• ETRI Journal
• /
• 제37권4호
• /
• pp.780-786
• /
• 2015

This paper describes an audio source separation that is based on nonnegative matrix factorization (NMF) and expectation maximization (EM). For stable and highperformance separation, an effective auxiliary source separation that extracts source residuals and reprojects them onto proper sources is proposed by taking into account an ambiguous region among sources and a source's refinement. Specifically, an additional NMF (model) is designed for the ambiguous region - whose elements are not easily represented by any existing or predefined NMFs of the sources. The residual signal can be extracted by inserting the aforementioned model into the NMF-EM-based audio separation. Then, it is refined by the weighted parameters of the separation and reprojected onto the separated sources. Experimental results demonstrate that the proposed scheme (outlined above) is more stable and outperforms existing algorithms by, on average, 4.4 dB in terms of the source distortion ratio.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2003년도 Proceedings of ACRS 2003 ISRS
• /
• pp.172-174
• /
• 2003

Using MODIS data and several different compositing algorithms utilizing the average cloud free days in a compositing period, maximum ndvi, or dual maximum NDVI/minimum blue, multi resolution composites (250m, 500m, 1km) have been produced for Southeast Asia, with spectral bands ranging from the visible to short-wave infrared with a single band in the thermal (for land and sea surface temperature). A total of nine composites have been produced for the months of May and August in 2003, including blue, green, red, NIR, three in the SWIR, and several to specifically monitor vegetation health.

• 전자공학회논문지B
• /
• 제33B권12호
• /
• pp.62-70
• /
• 1996

Image restoration is the process which estimates the original image form the blurred image observed by the non-ideal imaging system with additivenoise. According to the regularized approach, the resotred image can be obtained by iterative methods or the constrained least square error(CLS) filter. Among those retoratin methods, despite of many advantages, iterative iamge restoration is limited in use because of slow convergence. In the present paper, fast iterative image restoration algorithms based on preconditoning are proposed. The preconditioner can be obtained by using the characteristics finite impulse response (FIR) filter structure.

• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2004년도 추계학술대회
• /
• pp.714-719
• /
• 2004

This paper presents two numerical algorithms for registration of cross-sectional medical images such as CT (Computerized Tomography) or MRI (Magnetic Resonance Imaging) by using geometrical information from helix or line fiducials. The registration algorithms are designed to be used for a surgical robot working inside cavities of human body. A cylindrical device with a combination of line and helix fiducials were also devised and is supposed to be attached to the end-effector of surgical robot. The algorithms and the fiducial pattern were tested in various computer-simulated situations, and the results indicate excellent overall registration accuracy.

• Korean Journal of Radiology
• /
• 제22권3호
• /
• pp.334-343
• /
• 2021

Objective: We aimed to develop a prediction model for diagnosing severe aortic stenosis (AS) using computed tomography (CT) radiomics features of aortic valve calcium (AVC) and machine learning (ML) algorithms. Materials and Methods: We retrospectively enrolled 408 patients who underwent cardiac CT between March 2010 and August 2017 and had echocardiographic examinations (240 patients with severe AS on echocardiography [the severe AS group] and 168 patients without severe AS [the non-severe AS group]). Data were divided into a training set (312 patients) and a validation set (96 patients). Using non-contrast-enhanced cardiac CT scans, AVC was segmented, and 128 radiomics features for AVC were extracted. After feature selection was performed with three ML algorithms (least absolute shrinkage and selection operator [LASSO], random forests [RFs], and eXtreme Gradient Boosting [XGBoost]), model classifiers for diagnosing severe AS on echocardiography were developed in combination with three different model classifier methods (logistic regression, RF, and XGBoost). The performance (c-index) of each radiomics prediction model was compared with predictions based on AVC volume and score. Results: The radiomics scores derived from LASSO were significantly different between the severe AS and non-severe AS groups in the validation set (median, 1.563 vs. 0.197, respectively, p < 0.001). A radiomics prediction model based on feature selection by LASSO + model classifier by XGBoost showed the highest c-index of 0.921 (95% confidence interval [CI], 0.869-0.973) in the validation set. Compared to prediction models based on AVC volume and score (c-indexes of 0.894 [95% CI, 0.815-0.948] and 0.899 [95% CI, 0.820-0.951], respectively), eight and three of the nine radiomics prediction models showed higher discrimination abilities for severe AS. However, the differences were not statistically significant (p > 0.05 for all). Conclusion: Models based on the radiomics features of AVC and ML algorithms may perform well for diagnosing severe AS, but the added value compared to AVC volume and score should be investigated further.

• 대한원격탐사학회지
• /
• 제24권1호
• /
• pp.65-78
• /
• 2008

This study compares the relative accuracy and consistency of four split-window land surface temperature (LST) algorithms (Becker and Li, Kerr et ai., Price, Ulivieri et al.) using 24 sets of Terra (Aqua)/Moderate Resolution Imaging Spectroradiometer (MODIS) data, observed ground grass temperature and air temperature over South Korea. The effective spectral emissivities of two thermal infrared bands have been retrieved by vegetation coverage method using the normalized difference vegetation index. The intercomparison results among the four LST algorithms show that the three algorithms (Becker-Li, Price, and Ulivieri et al.) show very similar performances. The LST estimated by the Becker and Li's algorithm is the highest, whereas that by the Kerr et al.'s algorithm is the lowest without regard to the geographic locations and seasons. The performance of four LST algorithms is significantly better during cold season (night) than warm season (day). And the LST derived from Terra/MODIS is closer to the observed LST than that of Aqua/MODIS. In general, the performances of Becker-Li and Ulivieri et al algorithms are systematically better than the others without regard to the day/night, seasons, and satellites. And the root mean square error and bias of Ulivieri et al. algorithm are consistently less than that of Becker-Li for the four seasons.

