• Advances in nano research
• /
• 제12권2호
• /
• pp.197-212
• /
• 2022

The purpose of this study is to develop an automatic software system for bone age evaluation and to evaluate its accuracy in testing and feasibility in clinical practice. 20394 left-hand radiographs of healthy children (2-18 years old) were collected from China Skeletal Development Survey data of 1998 and China Skeletal Development Survey data of 2005. Three experienced radiologists and China-05 standard maker jointly evaluate the stages of bone development and the reference bone age was determined by consensus. 1020 from 20394 radiographs were picked randomly as test set and the remaining 19374 radiographs as training set and validation set. Accuracy of the automatic software system for bone age assessment is evaluated in test set and two clinical test sets. Compared with the reference standard, the automatic software system based on RUS-CHN for bone age assessment has a 0.04 years old mean difference, ±0.40 years old in 95% confidence interval by single reading, a 85.6% percentage agreement of ratings, a 93.7% bone age accuracy rate, 0.17 years old of MAD, 0.29 years old of RMS; Compared with the reference standard, the automatic software system based on TW3-C RUS has a 0.04 years old mean difference, a ±0.38 years old in 95% confidence interval by single reading, a 90.9% percentage agreement of ratings, a 93.2% bone age accuracy rate, a 0.16 years of MAD, and a 0.28 years of RMS. Automatic software system, AI-China-05 showed reliably accuracy in bone age estimation and steady determination in different clinical test sets.

• Korean Journal of Radiology
• /
• 제20권8호
• /
• pp.1275-1284
• /
• 2019

Objective: To develop algorithms using convolutional neural networks (CNNs) for automatic segmentation of acute ischemic lesions on diffusion-weighted imaging (DWI) and compare them with conventional algorithms, including a thresholding-based segmentation. Materials and Methods: Between September 2005 and August 2015, 429 patients presenting with acute cerebral ischemia (training:validation:test set = 246:89:94) were retrospectively enrolled in this study, which was performed under Institutional Review Board approval. Ground truth segmentations for acute ischemic lesions on DWI were manually drawn under the consensus of two expert radiologists. CNN algorithms were developed using two-dimensional U-Net with squeeze-and-excitation blocks (U-Net) and a DenseNet with squeeze-and-excitation blocks (DenseNet) with squeeze-and-excitation operations for automatic segmentation of acute ischemic lesions on DWI. The CNN algorithms were compared with conventional algorithms based on DWI and the apparent diffusion coefficient (ADC) signal intensity. The performances of the algorithms were assessed using the Dice index with 5-fold cross-validation. The Dice indices were analyzed according to infarct volumes (< 10 mL, ≥ 10 mL), number of infarcts (≤ 5, 6-10, ≥ 11), and b-value of 1000 (b1000) signal intensities (< 50, 50-100, > 100), time intervals to DWI, and DWI protocols. Results: The CNN algorithms were significantly superior to conventional algorithms (p < 0.001). Dice indices for the CNN algorithms were 0.85 for U-Net and DenseNet and 0.86 for an ensemble of U-Net and DenseNet, while the indices were 0.58 for ADC-b1000 and b1000-ADC and 0.52 for the commercial ADC algorithm. The Dice indices for small and large lesions, respectively, were 0.81 and 0.88 with U-Net, 0.80 and 0.88 with DenseNet, and 0.82 and 0.89 with the ensemble of U-Net and DenseNet. The CNN algorithms showed significant differences in Dice indices according to infarct volumes (p < 0.001). Conclusion: The CNN algorithm for automatic segmentation of acute ischemic lesions on DWI achieved Dice indices greater than or equal to 0.85 and showed superior performance to conventional algorithms.

• 한국음향학회지
• /
• 제27권3호
• /
• pp.111-118
• /
• 2008

본 논문에서는 음악 장르 분류를 위한 새로운 자동 Taxonomy 구축 알고리즘을 제안한다. 제안된 알고리즘은 모든 가능한 노드들의 분류 확률을 예측하여 예측된 분류 성능값이 가장 좋은 조합을 Taxonomy로 구축하는 것이다. 제안된 알고리즘에서의 분류 확률 예측은 훈련 데이터를 k-fold cross validation을 이용하여 분류기에 적용함으로써 이루어진다. 제안된 알고리즘을 기반으로 한 분류 성능 측정은 2 클래스로 이루어진 각각의 노드에 2개 범주 분류에 효과적인 support vector machine을 적용함으로써 이루어진다. 제안된 알고리즘의 성능 검증을 위해 음색, 리듬, 피치 등 오디오 신호의 특징을 나타내는 다양한 파라미터를 오디오 신호로부터 추출하여 제안된 알고리즘과 기존의 다중 범주 분류기들을 이용하여 분류성능을 평가하였다. 다양한 실험결과 제안된 알고리즘은 기존의 알고리즘에 비하여 5%에서 25%정도의 분류 성능이 향상된 것을 확인할 수 있었고 특히 낮은 차원의 특징벡터를 이용한 분류 실험에서는 10% 에서 25% 향상된 좋은 성능을 보였다.

