• Clinical Endoscopy
• /
• v.57 no.2
• /
• pp.164-174
• /
• 2024

Pancreatic cancers have a poor prognosis, and their incident rates have risen. Endoscopic ultrasonography (EUS) is an efficient and reliable diagnostic modality for pancreatic lesions, providing high spatial resolution. However, while EUS helps to detect minor pancreatic lesions, nearly all solid pancreatic lesions are hypoechoic, which creates difficulty in making differential diagnoses of pancreatic lesions. When diagnosing pancreatic lesions, the performance of image-enhanced EUS techniques is essential, such as EUS elastography or contrast-enhanced harmonic EUS (CH-EUS). CH-EUS diagnosis is based on assessing the vascularity of lesions, whereas tissue elasticity is measured via EUS elastography. Elastography is either strain or shear-wave, depending on the different mechanical properties being evaluated. The usefulness of enhanced EUS techniques is demonstrated in this review for the differential diagnosis of pancreatic lesions, including solid and cystic lesions, and pancreatic cancer staging.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.16 no.3
• /
• pp.332-337
• /
• 2006

It has been suggested that the endoscopic color of intramucosal gastric carcinoma is correlated with mucosal vascularity within the carcinomatous tissue. The development of electronic endoscopy has made it possible to quantitatively measure the mucosal hemoglobin volume, using a hemoglobin index. The aim of this study was to make a software program to calculate the hemoglobin index (IHb) and then investigate whether the mucosal IHb determined from the electronic endoscopic data is a useful marker for evaluating the color of intramucosal gastric carcinoma, in particular with regard to its value for discriminating between the histologic types. The mean values of IHb for the carcinoma (IHb-C) and the mean values of IHb for the surrounding non-cancerous mucosa (IHb-N) were calculated in 75 intestinal-type and 34 diffuse-type gastric carcinomas. Then, we analyzed the ratio of the IHb-C to IHb-N. The mean IHb-C/IHb-N ratio in the intestinal-type carcinoma group was higher than that in the diffuse-type carcinoma group (1.28$\pm$0.19 vs. 0.81$\pm$0.18, respectively, p<0.001). When the cut-off point of the C/N ratio was set at 1.00, the accuracy rate, the sensitivity, the specificity, and the positive and negative predictive values of a C/R ratio below 1.00 for the differential diagnosis of diffuse-type carcinoma from intestinal-type carcinoma were 94.5%, 94.1%, 94.7%, 88.9% and 97.3%, respectively. IHb is useful for quantitative measurement of the endoscopic color in intramucosal gastric carcinoma and the IHb-C/IHb-N ratio would be helpful in distinguishing diffuse-type carcinoma from intestinal-type carcinoma.

• Journal of Biomedical Engineering Research
• /
• v.43 no.2
• /
• pp.102-108
• /
• 2022

Purpose: To propose a deep learning-based clinical decision support technique for laryngeal disease on epiglottis, tongue and vocal cords. Materials and Methods: A total of 873 laryngeal endoscopic images were acquired from the PACS database of Pusan N ational University Yangsan Hospital. and VGG16 model was applied with transfer learning and fine-tuning. Results: The values of precision, recall, accuracy and F1-score for test dataset were 0.94, 0.97, 0.95 and 0.95 for epiglottis images, 0.91, 1.00, 0.95 and 0.95 for tongue images, and 0.90, 0.64, 0.73 and 0.75 for vocal cord images, respectively. Conclusion: Experimental results demonstrated that the proposed model have a potential as a tool for decision-supporting of otolaryngologist during manual inspection of laryngeal endoscopic images.

• Journal of Biomedical Engineering Research
• /
• v.3 no.1
• /
• pp.55-58
• /
• 1982

In this paper, a method for camera position estimation in gaster using elechoendoscopic image sequence is proposed. In order to obtain proper image sequences, the gaster in divided into three sections. It is presented that camera position modeling for 3D information extraction and image distortion due to the endoscopic lenses is corrected.The feature points are represented with respect to the reference coordinate system belpw 10 percents error rate. The faster distortion correction algorithm is proposed in this paper. This algorithm uses error table which is faster than coordinate transform method using n-th order polynomials.