• 전자공학회논문지
• /
• 제52권4호
• /
• pp.145-155
• /
• 2015

디지털 영상 처리 분야에서 잡음 제거는 활발히 연구되어오고 있으며, 최근에는 블록 기반의 잡음 제거 알고리즘이 널리 사용되고 있다. 저계수행렬 근사 기반의 잡음 제거 알고리즘은 WNNM(Weighted Nuclear Norm Minimization)과 블록 기반의 잡음 제거 방법을 적용하여 잡음 제거 방법에 대한 잠재력을 입증했다. 그러나 저계수행렬 근사 기반의 잡음 제거 알고리즘은 영상복원 과정에서 의도치 않은 아티팩트를 발생시킨다. 본 논문에서는 STFT(Short Time Fourier Transform)을 이용해 영상을 분석하여 기존 알고리즘에서 발생하는 아티팩트를 적응적으로 최소화시키는 방법을 제안한다. 성능을 확인하기 위해 다양한 잡음정도를 포함하는 영상에서 실험하였으며, 비교를 통해 제안된 방법이 기존의 잡음 제거 알고리즘보다 효과적으로 잡음을 제거하는 것을 확인했다.

• 지구물리와물리탐사
• /
• 제14권3호
• /
• pp.191-202
• /
• 2011

역시간 구조보정은 양방향 파동방정식을 이용하여 지하 구조를 영상화하는 정확성이 높은 구조보정 기법으로, 최근까지 주로 지하 매질을 등방성 매질로 가정하고 실시되어 왔다. 그러나 실제 지하매질은 이방성을 띠는 경우가 많으므로 역시간 구조보정 시 이를 고려한다면 영상의 정확도가 향상될 것으로 기대된다. 이에 본 연구에서는 대표적인 이방성매질인 VTI 및 TTI 매질에서의 역시간 구조보정 기술을 개발하였다. 이를 위하여 탄성 파동방정식을 음향 파동방정식으로 근사시킨 유사음향 파동방정식을 고차근사 유한차분법에 기반하여 모델링하였다. 역시간 구조보정 알고리듬으로는 상호상관을 이용한 영상화 기법과 가상 송신원을 이용한 영상화 기법을 모두 사용하였다. 완성된 알고리듬을 벤치마킹 모델인 Hess VTI 및 BP TTI 모델에 적용해본 결과, 본 연구에서 개발한 역시간 구조보정 알고리듬을 통하여 매질의 이방성을 고려해주었을 때 결과단면의 정확도가 크게 향상되는 것을 확인할 수 있었다.

• Journal of Gastric Cancer
• /
• 제23권3호
• /
• pp.388-399
• /
• 2023

Gastric cancer remains a significant global health concern, coercing the need for advancements in imaging techniques for ensuring accurate diagnosis and effective treatment planning. Artificial intelligence (AI) has emerged as a potent tool for gastric-cancer imaging, particularly for diagnostic imaging and body morphometry. This review article offers a comprehensive overview of the recent developments and applications of AI in gastric cancer imaging. We investigated the role of AI imaging in gastric cancer diagnosis and staging, showcasing its potential to enhance the accuracy and efficiency of these crucial aspects of patient management. Additionally, we explored the application of AI body morphometry specifically for assessing the clinical impact of gastrectomy. This aspect of AI utilization holds significant promise for understanding postoperative changes and optimizing patient outcomes. Furthermore, we examine the current state of AI techniques for the prognosis of patients with gastric cancer. These prognostic models leverage AI algorithms to predict long-term survival outcomes and assist clinicians in making informed treatment decisions. However, the implementation of AI techniques for gastric cancer imaging has several limitations. As AI continues to evolve, we hope to witness the translation of cutting-edge technologies into routine clinical practice, ultimately improving patient care and outcomes in the fight against gastric cancer.

• 전기학회논문지
• /
• 제60권6호
• /
• pp.1209-1214
• /
• 2011

Photoacoustics has been broadly studied in biomedicine, for both human and small animal tissues. Photoacoustics uniquely combines the absorption contrast of light or radio frequency waves with ultrasound resolution. Moreover, it is non-ionizing and non-invasive, and is the fastest growing new biomedical method, with clinical applications on the way. This paper provides a brief recap of recent developments in photoacoustics in biomedicine, from basic principles to applications. The emphasized areas include the new imaging modalities as well as translational research topics. A primary PA application in biomedicine is photoacoustic tomography (PAT). The past decade has seen fast developments in both theoretical reconstruction algorithms and innovative imaging techniques, and PAT has been implemented in imaging different tissues, from centimeter-large breast tumors to several micrometer-large single red blood cels (RBC). PAT now provides structural, functional and molecular imaging. Overall, PA techniques for biomedicine are maturing. They have been widely used to study both animal and human tissues. Recently, more and more research focuses on clinical applications. Commercialized PA systems are expected to be available in the near future, and wide clinical PA applications are foreseen.