• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.2-5
• /
• 2022

Human organs in the body have a complex structure, and in particular, the small intestine is about 7m long, so endoscopy is not easy and the risk of endoscopy is high. Currently, the test is performed with a capsule endoscope, and the test time is very long. The doctor connects the removed storage device to the computer to store the patient's capsule endoscope image and reads it using a program, but the capsule endoscope test results in a long image length, which takes a lot of time to read. In addition, in the case of the small intestine, there are many curves due to villi, so the occlusion area or light and shade of the image are clearly visible during the examination, and there may be cases where lesions and abnormal signs are missed during the examination. In this paper, we provide a method of assisting small intestine capsule endoscopic lesion examination using artificial neural networks to shorten the doctor's image reading time and improve diagnostic reliability.

• Korean Journal of Radiology
• /
• v.2 no.4
• /
• pp.192-196
• /
• 2001

Objective: To compare conventional and diffusion-weighted MR imaging in terms of their depiction of the abnormalities occurring in Creutzfeldt-Jakob disease. Materials and Methods: We retrospectively analyzed the findings of conventional (T2-weighted and fluid-attenuated inversion recovery) and diffusion-weighted MR imaging in four patients with biopsy-proven Creutzfeldt-Jakob disease. The signal intensity of the lesion was classified by visual assessment as markedly high, slightly high, or isointense, relative to normal brain parenchyma. Results: Both conventional and diffusion-weighted MR images demonstrated bilateral high signal intensity in the basal ganglia in all four patients. Cortical lesions were observed on diffusion-weighted MR images in all four, and on fluid-attenuated inversion recovery MR images in one, but in no patient on T2-weighted images. Conventional MR images showed slightly high signal intensity in all lesions, while diffusion-weighted images showed markedly high signal intensity in most. Conclusion: Diffusion-weighted MR imaging is more sensitive than its conventional counterpart in the depiction of Creutzfeldt-Jakob disease, and permits better detection of the lesion in both the cerebral cortices and basal ganglia.

• Korean Journal of Veterinary Research
• /
• v.64 no.1
• /
• pp.7.1-7.6
• /
• 2024

Bird species, particularly poultry and other bird types, including domestic pigeons, are susceptible to fowl pox, a contagious viral disease. The main goal of this study was to validate clinical avipoxvirus diagnoses using molecular analytical methods. The essential components of the investigation were the clinical signs, visible abnormalities, histological changes, and polymerase chain reaction analysis. Twenty out of 120 pigeons had clinical symptoms, which included yellowish crust or nodules near the feet, eyes, and beak. An erosive epidermal lesion and an epidermal acanthotic papular lesion with basal vacuolation were maculopapular evidence associated with significant epidermal hyperkeratosis, as confirmed by histological analysis. In addition, the results showed keratinocyte necrosis beneath the hyperkeratotic epidermal layer, together with superficial and deep dermal perivascular lymphocytic infiltration. In addition, the P4b core protein gene underwent phylogenetic analysis. The sequence analysis results indicated a high degree of similarity across the local strains, with just minor variations observed. Five sample sequences were selected and submitted to the NCBI database. These sequences were identified as OR187728, OR187729, OR187730, OR187731, and OR187732. All the various strains in this research may be classified under clade A of the chicken pox virus phylogenetic classification. This study presents the first description and characterization of pox virus infections in domestic pigeons inside the Basrah governorate.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.30 no.7C
• /
• pp.675-686
• /
• 2005

In this paper, we propose an efficient face region detection technique for the content-based video summarization. To segment video, shot changes are detected from a video sequence and key frames are selected from the shots. We select one frame that has the least difference between neighboring frames in each shot. The proposed face detection algorithm detects face region from selected key frames. And then, we provide user with summarized frames included face region that has an important meaning in dramas or movies. Using Bayes classification rule and statistical characteristic of the skin pixels, face regions are detected in the frames. After skin detection, we adopt the projection method to segment an image(frame) into face region and non-face region. The segmented regions are candidates of the face object and they include many false detected regions. So, we design a classifier to minimize false lesion using CART. From SGLD matrices, we extract the textual feature values such as Inertial, Inverse Difference, and Correlation. As a result of our experiment, proposed face detection algorithm shows a good performance for the key frames with a complex and variant background. And our system provides key frames included the face region for user as video summarized information.

