• Archives of Craniofacial Surgery
• /
• v.21 no.1
• /
• pp.64-68
• /
• 2020

The coexistence of craniofacial cleft and bilateral choanal atresia has only been reported in three cases in the literature, and only one of those cases involved a Tessier number 3 facial cleft. It is also rare for bilateral choanal atresia to be found in adulthood, with 10 previous cases reported in the literature. This report presents the case of a 19-year-old woman with a Tessier number 3 facial cleft who was diagnosed with bilateral choanal atresia in adulthood. At first, the diagnosis of bilateral choanal atresia was missed and septoplasty was performed. After septoplasty, the patient's symptoms did not improve, and an endoscopic examination revealed previously unnoticed bilateral choanal atresia. Computed tomography showed left membranous atresia and right bony atresia. The patient underwent an operation for opening and widening of the left choana with an image-guided navigation system (IGNS), which enabled accurate localization of the lesion while ensuring patient safety. Postoperatively, the patient became able to engage in nasal breathing and reported that it was easier for her to breathe, and there were no signs of restenosis at a 26-month follow-up. The patient was successfully treated with an IGNS.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.3
• /
• pp.19-28
• /
• 2021

Esophagogastroduodenoscopy is a method commonly used for early diagnosis of upper gastrointestinal lesions. However, 10-20 percent of the gastric lesions are reported to be missed, due to human error. And countries including the US, the UK, and Japan, the World Endoscopy Organization (WEO) suggested guidelines about essential gastrointestinal parts to take pictures of so that all gastric lesions are observed. In this paper, we propose deep learning techniques for classification of anatomical sites, aiming for the system that informs practitioners whether they successfully did the gastroscopy without blind spots. The proposed model uses pre-processing modules and data augmentation techniques suitable for gastroscopy images. Not only does the experiment result with a maximum F1 score of 99.6%, but it also shows a error rate of less than 4% based on the actual data. Given the performance results, we found the model to be explainable with the potential to be utilized in the clinical area.

• 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.

• Korean Journal of Optics and Photonics
• /
• v.33 no.6
• /
• pp.295-302
• /
• 2022

In this paper, a wedge prism application method was studied to design a full-high-definition (FHD)-class high-resolution flexible endoscope. In the case of the conventional flexible endoscope optical system, the F number is made large or a liquid lens is applied to obtain the same imaging performance in a wide depth of field. However, there is a problem in that the diameter of the optical system increases because an additional light guide and equipment are required. To solve this problem, two wedge prisms were applied to the flexible endoscope optical system to adjust the image distance for each object distance. First, two wedge prisms were symmetrically placed on the designed endoscopic optical system. An image distance satisfying the target imaging performance according to each objective distance was derived. Next, the wedge prism decenter value for controlling the image distance was derived. By combining these two data, a wedge prism decenter value that satisfied the target imaging performance at each object distance was applied in multi configurations. As a result of the optimal design applied with the wedge prism, a target imaging performance of more than 20% of the modulation transfer function for a resolution of 178 cycles/mm was satisfied in the entire depth of field of 100 mm-7 mm.

• Investigative Magnetic Resonance Imaging
• /
• v.1 no.1
• /
• pp.148-153
• /
• 1997

Purpose: To evaluate the diagnostic role of a three-dimensional MR cholangiopancreatography (MRCP) over endoscopic retrograde cholangio-pancreatography (ERCP) in various extrah-epatic biliary disease. Materials and Methods: MRCP and ERCP were performed in 45 consecutive patients with suspected extrahepatic biliary diseases. MRCP was obtained using a reverse fast imaging with a steady-state free precession (reverse FISP: PSIF) sequence, and then images were reconstructed by standard MIP algorithm. The predictability of biliary dilatation and level of obstruction of MRCP was evaluated using ERCP as a gold standard. The accuracy distinguishing malignant from benign lesions, and overall diagnostic accuracy were compared between MRCP and ERCP. Results: The sensitivity, specificity and accuracy of MRCP in predicting biliary dilatation were 94.6%, 75.0% and 91.1%, respectively. The level of obstruction was accurate in 87.0% with MRCP. The sensitivity, specificity and accuracy of MRCP and ERCP in distinguishing malignant from benign lesions were 76.2%, 87.5% and 82.2% and 71.4%, 83.3% and 77.8%, respectively. The overall diagnostic accuracy was 60.0% with MRCP and 55.6% with ERCP. Conclusion: 3D MRCP shows a good diagnostic value compared to that of ERCP, and can replace a ERCP.

• Journal of Biomedical Engineering Research
• /
• v.41 no.2
• /
• pp.101-106
• /
• 2020

Although benign gastric ulcers do not develop into gastric cancer, they are similar to early gastric cancer and difficult to distinguish. This may lead to misconsider early gastric cancer as gastric ulcer while diagnosing. Since gastric cancer does not have any special symptoms until discovered, it is important to detect gastric ulcers by early gastroscopy to prevent the gastric cancer. Therefore, we developed a Convolution Neural Network (CNN) model that can be helpful for endoscopy. 3,015 images of gastroscopy of patients undergoing endoscopy at Gachon University Gil Hospital were used in this study. Using ResNet-50, three models were developed to classify normal and gastric ulcers, normal and gastric cancer, and gastric ulcer and gastric cancer. We applied the data augmentation technique to increase the number of training data and examined the effect on accuracy by varying the multiples. The accuracy of each model with the highest performance are as follows. The accuracy of normal and gastric ulcer classification model was 95.11% when the data were increased 15 times, the accuracy of normal and gastric cancer classification model was 98.28% when 15 times increased likewise, and 5 times increased data in gastric ulcer and gastric cancer classification model yielded 87.89%. We will collect additional specific shape of gastric ulcer and cancer data and will apply various image processing techniques for visual enhancement. Models that classify normal and lesion, which showed relatively high accuracy, will be re-learned through optimal parameter search.

