• 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.

• Journal of the Korea Computer Graphics Society
• /
• v.8 no.1
• /
• pp.29-35
• /
• 2002

In virtual endoscopy, it is important to produce high quality perspective images in real-time. However, it is more significant to devise a navigation method that can make a virtual camera move through in human cavities such as colon and bronchus without collision and let the user control the camera intuitively. We propose an efficient navigation method, which generates 2D depth map during rendering the current frame, then determines position and direction of camera using the depth information. It offers collision-free navigation and allows us to control the camera as we want. Also it does not require preprocessing step and additional data structures.

• Journal of Biomedical Engineering Research
• /
• v.39 no.5
• /
• pp.213-219
• /
• 2018

Stomach cancer is the most diagnosed cancer in Korea. When gastric cancer is detected early, the 5-year survival rate is as high as 90%. Gastroscopy is a very useful method for early diagnosis. But the false negative rate of gastric cancer in the gastroscopy was 4.6~25.8% due to the subjective judgment of the physician. Recently, the image classification performance of the image recognition field has been advanced by the convolutional neural network. Convolutional neural networks perform well when diverse and sufficient amounts of data are supported. However, medical data is not easy to access and it is difficult to gather enough high-quality data that includes expert annotations. So This paper evaluates the efficacy of transfer learning in gastroscopy classification and diagnosis. We obtained 787 endoscopic images of gastric endoscopy at Gil Medical Center, Gachon University. The number of normal images was 200, and the number of abnormal images was 587. The image size was reconstructed and normalized. In the case of the ResNet50 structure, the classification accuracy before and after applying the transfer learning was improved from 0.9 to 0.947, and the AUC was also improved from 0.94 to 0.98. In the case of the InceptionV3 structure, the classification accuracy before and after applying the transfer learning was improved from 0.862 to 0.924, and the AUC was also improved from 0.89 to 0.97. In the case of the VGG16 structure, the classification accuracy before and after applying the transfer learning was improved from 0.87 to 0.938, and the AUC was also improved from 0.89 to 0.98. The difference in the performance of the CNN model before and after transfer learning was statistically significant when confirmed by T-test (p < 0.05). As a result, transfer learning is judged to be an effective method of medical data that is difficult to collect good quality data.

• Journal of the Korean Association of Oral and Maxillofacial Surgeons
• /
• v.37 no.3
• /
• pp.234-236
• /
• 2011

Traditional surgery to remove foreign bodies in the face carries a risk of postoperative morbidity with an injury to various anatomical structures, particularly the facial nerve and parotid duct and gland. Endoscopy can be a great aid in the removal of foreign bodies in the maxillofacial region. Surgical intervention using endoscope and/,or intraoperative images can be minimized, allowing the safe and precise removal of foreign bodies, and saving operating time. We report a case of the use of an endoscope and C-arm fluoroscopy guidance system to remove a very small foreign body.

• 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 the Korean Society of Radiology
• /
• v.83 no.2
• /
• pp.400-405
• /
• 2022

Gastrointestinal stromal tumors (GISTs) are not uncommon and often cause gastrointestinal bleeding. GISTs occurring in the small intestine are occasionally difficult to identify by endoscopy and CT. In this case, the patient underwent CT three times before surgery, and the lesion was found to be located in a different area of the abdominal cavity on each CT scan. Moreover, the lesion was missed in the first two CT images because it was difficult to distinguish it from the nearby collapsed small intestine. The lesion was eventually detected through angiography; however, the correct diagnosis and treatment were delayed for 3 years because it was mistaken for a vascular malformation, which is the most common cause of obscure GI bleeding in elderly patients. This report emphasizes the need for interventional radiologists to be updated and vigilant of the angiographic features of GISTs to make an accurate diagnosis and establish a management strategy.

• Journal of Korea Multimedia Society
• /
• v.13 no.7
• /
• pp.1044-1050
• /
• 2010

Endoscopic ultrasonography is a medical procedure in endoscopy combined with ultrasound to obtain images of the internal organs. It is useful to have a predictive pathological manifestation since a doctor can observe tumors under mucosa. However, it is often subjective to judge the degree of malignant degeneration of tumors. Thus, in this paper, we propose a feature analysis procedure to make the pathological manifestation more objective so as to improve the accuracy and recall of the diagnosis. In the process, we extract the ultrasound region from the image obtained by endoscopic ultrasonography. It is necessary to standardize the intensity of this region with the intensity of water region as a base since frequently found small intensity difference is only to be inefficient in the analysis. Then, we analyze the spot region with high echo and calcium deposited region by applying LVQ algorithm and bit plane partitioning procedure to tumor regions selected by medical expert. For detailed analysis, features such as intensity value, intensity information included within two random points chosen by medical expert in tumor region, and the slant of outline of tumor region in order to decide the degree of malignant degeneration. Such procedure is proven to be helpful for medical experts in tumor analysis.

