• 한국식물병리학회지
• /
• 제3권2호
• /
• pp.131-136
• /
• 1987

벼 품종 Brazos와 M-201의 도열병에 대한 단위시간당 감염속도와 점접종원으로 부터의 단위 거리당 확산경사는 밭논과 물논의 두 재배조건에 따라 크게 달랐다. 물논재배는 도열병의 감염속도를 늦추고 확산경사를 완만하게 하였다. 점접종원으로부터 거리별로 4지점에서 측정된 도열병의 감염속도는 거리에 따른 통계적인 유의차는 없었지만 점접종원으로부터의 거리가 멀어짐에 따라 빨라지는 경향이었다. 품종별 감염속도는 Brazos보다 더 이병성인 M-201 품종에서 높았고 확산경사도 M-201 품종에서 가파른 경향이었다. 그러나 도열병이 진전함에 따라 생성된 이차전염원 때문에 도열병 확산경사는 두 품종에서 모두 완만해졌다. 조사된 확산형사의 두 경험적 모델 중에서 Kiyosawa와 Shiyomi 모델이 Gregory 모델에 비하여 통계적 적합성이 높았다. 밭상태에서 단위시간당 도열병 isopaths 이동거리는 Brazos와 M-201 품종에서 각각 0.2m/일와 0.4m/일로 측정하였다. 이상의 결과, 도열병에 대한 품종저항성의 차이는 감염속도뿐만 아니라 확산경사의 측정에 의하여 효과적으로 감지될 수 있다고 생각된다.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2015년도 추계학술대회
• /
• pp.693-694
• /
• 2015

본 논문은 소아 및 성인의 중이염을 자동 판별할 수 있는 알고리즘을 제안한다. 제안 방법은 중이염 영상과 정상 영상 데이터베이스에서 HOG(histogram of oriented gradient) 기술자를 사용하여 특징을 추출한 다음 SVM(support vector machine) 분류기를 통하여 추출된 특징들을 학습시킨다. 입력 영상이 학습된 특징들의 모델을 기반으로 SVM 분류기를 통하여 중이염 여부가 판별된다. 실험결과 제안한 방법이 정확도 90% 이상의 판별 성능을 나타내었다.

• 한국멀티미디어학회논문지
• /
• 제24권2호
• /
• pp.178-185
• /
• 2021

Three-dimensional high-resolution magnetic resonance imaging (MRI) provides fine-level anatomical information for disease diagnosis. However, there is a limitation in obtaining high resolution due to the long scan time for wide spatial coverage. Therefore, in order to obtain a clear high-resolution(HR) image in a wide spatial coverage, a super-resolution technology that converts a low-resolution(LR) MRI image into a high-resolution is required. In this paper, we propose a super-resolution technique through filter learning based on information on the surrounding gradient information in 3D space from 3D MRI images. In the learning step, the gradient features of each voxel are computed through eigen-decomposition from 3D patch. Based on these features, we get the learned filters that minimize the difference of intensity between pairs of LR and HR images for similar features. In test step, the gradient feature of the patch is obtained for each voxel, and the filter is applied by selecting a filter corresponding to the feature closest to it. As a result of learning 100 T1 brain MRI images of HCP which is publicly opened, we showed that the performance improved by up to about 11% compared to the traditional interpolation method.

• 한국정보통신학회논문지
• /
• 제20권3호
• /
• pp.621-629
• /
• 2016

본 논문은 소아 및 성인의 중이염을 자동 판별할 수 있는 알고리즘을 제안한다. 제안 방법은 중이염 영상과 정상 영상 데이터베이스에서 HoG(histogram of oriented gradient) 기술자를 사용하여 특징을 추출한 다음 SVM(support vector machine) 분류기를 통하여 추출된 특징들을 학습시킨다. 여기서 SVM 입력 벡터의 추출을 위하여 입력영상은 영상크기를 사전에 정의된 일정크기의 영상으로 변환되고 변환된 영상을 16개의 블록과 4개의 셀로 분할하며 9개의 빈을 가진 HoG를 사용한다. 결과적으로 입력 영상에서 576개의 특징을 추출하고 이를 SVM의 학습과 분류에 사용된다. 입력 영상이 학습된 특징들의 모델을 기반으로 SVM 분류기를 통하여 중이염 여부가 판별된다. 실험 결과 제안한 방법은 정확도 90% 이상의 판별 성능을 나타내었다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권2호
• /
• pp.576-590
• /
• 2023

Machine learning is widely used in various academic fields, and recently it has been actively applied in the medical research. In the medical field, machine learning is used in a variety of ways, such as speeding up diagnosis, discovering new biomarkers, or discovering latent traits of a disease. In the respiratory field, a relative regional air volume change (RRAVC) map based on quantitative inspiratory and expiratory computed tomography (CT) imaging can be used as a useful functional imaging biomarker for characterizing regional ventilation. In this study, we seek to predict RRAVC using various regular machine learning models such as extreme gradient boosting (XGBoost), light gradient boosting machine (LightGBM), and multi-layer perceptron (MLP). We experimentally show that MLP performs best, followed by XGBoost. We also propose several relative coordinate systems to minimize intersubjective variability. We confirm a significant experimental performance improvement when we apply a subject's relative proportion coordinates over conventional absolute coordinates.

