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

Intracranial hemorrhage (ICH) is a life-threatening emergency with high rates of mortality and morbidity. Rapid and accurate detection of ICH is crucial for patients to get a timely treatment. In order to achieve the automatic diagnosis of ICH, most deep learning models rely on huge amounts of slice labels for training. Unfortunately, the manual annotation of CT slices by radiologists is time-consuming and costly. To diagnose ICH, in this work, we propose to use an attention-based multiple instance learning (Att-MIL) approach implemented through the combination of an attention-based convolutional neural network (Att-CNN) and a variational Gaussian process for multiple instance learning (VGPMIL). Only labels at scan-level are necessary for training. Our method (a) trains the model using scan labels and assigns each slice with an attention weight, which can be used to provide slice-level predictions, and (b) uses the VGPMIL model based on low-dimensional features extracted by the Att-CNN to obtain improved predictions both at slice and scan levels. To analyze the performance of the proposed approach, our model has been trained on 1150 scans from an RSNA dataset and evaluated on 490 scans from an external CQ500 dataset. Our method outperforms other methods using the same scan-level training and is able to achieve comparable or even better results than other methods relying on slice-level annotations.

Combining Attention-based Multiple Instance Learning and Gaussian Processes for CT Hemorrhage Detection

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 image restoration problems. We use a spatially varying image prior utilizing a Gamma-Normal hyperprior distribution on the local precision parameters. This kind of hyperprior distribution, which to our knowledge has not been used before in image restoration, allows for the incorporation of information on local as well as global image variability, models correlation of the local precision parameters and is a conjugate hyperprior to the image model used in the paper. The proposed restoration technique is compared with other image restoration approaches, demonstrating its improved performance.

/pdf/local-bayesian-image-restoration-using-variational-methods-5ae1baqnzp.pdf

Local Bayesian image restoration using variational methods and Gamma-Normal distributions

In this paper a new image prior is introduced and used in image restoration. This prior is based on products of spatially weighted Total Variations (TV). These spatial weights provide this prior with the flexibility to better capture local image features than previous TV based priors. Bayesian inference is used for image restoration with this prior via the variational approximation. The proposed algorithm is fully automatic in the sense that all necessary parameters are estimated from the data. Numerical experiments are shown which demonstrate that image restoration based on this prior compares favorably with previous state-of-the-art restoration algorithms.

/pdf/variational-bayesian-inference-image-restoration-using-a-4j0q4jm2xf.pdf

Variational Bayesian inference image restoration using a product of total variation-like image priors

Antecedentes: Una de las estrategias en quimioprevencion se basa en utilizar productos naturales para inducir el metabolismo y de esta manera inactivar sustancias toxicas. Los inductores monofuncionales inducen los enzimas de Fase II, como las glutation S-transferasas (GSTs) y la quinona oxido-reductasa (NQO1), sin modificar los sistemas oxidativos de Fase 1. En la induccion de los enzimas de Fase II esta involucrado el elemento regulador genetico de respuesta a antioxidantes (ARE).
Objetivo: El objetivo de este trabajo ha sido realizar un estudio descriptivo in vitro de la capacidad de induccion metabolica de las verduras (15 verduras seleccionadas) que se consumen habitualmente.
Material y metodo: Los extractos de verduras se ensayan en dos lineas celulares: Hepa lclc7 y PE transfectada de manera estable con el plasmido ARE-luc+ (AREPE). Para las Hepa lclc7 se ha valorado la capacidad de estos productos de inducir la NQO1, GST y GSH. Para la linea celular AREPE se ha utilizado un ensayo luminometrico.
Resultados: Se considera extractos activos a aquellos que incrementan la actividad enzimatica o la concentracion de GSH mas de 1,5 veces (OR>_1,5) a la dosis utilizada de 8 mg/ml. Para la actividad NQO1, las verduras mas activas son el broccoli (OR=5,5),calcot" (Allium cepa L) (OR=4,76), coliflor (OR=2,88), coles de bruselas (OR=2,3), acelgas (OR=2,16) y col (OR=2). Tambien el calcot, induce significativamente la GST (OR=2,1) y la sintesis de GSH (OR=2,4). Los extractos con una OR mas elevada (OR>2,5) se ensayaron en la nueva linea celular AREPE, confirmandose como inductores: brocoli (OR=3,5), calcot (OR=4,8) y coliflor (OR=1,8). Estos resultados son muy similares a los descritos para las verduras consumidas en USA, anadiendo como novedad al calcot como producto autoctono de Cataluna. Ahora hay que confirmar estos resultados con lineas celulares modificadas para descartar la bifuncionalidad de los extractos activos.

Capacidad de inducción metabólica de las verduras más consumidas habitualmente

Many real classification tasks are oriented to sequence (neighbor) labeling, that is, assigning a label to every sample of a signal while taking into account the sequentiality (or neighborhood) of the samples. This is normally approached by first filtering the data and then performing classification. In consequence, both processes are optimized separately, with no guarantee of global optimality. In this work we utilize Bayesian modeling and inference to jointly learn a classifier and estimate an optimal filterbank. Variational Bayesian inference is used to approximate the posterior distributions of all unknowns, resulting in an iterative procedure to estimate the classifier parameters and the filterbank coefficients. In the experimental section we show, using synthetic and real data, that the proposed method compares favorably with other classification/filtering approaches, without the need of parameter tuning.

/pdf/learning-filters-in-gaussian-process-classification-problems-1yhjj5lerk.pdf

Rafael Molina

Papers

Combining Attention-based Multiple Instance Learning and Gaussian Processes for CT Hemorrhage Detection

Local Bayesian image restoration using variational methods and Gamma-Normal distributions

Variational Bayesian inference image restoration using a product of total variation-like image priors

Capacidad de inducción metabólica de las verduras más consumidas habitualmente

Learning filters in Gaussian process classification problems