• Korean Journal of Radiology
• /
• 제21권6호
• /
• pp.660-669
• /
• 2020

Objective: To evaluate the accuracy of a deep learning-based automated segmentation of the left ventricle (LV) myocardium using cardiac CT. Materials and Methods: To develop a fully automated algorithm, 100 subjects with coronary artery disease were randomly selected as a development set (50 training / 20 validation / 30 internal test). An experienced cardiac radiologist generated the manual segmentation of the development set. The trained model was evaluated using 1000 validation set generated by an experienced technician. Visual assessment was performed to compare the manual and automatic segmentations. In a quantitative analysis, sensitivity and specificity were calculated according to the number of pixels where two three-dimensional masks of the manual and deep learning segmentations overlapped. Similarity indices, such as the Dice similarity coefficient (DSC), were used to evaluate the margin of each segmented masks. Results: The sensitivity and specificity of automated segmentation for each segment (1-16 segments) were high (85.5-100.0%). The DSC was 88.3 ± 6.2%. Among randomly selected 100 cases, all manual segmentation and deep learning masks for visual analysis were classified as very accurate to mostly accurate and there were no inaccurate cases (manual vs. deep learning: very accurate, 31 vs. 53; accurate, 64 vs. 39; mostly accurate, 15 vs. 8). The number of very accurate cases for deep learning masks was greater than that for manually segmented masks. Conclusion: We present deep learning-based automatic segmentation of the LV myocardium and the results are comparable to manual segmentation data with high sensitivity, specificity, and high similarity scores.

• Investigative Magnetic Resonance Imaging
• /
• 제24권3호
• /
• pp.123-131
• /
• 2020

Purpose: Joint label fusion (JLF) is a popular multi-atlas-based segmentation algorithm, which compensates for dependent errors that may exist between atlases. However, in order to get good segmentation results, it is very important to set the several free parameters of the algorithm to optimal values. In this study, we first investigate the feasibility of a JLF algorithm for prostate segmentation in MR images, and then suggest the optimal set of parameters for the automatic prostate segmentation by validating the results of each parameter combination. Materials and Methods: We acquired T2-weighted prostate MR images from 20 normal heathy volunteers and did a series of cross validations for every set of parameters of JLF. In each case, the atlases were rigidly registered for the target image. Then, we calculated their voting weights for label fusion from each combination of JLF's parameters (r_pxy, r_pz, r_sxy, r_sz, β). We evaluated the segmentation performances by five validation metrics of the Prostate MR Image Segmentation challenge. Results: As the number of voxels participating in the voting weight calculation and the number of referenced atlases is increased, the overall segmentation performance is gradually improved. The JLF algorithm showed the best results for dice similarity coefficient, 0.8495 ± 0.0392; relative volume difference, 15.2353 ± 17.2350; absolute relative volume difference, 18.8710 ± 13.1546; 95% Hausdorff distance, 7.2366 ± 1.8502; and average boundary distance, 2.2107 ± 0.4972; in parameters of r_pxy = 10, r_pz = 1, r_sxy = 3, r_sz = 1, and β = 3. Conclusion: The evaluated results showed the feasibility of the JLF algorithm for automatic segmentation of prostate MRI. This empirical analysis of segmentation results by label fusion allows for the appropriate setting of parameters.

• 한국음향학회지
• /
• 제39권4호
• /
• pp.279-285
• /
• 2020

항행 선박의 시·공간적 모니터링 기술 연구는 연안 해양공간에서 해양 생태계 보호 및 효율적인 관리를 위해서 중요하다. 본 연구에서는 실험해역에서 측정된 선박 소음 특징인 광대역 줄무늬 패턴 자료에 인공지능 기술을 적용하여 항행하는 선박을 자동 탐지하는 연구를 수행하였다. 소음 스펙트럼 이미지와 선박의 항행정보를 수집하기 위한 해상시험은 2016년 7월 15일부터 26일까지 제주 남부 해역에서 실시되었고, 컨볼루션 신경망 모델은 수집된 이미지를 기반으로 학습, 교차검증 과정을 거쳐 최적화되었다. 선박 소음 자동 탐지 기법의 성능은 정밀도(0.936), 재현율(0.830), 평균 정밀도(0.824) 그리고 정확도(0.949)로 평가되었다. 결론적으로 인공지능 기법을 활용하여 선박 소음의 자동 탐지 가능성을 확인하였다. 본 연구의 결과로부터 성능을 향상시킬 수 있는 방안 및 향후 연구에 대하여 제안하였다.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2018년도 학술발표회
• /
• pp.448-448
• /
• 2018

