• Journal of Preventive Medicine and Public Health
• /
• v.19 no.2 s.20
• /
• pp.263-272
• /
• 1986

During the 8 months from October 1985 to May 1986, the survey was performed on 211 leprosy patients over fifty years old, settled in the four villages of Iksan county, North of Chulla province. In that obserbation, we investigated the frequency and the degree of impairments according to sex, age, and anatomical location by the 'guides to the evaluation of permanent impairment'. The noticeable findings were made as follows: 1) Frequency of impairment by anatomical location was significantly higher in hand than eye and foot (p<0.01). 2) Frequency of impairment was significantly increased in eye according as age increase (p<0.01). 3) The degree of impairments of all patients was the highest in hand as 28.7%. 4) By the kinds of impairment, the flextion and the amputation were most common in hand and foot, and loss of central vision was common symptom in eye. 5) The degree of impairments of 211 leprosy patients was shown as 44.1% and increased according as age increase.

• Annals of Clinical Neurophysiology
• /
• v.24 no.2
• /
• pp.107-110
• /
• 2022

We describe the case of a 22-year-old female complaining of ophthalmoplegia, which deteriorated with seizure. Leigh syndrome (LS) was diagnosed by identifying the m.9176T>C mutation. She improved with vitamin cocktail therapy plus intravenous methylprednisolone, and had an excellent prognosis. This was the first case of an adult patient with LS presenting with the m.9176T>C mutation and reporting cortical symptoms, which in this case comprised cortical vision loss, and cortical, basal ganglia, and brainstem signal changes on magnetic resonance imaging.

• Journal of Information Processing Systems
• /
• v.18 no.6
• /
• pp.794-802
• /
• 2022

The recovery of reasonable depth information from different scenes is a popular topic in the field of computer vision. For generating depth maps with better details, we present an efficacious monocular depth prediction framework with coordinate attention and feature fusion. Specifically, the proposed framework contains attention, multi-scale and feature fusion modules. The attention module improves features based on coordinate attention to enhance the predicted effect, whereas the multi-scale module integrates useful low- and high-level contextual features with higher resolution. Moreover, we developed a feature fusion module to combine the heterogeneous features to generate high-quality depth outputs. We also designed a hybrid loss function that measures prediction errors from the perspective of depth and scale-invariant gradients, which contribute to preserving rich details. We conducted the experiments on public RGBD datasets, and the evaluation results show that the proposed scheme can considerably enhance the accuracy of depth prediction, achieving 0.051 for log10 and 0.992 for δ<1.25³ on the NYUv2 dataset.

• Journal of Yeungnam Medical Science
• /
• v.40 no.2
• /
• pp.198-201
• /
• 2023

Invasive sphenoid sinus aspergillosis can mimic Tolosa-Hunt syndrome (THS), leading to frequent misdiagnoses and potentially fatal consequences. We report a case of invasive sphenoid sinus aspergillosis initially misdiagnosed as THS. A 79-year-old man presented with right periorbital pain, ophthalmoplegia, and loss of vision. Initial evaluations including magnetic resonance imaging (MRI), were normal. He was first diagnosed with THS based on clinical features. The disease progressed despite high-dose intravenous steroid treatment, and an enhancing mass-like lesion was found in the right orbital apex, cavernous sinus, and sphenoid sinus on follow-up MRI. Aspergillosis was eventually confirmed by sphenoid sinus biopsy. The patient developed cerebral infarction and finally died despite being treated with amphotericin B. Given that invasive sphenoid sinus aspergillosis may initially resemble THS, high suspicion and rapid histological examination are important for diagnosis.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.556-558
• /
• 2022

Diabetic retinopathy (DR) is one of the leading diseases causing vision loss. Early detection of this disease has a crucial role in protecting patients' eyes. Recent works have achieved impressive result when performing DR detection on fundus images using deep learning. In the deep learning-based approach, data augmentation has significant impact on the result. Recently, many data augmentation policies have been proposed and achieved state-of-the-art performance on different tasks. In this work, we compare effects of three data augmentation policies on DR grading in fundus images.