• Proceedings of the Korea Contents Association Conference
• /
• 2009.05a
• /
• pp.390-397
• /
• 2009

Endoscopic ultrasonography is a medical procedure in endoscopy combined with ultrasound to obtain images of the internal organs. It is useful to have a predictive pathological manifestation since a doctor can observe tumors under mucosa. However, it is often subjective to judge the degree of malignant degeneration of tumors. Thus, in this paper, we propose a feature analysis procedure to make the pathological manifestation more objective so as to improve the accuracy and recall of the diagnosis. In the process, we extract the ultrasound region from the image obtained by endoscopic ultrasonography. It is necessary to standardize the intensity of this region with the intensity of water region as a base since frequently found small intensity difference is only to be inefficient in the analysis. Then, we analyze the spot region with high echo and calcium deposited region by applying LVQ algorithm and bit plane partitioning procedure to tumor regions selected by medical expert. For detailed analysis, features such as intensity value, intensity information included within two random points chosen by medical expert in tumor region, and the slant of outline of tumor region in order to decide the degree of malignant degeneration. Such procedure is proven to be helpful for medical experts in tumor analysis.

• Journal of Korean Neurosurgical Society
• /
• v.59 no.6
• /
• pp.577-583
• /
• 2016

Objective : The inter-rater reliability of the modified Knosp's classification was measured before the analysis. The clinical validity of the parasellar extension grading system was evaluated by investigating the extents of resection and complication rates among the grades in the endoscopic endonasal transsphenoidal surgery (EETS) for pituitary adenomas. Methods : From November 2008 to August 2015, of the 286 patients who underwent EETS by the senior author, 208 were pituitary adenoma cases (146 non-functioning pituitary adenomas, 10 adrenocorticotropic hormone-secreting adenomas, 31 growth hormone-secreting adenomas, 17 prolactin-secreting adenomas, and 4 thyroid-stimulating hormone-secreting adenomas; 23 microadenomas, 174 macroadenomas, and 11 giant adenomas). Two neurosurgeons and a neuroradiologist independently measured the degree of parasellar extension on the preoperative sellar MRI according to the modified Knosp's classification. Inter-rater reliability was statistically assessed by measuring the intraclass correlation coefficient. The extents of resection were evaluated by comparison of the pre- and post-operative MR images; the neurovascular complications were assessed by reviewing the patients' medical records. The extent of resection was measured in each parasellar extension grade; thereafter, their statistical differences were calculated. Results : The intraclass correlation coefficient value of reliability across the three raters amounted to 0.862. The gross total removal (GTR) rates achieved in each grade were 70.0, 69.8, 62.9, 21.4, 37.5, and 4.3% in Grades 0, 1, 2, 3A, 3B, and 4, respectively. A significant difference in the extent of resection was observed only between Grades 2 and 3A. In addition, significantly higher complication rates were observed in the groups above Grade 3A. Conclusion : Although the modified Knosp's classification system appears to be complex, its inter-rater reliability proves to be excellent. Regarding the clinical validity of the parasellar extension grading system, Grades 3A, 3B, and 4 have a negative predictive value for the GTR rate, with higher complication rates.

• Journal of Yeungnam Medical Science
• /
• v.30 no.2
• /
• pp.116-119
• /
• 2013

A burnt-out prostate cancer tumor is a very rare clinical entity. The term 'burnt-out' refers to a primary tumor that has spontaneously and nearly completely regressed without treatment. Since metastasis of prostate cancer is usually encountered in the presence of advanced disease, distant metastasis with an undetectable primary tumor is very rare. We report herein a case of a burnt-out prostate cancer tumor that metastasized to the thoracic (T) spine and caused cord compression. A 66-year-old man visited the Emergency Department due to weakness of both legs for the past two days. His blood and urine tests were normal at the time. His spine magnetic resonance imaging (MRI) scans looked like bone metastasis that involved the T-7 vertebral body and a posterior element, and caused spinal cord compression. Other images, including from the brain MRI, neck/chest/abdomino-pelvic computed tomography (CT) scan and 18F-fluorodeoxyglucose (FDG)-positron emission tomography (PET) and endoscopy, revealed no lesions that suggested malignancy. After total corpectomy T-7 and screw fixation/fusion at T5 to T10, the pathology report revealed a metastatic carcinoma that was strongly positive for prostate-specific antigen (PSA). The serum PSA value was 1.5 ng/mL. The transrectal 12-core prostate biopsy and ultrasonography showed no definitive hypoechoic lesion, but one specimen had slight (only 1%) adenocarcinoma with a Gleason score of 6 (3+3). The final diagnosis was burned-out prostate cancer with an initial normal PSA value. Although metastatic disease with an unknown primary origin was confirmed, a more aggressive approach in seeking the primary origin could provide a more specific treatment strategy and greater clinical benefit to patients.