• Journal of the Korean Society of Radiology
• /
• v.16 no.1
• /
• pp.25-34
• /
• 2022

Brain computed tomography (CT) is useful for brain lesion diagnosis, such as brain hemorrhage, due to non-invasive methodology, 3-dimensional image provision, low radiation dose. However, there has been numerous misdiagnosis owing to a lack of radiologist and heavy workload. Recently, object detection technologies based on artificial intelligence have been developed in order to overcome the limitations of traditional diagnosis. In this study, the applicability of a deep learning-based YOLOv5s model was evaluated for brain hemorrhage detection using brain CT images. Also, the effect of hyperparameters in the trained YOLOv5s model was analyzed. The YOLOv5s model consisted of backbone, neck and output modules. The trained model was able to detect a region of brain hemorrhage and provide the information of the region. The YOLOv5s model was trained with various activation functions, optimizer functions, loss functions and epochs, and the performance of the trained model was evaluated in terms of brain hemorrhage detection accuracy and training time. The results showed that the trained YOLOv5s model is able to provide a bounding box for a region of brain hemorrhage and the accuracy of the corresponding box. The performance of the YOLOv5s model was improved by using the mish activation function, the stochastic gradient descent (SGD) optimizer function and the completed intersection over union (CIoU) loss function. Also, the accuracy and training time of the YOLOv5s model increased with the number of epochs. Therefore, the YOLOv5s model is suitable for brain hemorrhage detection using brain CT images, and the performance of the model can be maximized by using appropriate hyperparameters.

• The Korean Journal of Nuclear Medicine
• /
• v.37 no.2
• /
• pp.120-127
• /
• 2003

Purpose: To evaluate diagnostic sensitivity of nuclear imaging in the detection of residual thyroid tissue and metastatic lesion, we have compared neck scintigrams with Tc-99m pertechnetate (Tc-99m scan) and high dose I-131 iodide (I-131 scan) in patients with differentiated thyroid cancer. Subjects and Methods: One hundred thirty-five thyroidectomized patients for differentiated thyroid cancer were enrolled in this study. Twenty-three had a previous history of radioiodine therapy. Planar and pin-hole images of anterior neck with Tc-99m were acquired at 20 minutes after injection, followed by I-131 scan three days after high-dose radioiodine therapy within 7 days interval. Patients were asked to discontinue thyroid hormone replacement more than 4 weeks. Results: All subjects were in hypothyroid state. Seventy out of 135 patients (51.9%) showed concordant findings between Tc-99m and I-131 scans. I-131 scan showed higher number of uptake foci in all of 65 patients showing discordant finding. Tc-99m scan showed no thyroid bed uptake in 34 patients, whereas 23 of them (67.6%) showed bed uptake in I-131 scan. Tc-99m scan did not show any uptake in thyroid bed in 11 of 112 patients without previous history of radioiodine therapy, but 9 of them showed bed uptake in I-131 scan. Tc-99m scan showed no bed uptake in all of the 23 patients with previous history of radioiodine therapy, in contrast 14 of them (60.9%) showed bed uptake in I-131 scan. Conclusion: These results suggest that Tc-99m scan has poor detectability for residual thyroid tissue or metastatic lesion in thyroidectomized differentiated thyroid cancer patients, compared to high dose I-131 therapy scan. Tc-99m scan could not detect any remnant tissue or metastatic lesion in patients with previous history of radioiodine treatment, especially.