• Archives of Craniofacial Surgery
• /
• v.25 no.1
• /
• pp.31-37
• /
• 2024

Orbital floor fractures are commonly encountered, but the dislocation of the eyeball into the maxillary sinus is relatively rare. When it does occur, globe dislocation can have serious consequences, including vision loss, enucleation, and orbito-ocular deformity. Immediate surgical intervention is typically attempted when possible. However, severe comorbidities and poor general health can delay necessary surgery. In this report, we present the surgical outcomes of a 70-year-old woman who received delayed treatment for traumatic eyeball dislocation into the maxillary sinus due to a subarachnoid hemorrhage and hemopneumothorax. Additionally, we propose a treatment algorithm based on our clinical experience and a review of the literature.

• ETRI Journal
• /
• v.46 no.3
• /
• pp.526-537
• /
• 2024

Monitoring fetal growth in utero is crucial to anomaly diagnosis. However, current computer-vision models struggle to accurately assess the key metrics (i.e., head circumference and occipitofrontal and biparietal diameters) from ultrasound images, largely owing to a lack of training data. Mitigation usually entails image augmentation (e.g., flipping, rotating, scaling, and translating). Nevertheless, the accuracy of our task remains insufficient. Hence, we offer a U-Net fetal head measurement tool that leverages a hybrid Dice and binary cross-entropy loss to compute the similarity between actual and predicted segmented regions. Ellipse-fitted two-dimensional ultrasound images acquired from the HC18 dataset are input, and their lower feature layers are reused for efficiency. During regression, a novel region of interest pooling layer extracts elliptical feature maps, and during segmentation, feature pyramids fuse field-layer data with a new scale attention method to reduce noise. Performance is measured by Dice similarity, mean pixel accuracy, and mean intersection-over-union, giving 97.90%, 99.18%, and 97.81% scores, respectively, which match or outperform the best U-Net models.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.47 no.1
• /
• pp.1-6
• /
• 2010

The lens distortion in the machine vision system is inevitable phenomenon. Distortion is getting worse, due to the selection of lens in the trend of reducing prices and size of the system. In this trend, the distortion correction becomes more important. But, the traditional correction methods has problems, such as complexity and requiring more operations. Effective distorted digital image correction is the precondition of target detection and recognition based on vision inspection. To overcome the disadvantage of traditional distortion correction algorithms, such as complex modeling, massive computation and marginal information loss, an image distortion correction algorithm based on photogrammetry method is proposed in this paper. In our method, we use the lattice image as the measurement target. Through the experimental results, we could find that we can reduce the processing time by 4ms. And also the inspection failure rate of our method was reduced by 2.3% than human-eyes inspection method.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.17 no.6
• /
• pp.121-130
• /
• 2007

In this paper, we propose a reversible watermarking scheme in the JPEG compression domain. The reversible watermarking is useful to authenticate the content without the quality loss because it preserves the original content when embed the watermark information. In the internet, for the purpose to save the storage space and improve the efficiency of communication, digital image is usually compressed by JPEG or GIF. Therefore, it is necessary to develop a reversible watermarking in the JPEG compression domain. When the watermark is embedded, the lossless compression was used and the original image is recovered during the watermark extracting process. The test results show that PSNRs are distributed from 38dB to 42dB and the payload is from 2.5Kbits to 3.4Kbits where the QF is 75. Where the QF of the Lena image is varied from 10 to 99, the PSNR is directly proportional to the QF and the payload is around $1.6{\sim}2.8Kbits$.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.5
• /
• pp.1814-1828
• /
• 2021

Low-light image enhancement is a key technique to overcome the quality degradation of photos taken under scotopic vision illumination conditions. The degradation includes low brightness, low contrast, and outstanding noise, which would seriously affect the vision of the human eye recognition ability and subsequent image processing. In this paper, we propose an approach based on deep learning and Retinex theory to enhance the low-light image, which includes image decomposition, illumination prediction, image reconstruction, and image optimization. The first three parts can reconstruct the enhanced image that suffers from low-resolution. To reduce the noise of the enhanced image and improve the image quality, a super-resolution algorithm based on the Laplacian pyramid network is introduced to optimize the image. The Laplacian pyramid network can improve the resolution of the enhanced image through multiple feature extraction and deconvolution operations. Furthermore, a combination loss function is explored in the network training stage to improve the efficiency of the algorithm. Extensive experiments and comprehensive evaluations demonstrate the strength of the proposed method, the result is closer to the real-world scene in lightness, color, and details. Besides, experiments also demonstrate that the proposed method with the single low-light image can achieve the same effect as multi-exposure image fusion algorithm and no ghost is introduced.