In this study, the regression models (Load ESTimator and eight-parameter model) were evaluated to estimate instantaneous pollutant loads under various criteria and optimization methods. As shown in the results, LOADEST commonly used in interpolating pollutant loads could not necessarily provide the best results with the automatic selected regression model. It is inferred that the various regression models in LOADEST need to be considered to find the best solution based on the characteristics of watersheds applied. The recently developed eight-parameter model integrated with Genetic Algorithm (GA) and Gradient Descent Method (GDM) were also compared with LOADEST indicating that the eight-parameter model performed better than LOADEST, but it showed different behaviors in calibration and validation. The eight-parameter model with GDM could reproduce the nitrogen loads properly outside of calibration period (validation). Furthermore, the accuracy and precision of model estimations were evaluated using various criteria (e.g., $R^2$ and gradient and constant of linear regression line). The results showed higher precisions with the $R^2$ values closed to 1.0 in LOADEST and better accuracy with the constants (in linear regression line) closed to 0.0 in the eight-parameter model with GDM. In hence, based on these finding we recommend that users need to evaluate the regression models under various criteria and calibration methods to provide the more accurate and precise results for pollutant load estimations.

• 한국항공운항학회지
• /
• 제29권4호
• /
• pp.37-44
• /
• 2021

In case of South Korea, the airspace which airlines can operate is extremely limited due to the military operational area located within the Incheon flight information region. As a result, safety problems such as mid-air collision between aircraft or Traffic alert and Collision Avoidance System Resolution Advisory (TCAS RA) may occur with higher probability than in wider airspace. In order to prevent such safety problems, an mid-air collision risk detection model based on Detect-And-Avoid (DAA) well clear metrics is investigated. The model calculates the risk of mid-air collision between aircraft using aircraft trajectory data. In this paper, the practical use of DAA well clear metrics based model has been validated. Aviation safety data such as aviation safety mandatory report and Automatic Dependent Surveillance Broadcast is used to measure the performance of the model. The attributes of individual aircraft track data is analyzed to correct the threshold of each parameter of the model.

• Clinical and Experimental Pediatrics
• /
• 제65권2호
• /
• pp.73-80
• /
• 2022

A mercury sphygmomanometer (MS) has been the gold standard for pediatric blood pressure (BP) measurements, and diagnosing hypertension is critical. However, because of environmental issues, other alternatives are needed. Noninvasive BP measurement devices are largely divided into auscultatory and oscillometric types. The aneroid sphygmomanometer, the currently used auscultatory method, is inferior to MS in terms of limitations such as validation and regular calibration and difficult to apply to infants, in whom Korotkoff sounds are not audible. The oscillometric method uses an automatic device that eliminates errors caused by human observers and has the advantage of being easy to use; however, owing to its measurement accuracy issues, the development of an international validation protocol for children is important. The hybrid method, which combines the auscultatory and electronic methods, solves some of these problems by eliminating the observer bias of terminal digit preference while maintaining measurement accuracy; however, the auscultatory method remains limited. As the age-related characteristics of the pediatric group are heterogeneous, it is necessary to reconsider the appropriate BP measurement method suitable for this indication. In addition, the mobile application-based BP measurement market is growing rapidly with the development of smartphone applications. Although more research is still needed on their accuracy, many experts expect that mobile application-based BP measurement will effectively reduce medical costs due to increased ease of access and early BP management.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제6권7호
• /
• pp.329-336
• /
• 2017

웹 앱은 빠르게 진화하며 나날이 복잡해지고 있다. 이에 따라 웹 앱의 검증(validation & verification)이 웹 앱의 개발 및 유지보수를 위해 더욱 중요해 지고 있다. 효율적인 검증을 위해서는 웹 앱 실행 시 일어나는 웹 컴포넌트 사이의 협력 과정(collaboration)에 대한 이해가 선행되어야 한다. 이를 위해 본 논문에서는 웹 페이지 요청 시 페이지 생성을 위해 실행되는 웹 컴포넌트와 이들의 협력 과정을 자동적으로 추출하는 기법을 제안한다. 제안하는 기법은 복잡한 웹 개발 언어 및 기술에 덜 의존하는 동적 기법이며 웹 앱 소스를 블랙박스로 보고 웹 앱의 기능 변화 없이 협력 과정을 추출한다. 오픈 소스 웹 앱에 적용하는 실험을 통해 제안하는 기법의 유효성을 확인할 수 있다.