• Asian Pacific Journal of Cancer Prevention
• /
• v.16 no.14
• /
• pp.6093-6097
• /
• 2015

Background: HPV DNA testing has been recently introduced as an adjunct test to cytology in the follow-up of patients after treatment for cervical lesions using the loop electrosurgical excision procedure (LEEP). The aim of this study was to evaluate the role of HPV testing in the detection of persistent or recurrent disease after LEEP in patients with cervical epithelial lesions in northern Thailand. Materials and Methods: Patients who underwent LEEP as a treatment for histological low-grade (LSIL) or high-grade squamous intraepithelial lesion (HSIL) or worse at Chiang Mai University Hospital between June 2010 and May 2012 were included. Follow-ups were scheduled at 6-month intervals and continued for 2 years using co-testing (liquid-based cytology and Hybrid Capture 2 [HC2]) at 6 months and 24 months and liquid-based cytology alone at 12 and 18 months. Results: Of 98 patients included, the histological diagnoses for LEEP included LSIL in 16 patients, and HSIL or worse in 82 patients. The LEEP margin status was negative in 84 patients (85.7%). At follow-up, 10 patients (10.2%) had persistent/recurrent lesions; 4 among LSIL patients (25.0%) and 6 in the group with HSIL or worse (7.3%). Only 2 of 82 patients (2.4%) with HSIL or worse diagnoses had histological HSIL in the persistent/recurrent lesions. Using histologically confirmed LSIL as the threshold for the detection of persistent/recurrent disease, cytology had a higher sensitivity than HC2 (90.0% versus 70.0%). At the 6-month follow-up appointment, combined cytology and HC2 (co-testing) had a higher sensitivity in predicting persistent/recurrent disease (80.0%) compared with that of cytology alone (70.0%) and HC2 (50.0%). Conclusions: After LEEP with a negative surgical margin, the rate of persistent/recurrent lesions is low. The addition of HPV testing at the 6-month visit to the usual cytology schedule may be an effective approach in the follow-up after LEEP.

• Journal of the Korean Arthroscopy Society
• /
• v.5 no.2
• /
• pp.124-130
• /
• 2001

Purpose : To identify occult intra-articular pathologies in the acute ankle fracture using arthroscopy and to investigate the factors to predict its possibility of occult injuries that could be occurred. Materials and Methods : This prospective study included fifty patients who got operation for the ankle fractures. Ankle arthroscopy was performed to document the type and anatomical location of occult lesion. We investigated the correlation between incidence of occult injuries and specific fracture type. Results : Of fifty ankles, 37 ankles had occult lesion. Twenty five loose bodies including displaced fragments were found and various cartilage lesions were found in 31 ankles. Tibial avulsion fragment by anterior inferior tibiofibular ligament was occurred in 6 cases. There was no correlation between the incidence of occult lesion and various factors including age, sex, injury mechanism and fracture type(p>0.05). Conclusion : The ankle arthroscopy had an effective role for the detection and treatment of occult injuries and it was difficult to predict the occurrence or associated accurately in all of th ankle fractures.

• Journal of Korean Academy of Oral and Maxillofacial Radiology
• /
• v.24 no.1
• /
• pp.115-124
• /
• 1994