• Mass Spectrometry Letters
• /
• 제6권4호
• /
• pp.116-119
• /
• 2015

Globotriaosylsphingosine (lyso-Gb3) is considered as one of the biological marker for Fabry disease. To date, a reliable biomarker that reflects disease severity and progression has not been discovered to guide the management of Fabry disease. A new method included a simple protein precipitation with acetonitrile in 100 μL of plasma following analyte separation on an Phenomenex Kintex- C18 column using a gradient elution (0.1% formic acid in 5-90% acetonitrile). Total run time was within 12 min including sample preparation and MS/MS analysis. The limit of detection and limit of quantitation were 1 ng/mL and 2 ng/mL, respectively. The calibration curve was linear over the concentration range of 2.0-200.0 ng/mL (r² = 0.9999). Inter-day accuracy and precision at 7 level were 93.4-100.7% with RSD of 0.55-5.97%. Absolute recovery was 97.6-98.6%. The method was applied to human and mice plasma, proved the suitability for quantification of lyso-Gb3 for screening, diagnosis and therapeutic monitoring of Fabry disease patients.

• 한국멀티미디어학회논문지
• /
• 제25권8호
• /
• pp.1233-1241
• /
• 2022

Tumors of the brain are the deadliest, with a life expectancy of only a few years for those with the most advanced forms. Diagnosing a brain tumor is critical to developing a treatment plan to help patients with the disease live longer. A misdiagnosis of brain tumors will lead to incorrect medical treatment, decreasing a patient's chance of survival. Radiologists classify brain tumors via biopsy, which takes a long time. As a result, the doctor will need an automatic classification system to identify brain tumors. Image classification is one application of the deep learning method in computer vision. One of the deep learning's most powerful algorithms is the convolutional neural network (CNN). This paper will introduce a novel deep learning structure and image gradient to classify brain tumors. Meningioma, glioma, and pituitary tumors are the three most popular forms of brain cancer represented in the Figshare dataset, which contains 3,064 T1-weighted brain images from 233 patients. According to the numerical results, our method is more accurate than other approaches.

• ETRI Journal
• /
• 제46권3호
• /
• pp.513-525
• /
• 2024

Deep neural networks trained on labeled medical data face major challenges owing to the economic costs of data acquisition through expensive medical imaging devices, expert labor for data annotation, and large datasets to achieve optimal model performance. The heterogeneity of diseases, such as Alzheimer's disease, further complicates deep learning because the test cases may substantially differ from the training data, possibly increasing the rate of false positives. We propose a reconstruction-based self-supervised anomaly detection model to overcome these challenges. It has a dual-subnetwork encoder that enhances feature encoding augmented by skip connections to the decoder for improving the gradient flow. The novel encoder captures local and global features to improve image reconstruction. In addition, we introduce an entropy-based image conversion method. Extensive evaluations show that the proposed model outperforms benchmark models in anomaly detection and classification using an encoder. The supervised and unsupervised models show improved performances when trained with data preprocessed using the proposed image conversion method.

• Clinical and Experimental Pediatrics
• /
• 제55권8호
• /
• pp.297-300
• /
• 2012

Symptomatic pulmonary arterial hypertension (PAH) in patients with isolated atrial septal defect (ASD) is rare during infancy. We report a case of isolated ASD with severe PAH in an infant who developed airway obstruction as cardiomegaly progressed. The patient presented with recurrent severe respiratory insufficiency and failure to thrive before the repair of the ASD. Echocardiography confirmed volume overload on the right side of heart and severe PAH (tricuspid regurgitation [TR] with a peak pressure gradient of 55 to 60 mmHg). The chest radiographs demonstrated severe collapse of both lung fields, and a computed tomography scan showed narrowing of the main bronchus because of an intrinsic cause, as well as a dilated pulmonary artery compressing the main bronchus on the left and the intermediate bronchus on the right. ASD patch closure was performed when the infant was 8 months old. After the repair of the ASD, echocardiography showed improvement of PAH (TR with a peak pressure gradient of 22 to 26 mmHg), and the patient has not developed recurrent respiratory infections while showing successful catch-up growth. In infants with symptomatic isolated ASD, especially in those with respiratory insufficiency associated with severe PAH, extrinsic airway compression should be considered. Correcting any congenital heart diseases in these patients may improve their symptoms.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제18권6호
• /
• pp.1478-1499
• /
• 2024

Coronavirus disease (COVID-19) is an infectious disease caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) virus. COVID-19 become an active epidemic disease due to its spread around the globe. The main causes of the spread are through interaction and transmission of the droplets through coughing and sneezing. The spread can be minimized by isolating the susceptible patients. However, it necessitates remote monitoring to check the breathing issues of the patient remotely to minimize the interactions for spread minimization. Thus, in this article, we offer a wearable-IoTs-centered framework for remote monitoring and recognition of the breathing pattern and abnormal breath detection for timely providing the proper oxygen level required. We propose wearable sensors accelerometer and gyroscope-based breathing time-series data acquisition, temporal features extraction, and machine learning algorithms for pattern detection and abnormality identification. The sensors provide the data through Bluetooth and receive it at the server for further processing and recognition. We collect the six breathing patterns from the twenty subjects and each pattern is recorded for about five minutes. We match prediction accuracies of all machine learning models under study (i.e. Random forest, Gradient boosting tree, Decision tree, and K-nearest neighbor. Our results show that normal breathing and Bradypnea are the most correctly recognized breathing patterns. However, in some cases, algorithm recognizes kussmaul well also. Collectively, the classification outcomes of Random Forest and Gradient Boost Trees are better than the other two algorithms.