• Investigative Magnetic Resonance Imaging
• /
• v.20 no.3
• /
• pp.185-190
• /
• 2016

Xanthogranulomatous inflammation is a rare benign condition involving various organs. However, its pancreas involvement is very rare. To the best of our knowledge, only 17 cases have been described in the literature. Interestingly, all reported 17 cases due to various causes underwent surgical resection. Here, we present a case of xanthogranulomatous pancreatitis in a 63-year-old man. He presented with epigastric pain and solid mass mimicking ductal adenocarcinoma in the body and tail of pancreas on magnetic resonance imaging. The patient was diagnosed as xanthogranulomatous pancreatitis via endoscopic ultrasound-guided fine needle aspiration. After that, he was followed up and monitored without any surgical treatment. Here, we show imaging findings and serial image changes of xanthogranulomatous pancreatitis for this case.

• Maxillofacial Plastic and Reconstructive Surgery
• /
• v.21 no.2
• /
• pp.149-165
• /
• 1999

The pathomechanism of obstructive sleep apnea(OSA) is not clearly elucidated. The possible mechanisms are pathologic reduction of pharyngeal muscular tonus during sleep, abnormal anatomical stenosis of nasopharyx or a combination of the above two mechanisms. It is very important to find the cause(anatomical location or pathologic dynamic change) of OSA in order to treat it. Cephalometric analysis in patients with obstructive sleep apnea is a good method for evaluating anatomical morphologic change but it cannot give any information about the dynamic changes occurring during sleep. On the contrary, nasopharyngeal endoscopy offer 3 dimensional image and information about the dynamic changes. Accordingly, these two diagnostic tools can be utilize in the diagnosis and treatment planning of OSA Cephalometric analysis of craniofacial skeletal and soft tissue morphology in 53 patients with OSA and 43 controls was performed and cephalometric analysis and nasopharygeal endoscopy were performed in 9 patients with OSA in order to come up with individualized therapy plans. Following results were obtained ; Patients with OSA showed 1. body weight gain 2. clockwise mandibular rotation 3. increased anterior lower facial height 4. inferiorly positioned hyoid bone 5. increased length of soft palate 6. decreased sagittal dimension of nasopharyx 7. increased vertical length of inferior collapsable nasopharyx 8. increased length of tongue Through cephalometric analysis and nasopharygeal endoscopy(mutually cooperative in diagnosis), 9. one can find the possible origin of OSA and make a adequate individualized therapy plan and predict accurate prognosis. Cephalometric analysis and nasopharygeal endoscopy are highly recommended as a diagnostic aid in OSA patients

• Korean Journal of Optics and Photonics
• /
• v.19 no.2
• /
• pp.87-94
• /
• 2008

We present a new design for an endoscope objective lens composed of a lexible fiber bundle with 30,000 core, and a gradient-index (GRIN) objective lens with an optical adaptor. The characteristic of this objective lens is to be minimally-invasive to be able to insert easily in the internal organs of live animals. The GRIN lens has a small diameter and a very simple construction, which is selected with the diameter of 1.0 mm and numerical aperture of 0.5 to achieve a minimally-invasive outer diameter and a high resolution. The resultant designed lens shows the performance as follows; a lateral resolution of 1.63 um and diameters of 100% encircled energy of $0.3\;{\mu}m$ and $0.83\;{\mu}m$ for the on-axis and the off-axis image point, respectively. Also, we can present a cheap solution with a lateral resolution of 1.74 um and diameters of 100% encircled energy of $1.10\;{\mu}m$ and $2.84\;{\mu}m$ for the on-axis and the off-axis image point, respectively.

• Journal of the Korean Association of Oral and Maxillofacial Surgeons
• /
• v.34 no.1
• /
• pp.99-107
• /
• 2008

Objective : The objective of this review was to provide reliable comparative results regarding the effectiveness of any interventions either open or closed that can be used in the management of fractured mandibular condyle Patients and Methods : Research of studies from MEDLINE and Cochrane since 1990 was done. Controlled vocabulary terms were used. MeSH Terms were "Mandibular condyle" AND "Fractures, bone". Only comparative study were considered in this review using the "limit" function. According to the criteria, two review authors independently assessed the abstracts of studies resulting from the searches. The studies were divided according to some criteria, and following were measured: Ramus height, condyle sagittal displacement, condyle Towns's image displacement, Maximum open length, Protrusion & Lateral excursion, TMJ pain, Malocclusion, and TMJ disorder. Results : Many studies were analyzed to review the post-operative result of the two methods of treatment. Ramus height decreased more in when treated by closed reduction as opposed to open reduction. Sagittal condyle displacement was shown to be greater in closed reduction. Condyle Town's image condyle displacement had greater values in closed reduction. Maximum open length showed lower values in closed reduction. In protrusive and lateral movement, closed reduction was less than ORIF. Closed reduction showed greater occurrence of malocclusion than ORIF. However, post-operative pain and discomfort was greater in ORIF. Conclusion : In almost all categories, ORIF showed better results than CRIF. However, the use of the open reduction method should be considered due to the potential surgical morbidity and increased hospitalization time and cost. To these days, Endoscopic surgical techniques for ORIF (EORIF) are now in their infancy with the specific aims of eliminating concern for damage to the facial nerve and of reducing or eliminating facial scars. Before performing any types of treatment, patients must be understood of both of the treatment methods, and the best treatment method should be taken on permission.