The purpose of this study was to examine the differences in representation of a globular radiopaque mass on the pantomograms and Waters' views and to compare the efficacy of periapical radiograms, pantomograms and Waters' views in detection of defects on the internal walls of the maxillary sinus. This study was performed with dried human skull. For the study of difference of radiopaque mass shadow in the two views, rubber ball with a diameter of 10㎜ was used as the experimental lesion. It was placed successively on the internal wall of the anterior, posterior, medial, lateral walls and floor of the maxillary sinus. To examine the detectability of defects for radiographic techniques, defects were formed in the anterior, posterior, medial, lateral walls, and floor of the maxillary sinus. They were formed with 0.5㎜, 0.75㎜, 1.0㎜, 2.0㎜ and 3.0㎜ sized steel round burs with a slow speed dental handpiece. By subsequently plugging the holes with zinc oxide eugenol paste, radiopaque defects were produced. After that the periapical radiograms, the pantomograms and the Waters' views were taken each and every defect. The obtained results were as follows: 1. Rubber balls placed on each internal wall of the maxillary sinus were correctly depicted on the posterior wall and the floor in case of the pantomogram, and on the anterior wall and the medial wall in case of the Waters' view. 2. On the detectability of defects for each radiographic technique, radiolucent defects were detected in different places for each technique. Periapical radiogram could detect 1.0㎜ defect on the floor of the maxillary sinus, pantomogram could detect 2.0㎜ defect on every internal wall of the maxillary sinus, and Waters' view could detect 3.0㎜ defect on the anterior wall of the maxillary sinus. 3. On the detectability of defects for each radiographic technique, radiopaque defects were detected in different places for each technique. Periapical radiogram could clearly detect 0.5㎜ defect on the floor of the maxillary sinus, pantomogram could detect 0.5㎜ defect on every internal wall of the maxillary sinus, and finally Waters' view could detect 0.5㎜defect on the anterior wall of the maxillary sinus but 0.75㎜ defect on the anterior wall, lateral wall and floor of the maxillary sinus. As the result, the periapical radiogram is the most simple and satisfactory method for investigating in the maxillary sinus. The pantomogram is suitable method for screening of changes in the maxillary sinus. And the Waters' view is available for detect of lesion in the anterior wall of the maxillary sinus. For the purpose of accurate diagnosis and evaluation of lesion in the maxillary sinus, these techniques supplement each other.

• Korean Journal of Radiology
• /
• v.21 no.9
• /
• pp.1036-1044
• /
• 2020

Objective: To investigate the clinical feasibility of synthetic diffusion-weighted imaging (sDWI) at different b-values in patients with breast cancer by assessing the diagnostic image quality and the quantitative measurements compared with conventional diffusion-weighted imaging (cDWI). Materials and Methods: Fifty patients with breast cancer were assessed using cDWI at b-values of 800 and 1500 s/mm² (cDWI₈₀₀ and cDWI₁₅₀₀) and sDWI at b-values of 1000 and 1500 s/mm² (sDWI₁₀₀₀ and sDWI₁₅₀₀). Qualitative analysis (normal glandular tissue suppression, overall image quality, and lesion conspicuity) was performed using a 4-point Likert-scale for all DWI sets and the cancer detection rate (CDR) was calculated. We also evaluated cancer-to-parenchyma contrast ratios for each DWI set in 45 patients with the lesion identified on any of the DWI sets. Statistical comparisons were performed using Friedman test, one-way analysis of variance, and Cochran's Q test. Results: All parameters of qualitative analysis, cancer-to-parenchyma contrast ratios, and CDR increased with increasing b-values, regardless of the type of imaging (synthetic or conventional) (p < 0.001). Additionally, sDWI₁₅₀₀ provided better lesion conspicuity than cDWI₁₅₀₀ (3.52 ± 0.92 vs. 3.39 ± 0.90, p < 0.05). Although cDWI₁₅₀₀ showed better normal glandular tissue suppression and overall image quality than sDWI₁₅₀₀ (3.66 ± 0.78 and 3.73 ± 0.62 vs. 3.32 ± 0.90 and 3.35 ± 0.81, respectively; p < 0.05), there was no significant difference in their CDR (90.0%). Cancer-to-parenchyma contrast ratios were greater in sDWI₁₅₀₀ than in cDWI₁₅₀₀ (0.63 ± 0.17 vs. 0.55 ± 0.18, p < 0.001). Conclusion: sDWI₁₅₀₀ can be feasible for evaluating breast cancers in clinical practice. It provides higher tumor conspicuity, better cancer-to-parenchyma contrast ratio, and comparable CDR when compared with cDWI₁₅₀₀.