다중혈관 관상동맥 환자에서 y-문합을 이용하여 양쪽 내흉동맥만을 사용한 우회술의 조기 성적

Clustering algorithms are attractive for the task of class identification in spatial databases. However, the application to large spatial databases rises the following requirements for clustering algorithms: minimal requirements of domain knowledge to determine the input parameters, discovery of clusters with arbitrary shape and good efficiency on large databases. The well-known clustering algorithms offer no solution to the combination of these requirements. In this paper, we present the new clustering algorithm DBSCAN relying on a density-based notion of clusters which is designed to discover clusters of arbitrary shape. DBSCAN requires only one input parameter and supports the user in determining an appropriate value for it. We performed an experimental evaluation of the effectiveness and efficiency of DBSCAN using synthetic data and real data of the SEQUOIA 2000 benchmark. The results of our experiments demonstrate that (1) DBSCAN is significantly more effective in discovering clusters of arbitrary shape than the well-known algorithm CLAR-ANS, and that (2) DBSCAN outperforms CLARANS by a factor of more than 100 in terms of efficiency.

A density-based algorithm for discovering clusters a density-based algorithm for discovering clusters in large spatial databases with noise

Clustering algorithms are attractive for the task of class identification in spatial databases. However, the application to large spatial databases rises the following requirements for clustering algorithms: minimal requirements of domain knowledge to determine the input parameters, discovery of clusters with arbitrary shape and good efficiency on large databases. The well-known clustering algorithms offer no solution to the combination of these requirements. In this paper, we present the new clustering algorithm DBSCAN relying on a density-based notion of clusters which is designed to discover clusters of arbitrary shape. DBSCAN requires only one input parameter and supports the user in determining an appropriate value for it. We performed an experimental evaluation of the effectiveness and efficiency of DBSCAN using synthetic data and real data of the SEQUOIA 2000 benchmark. The results of our experiments demonstrate that (1) DBSCAN is significantly more effective in discovering clusters of arbitrary shape than the well-known algorithm CLARANS, and that (2) DBSCAN outperforms CLARANS by a factor of more than 100 in terms of efficiency.

/pdf/a-density-based-algorithm-for-discovering-clusters-in-large-1o5u8sf38m.pdf

A density-based algorithm for discovering clusters in large spatial Databases with Noise

[신간의 별자리x] 우리/미술, 그리고 ‘슬픔의 박물관’

Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

While high and ultra high definition displays are becoming popular, most of the available content has been acquired at much lower resolutions. In this work we propose to pseudo-invert with regularization the image formation model using GANs and perceptual losses. Our model, which does not require the use of motion compensation, utilizes explicitly the low resolution image formation model and additionally introduces two feature losses which are used to obtain perceptually improved high resolution images. The experimental validation shows that our approach outperforms current video super resolution learning based models.

Gan-Based Video Super-Resolution With Direct Regularized Inversion of the Low-Resolution Formation Model

In this paper we consider the problem of reconstructing a high resolution image from a set of undersampled and degraded frames, all of them obtained from high resolution images with unknown shifting displacements between them. We derive an iterative method to estimate the unknown shifts and the high resolution image given the low resolution observations. Finally, the proposed method is tested on real images.

/pdf/estimation-of-high-resolution-images-and-registration-u6if8oy5su.pdf

Estimation of High Resolution Images and Registration Parameters from Low Resolution Observations

In this paper we present a new Bayesian methodology for the restoration of blurred and noisy images. Bayesian methods rely on image priors that encapsulate prior image knowledge and avoid the ill-posedness of the image restoration problems. Some of these priors depend on global variance parameters, unable to account for local characteristics. Here we first use variational methods to approximate probability posterior distributions for the global model to later use those distributions to define local and more realistic image models which lead to better restored images as it is shown in the experimental section.

/pdf/from-global-to-local-bayesian-parameter-estimation-in-image-39o1qqsz5r.pdf

From Global to Local Bayesian Parameter Estimation in Image Restoration using Variational Distribution Approximations

Background: The description of a new method for the measurement of complexed prostate-specific antigen (cPSA) offers a new approach to the diagnosis of prostate cancer. Patients and Methods: We measured PSA (Hybritech and Bayer), free PSA (Hybritech) and complexed PSA (Bayer) in 72 patients with prostate cancer and 128 with benign prostate hyperplasia. Results and Conclusion: We found an increase of sensitivity using 2.5 and 7 ng/mL as cut-offs for cPSA in relation to total PSA using as cut- offs 4 and 10 ng/mL (96 and 36% vs. 92 and 35.5%). Similar differences were found for specificity (78% and 31% for cPSA vs. 73% and 29% for total PSA). Therefore, we defined a gray zone for patients with cPSA between 2.5 and 7 ng/mL for which the measurement of the free/complexed PSA ratio saves an important number of negative biopsies maintaining a higher sensitivity. Five years ago, Allard et al. (1) described a new method for the measurement of complexed prostate-specific antigen (cPSA) that improved on former attempts. Background problems observed in earlier assays were eliminated using a monoclonal antibody directed against free PSA (fPSA) that excluded this analyte from the subsequent reaction with anti-total PSA antibodies. The description of the different molecular forms of serum PSA in the early nineties (2,3), modified the traditional diagnostic scheme of prostate cancer. Several studies have demonstrated that the measurement of fPSA in relation to total PSA avoids the number of negative biopsies in the gray zone of PSA, with results between 4 and 10 ng/mL (4-7). Although fPSA has stability problems (8,9), its measurement has had important consequences both in terms of the increased costs and the morbidity associated with the biopsy. Following the description of the Allard group's method, various authors have pointed out advantages of measuring cPSA. Initially, Brawer et al. (10) reported that cPSA offers better results that total PSA in the early diagnosis of prostate cancer. Similar results have been presented by other authors recently (11,12). Nevertheless, the application of cPSA is not so clear in the differential diagnosis between benign prostatic hyperplasia (BPH) and prostate cancer. Our group, in a previous report, showed that cPSA improves the usefulness of total PSA only for patients with PSA around 4 ng/mL. So, in the differential diagnosis between prostate cancer and BPH, we have found that the use of PSA ratios improves the diagnostic accuracy of cPSA (13). We also reported, in a previous retrospective study, that the free/complexed PSA ratio offers the best results of all PSA ratios (14). Now, the aim of the present work was to study the clinical usefulness of cPSA in the differential diagnosis between prostate cancer and BPH, using a prospective evaluation of data. Also, with reference to previous studies, we evaluated the adaptation of cPSA measurement on the Advia Centaur analyzer, which includes certain changes in the master curve standard values.

Complexed prostate-specific antigen for the detection of prostate cancer.

In this paper we present a multichannel image restoration method using compound Gauss Markov random field (CGMRF) models. Information regarding the objects present in the scene is shared via the line process in the CGMRF. Two new iterative algorithms to estimate the underlying multichannel image are presented, which can be considered as extensions of the classical simulated annealing and ICM methods. Experimental results demonstrate the effectiveness of the proposed approach.

/pdf/a-general-multichannel-image-restoration-method-using-225n2vygd6.pdf

Rafael Molina

Papers

Gan-Based Video Super-Resolution With Direct Regularized Inversion of the Low-Resolution Formation Model

Estimation of High Resolution Images and Registration Parameters from Low Resolution Observations

From Global to Local Bayesian Parameter Estimation in Image Restoration using Variational Distribution Approximations

Complexed prostate-specific antigen for the detection of prostate cancer.

A general multichannel image restoration method using compound models