and post contrast supine position CT images were obtained and the virtual colonoscopic images were reconstructed, Axial, sagittal and presence, size and morphologic features of colorectal polypoid lesions, and thor these findings were compared with the colonoscopic findings. The degree of enhancement of colorecralpolypoid lesions was measured by subtracting the attenuation valves obtained with precontrastand postcontrast CT images for the differentiation of benignity and malignancy of the colorectal polypoid lesions. Results. Among 75 colorectal polypoid lesions identified on conventional colonoscopy, 49neoplasms were found on CT coloaographv, and the overall detection rate was 65,3%.Detection rate of lesions smaller than l0mm was 52.1%(24/46), and the detection rate for lesions equal to or larger than 10mm was 86.2%(25/29), Morphologic features of the sessile type lesions on CT colonography were well correlated with those noted on colonoscopy, but the stalks were not identified in 6 of 13 polyps on CT colonography. There was no statistical correlation between benignity and malignancy and the degree of contrast enhancement on CT colonography, Conclusion CT colonography is a useful modality for the detection of colorectal polypoid lesionsequal to or polyps. However, CT colonography cannot differentiate benignity from malignancy.

• Tuberculosis and Respiratory Diseases
• /
• v.59 no.2
• /
• pp.198-203
• /
• 2005

Patients with acromegaly have high incidence of benign or malignant neoplasia than general population. Around fifteen percent of the deaths reported in acromegaly are attributable to malignancy of cancer. On the whole, mortality in acromegaly has been shown to be correlated with the degree of growth hormone (GH) control. Especially, the levels of insulin like growth factor-1 (IGF-1) may be higher in neoplasm, but there is no clear evidence to prove that tumor development is triggered by IGF-1 in acromegaly. Henceforth, we report a case of acromegaly associated with lung and gastric cancer in a 58-year-old man, suggesting the possible carcinogenic role of IGF-1.