Automatic detection of abnormal vascular cross-sections based on density level detection and support vector machines

Zuluaga, María A.; Magnin, Isabelle E.; Hoyos, Marcela Hernández; Leyton, Edgar J. F. Delgado; Lozano, Fernando Restoy; Orkisz, Maciej

doi:10.1007/s11548-010-0494-8

Cited by 33 publications

(45 citation statements)

References 21 publications

(30 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…From this information we have computed the BER=0.164. While, our new proposal gives a lower TPR=0.838, it has a higher TNR=0.867 that can be explained by the fact that our novel method does not misclassify bifurcations, contrary to the one in [5]. Our lower BER=0.142 confirms that our overall performance is better.…”

Section: Patient Datamentioning

confidence: 60%

“…However, we used a different selection strategy based on the empirical risk R minimization. Four metrics calculated in cross-sections orthogonal to the vessel centerline (Concentric rings [5], Core, Hessian eigenvalues and Flux [9]) were kept.…”

Section: Featuresmentioning

confidence: 99%

“…The same definition of TP has been used in [5], so a direct comparison of the results can be done. In that work, a TPR=0.860 and TNR=0.812 have been reported.…”

Section: Patient Datamentioning

confidence: 99%

“…A first attempt to use an unsupervised scheme has been proposed in [5]. However, it failed to distinguish bifurcations from actual lesions.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Learning from Only Positive and Unlabeled Data to Detect Lesions in Vascular CT Images

Zuluaga

Hush

Leyton

et al. 2011

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Abstract. Detecting vascular lesions is an important task in the diagnosis and follow-up of the coronary heart disease. While most existing solutions tackle calcified and non-calcified plaques separately, we present a new algorithm capable of detecting both types of lesions in CT images. It builds up on a semi-supervised classification framework, in which the training set is made of both unlabeled data and a small amount of data labeled as normal. Our method takes advantage of the arrival of newly acquired data to re-train the classifier and improve its performance. We present results on synthetic data and on datasets from 15 patients. With a small amount of labeled training data our method achieved a 89.8% true positive rate, which is comparable to state-of-the-art supervised methods, and the performance can improve after additional iterations.

show abstract

Section: Patient Datamentioning

confidence: 60%

Section: Featuresmentioning

confidence: 99%

“…The same definition of TP has been used in [5], so a direct comparison of the results can be done. In that work, a TPR=0.860 and TNR=0.812 have been reported.…”

Section: Patient Datamentioning

confidence: 99%

“…A first attempt to use an unsupervised scheme has been proposed in [5]. However, it failed to distinguish bifurcations from actual lesions.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Learning from Only Positive and Unlabeled Data to Detect Lesions in Vascular CT Images

Zuluaga

Hush

Leyton

et al. 2011

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

show abstract

“…Additionally, it is very expensive to collect annotated data that are representative of all types of lesions, as the appearance of the lesions may vary a lot. A first attempt using an unsupervised scheme to detect the lesions regardless the plaque type has been proposed in [17]. It achieved a good specificity, but a lower sensitivity since it underestimated the extent of the lesions.…”

Section: Introductionmentioning

confidence: 99%

Feature selection based on empirical-risk function to detect lesions in vascular computed tomography

Zuluaga

Hoyos

Orkisz

2014

IRBM

View full text Add to dashboard Cite

Current Modeling Methods Used in QSAR/QSPR

Yee

Wei

2012

Statistical Modelling of Molecular Descriptors in QSAR/QSPR

View full text Add to dashboard Cite

j1 diagnostic abilities. They can be used to predict the biological activity (e.g., IC 50 ) or class (e.g., inhibitor versus noninhibitors) of compounds before the actual biological testing. They can also be used in the analysis of structural characteristics that can give rise to the properties of interest.As illustrated in Figure 1.1, developing QSAR models starts with the collection of data for the property of interest while taking into consideration the quality of the data. It is necessary to exclude low-quality data as they will lower the quality of the model. Following that, representation of the collected molecules is done through the use of features, namely molecular descriptors, which describes important information of the molecules. There are many types of molecular descriptors but not all will be useful for a particular modeling task. Thus, uninformative or redundant molecular descriptors should be removed before the modeling process. Subsequently, for tuning and validation of the QSAR model, the full data set is divided into a training set and a testing set prior to learning.During the learning process, various modeling methods like multiple linear regression, logistic regression, and machine learning methods are used to build models that describe the empirical relationship between the structure and property of interest. The optimal model is obtained by searching for the optimal modeling parameters and feature subset simultaneously. This finalized model built from the optimal parameters will then undergo validation with a testing set to ensure that the model is appropriate and useful. Figure 1.1 General workflow of developing a QSAR model. 2j 1 Current Modeling Methods Used in QSAR/QSPR Figure 1.3 A simple structure showing the three layers of an artificial neural network. 6j 1 Current Modeling Methods Used in QSAR/QSPR Figure 1.4 GRNN is a neural network with four layers.

show abstract

Automatic detection of abnormal vascular cross-sections based on density level detection and support vector machines

Cited by 33 publications

References 21 publications

Learning from Only Positive and Unlabeled Data to Detect Lesions in Vascular CT Images

Learning from Only Positive and Unlabeled Data to Detect Lesions in Vascular CT Images

Feature selection based on empirical-risk function to detect lesions in vascular computed tomography

Current Modeling Methods Used in QSAR/QSPR

Contact Info

Product

Resources

About