• Clinical Endoscopy
• /
• v.56 no.5
• /
• pp.563-577
• /
• 2023

In inflammatory bowel disease (IBD), chronic inflammation leads to unfavorable clinical outcomes and increases the risk of developing colorectal neoplasm (CRN); thereby highlighting the importance of endoscopically evaluating disease activity as well as detecting and characterizing CRN in patients with IBD. With recent advances in image-enhanced endoscopic (IEE) technologies, especially virtual chromoendoscopy (VCE) platforms, this review discusses state-of-the-art IEE techniques and their applicability in assessing disease activity and surveillance colonoscopy in patients with IBD. Among various IEE, VCE demonstrated the capacity to identify quiescent disease activity. And endoscopic remission defined by the new scoring system using VCE platform better predicted clinical outcomes, which may benefit the tailoring of therapeutic strategies in patients with IBD. High-definition dye-chromoendoscopy (HD-DCE) is numerically superior to high-definition white light endoscopy (HD-WLE) in detecting CRN in IBD; however, discrepancy is observed in the statistical significance. VCE showed comparable performance in detecting dysplasia to HD-WLE or DCE and potential for optical diagnosis to differentiate neoplastic from nonneoplastic lesions during surveillance colonoscopy. Applying these novel advanced IEE technologies would provide opportunities for personalized medicine in IBD and optimal treatment of CRN in patients with IBD.

• Korean Journal of Optics and Photonics
• /
• v.15 no.5
• /
• pp.429-434
• /
• 2004

An ophthalmic endoscope which is used in medical applications should have the total diameter less than 1 mm. Its image resolution is limited to 30∼40 lp/mm. Therefore, the image resolution is one of the most important factors to decide image quality of the ophthalmic endoscopic images. This study obtained high resolution and magnifying ophthalmic endoscopic images by a new optical design using a 0.23 pitch GRIN lens and high resolution fiber-optic image guide which has less than 5 ${\mu}{\textrm}{m}$ diameter microfibers. The resolutions of images from existing and from a new type of ophthalmic endoscope are measured and compared using a USAF resolution target.

• Korean Journal of Bronchoesophagology
• /
• v.18 no.2
• /
• pp.45-48
• /
• 2012

Background Neoplastic vessels tend to proliferate on the surface of malignant lesions in the aerodigestive tract. So, superficial malignant lesions can be detected earlier by enhancing mucosal vascular clarity. To enhance mucosal vascular clarity on endoscopic image, we developed an image processing algorithm of RGB (red-green-blue) channel substitution image (CSI). Methods Each pixel in original white light image (WLI) has its own value of red, green and blue channel. Various combinations of RGB channel substitution was tried on original WLI. Results To make superficial blood vessels darker than brighter background mucosa, in the CSI algorithm, RGB value in each pixel of WLI is substituted; red value to green one, green value to blue one. There was a good contrast between superficial mucosal vessels and background brighter mucosa in the CSI image. Conclusion By RGB CSI algorithm, WLI could be successfully converted to new images with enhanced mucosal vascular clarity. Using RGB CSI algorithm could provide added vascular visibility on original WLI.

• Proceedings of the KOSOMBE Conference
• /
• v.1994 no.12
• /
• pp.22-25
• /
• 1994

• Proceedings of the Optical Society of Korea Conference
• /
• 2006.07a
• /
• pp.235-236
• /
• 2006

• Clinical Endoscopy
• /
• v.55 no.1
• /
• pp.113-121
• /
• 2022

Background/Aims: We have been developing artificial intelligence based polyp histology prediction (AIPHP) method to classify Narrow Band Imaging (NBI) magnifying colonoscopy images to predict the hyperplastic or neoplastic histology of polyps. Our aim was to analyze the accuracy of AIPHP and narrow-band imaging international colorectal endoscopic (NICE) classification based histology predictions and also to compare the results of the two methods. Methods: We studied 373 colorectal polyp samples taken by polypectomy from 279 patients. The documented NBI still images were analyzed by the AIPHP method and by the NICE classification parallel. The AIPHP software was created by machine learning method. The software measures five geometrical and color features on the endoscopic image. Results: The accuracy of AIPHP was 86.6% (323/373) in total of polyps. We compared the AIPHP accuracy results for diminutive and non-diminutive polyps (82.1% vs. 92.2%; p=0.0032). The accuracy of the hyperplastic histology prediction was significantly better by NICE compared to AIPHP method both in the diminutive polyps (n=207) (95.2% vs. 82.1%) (p<0.001) and also in all evaluated polyps (n=373) (97.1% vs. 86.6%) (p<0.001) Conclusions: Our artificial intelligence based polyp histology prediction software could predict histology with high accuracy only in the large size polyp subgroup.