Nabil Bouhouch - Academia.edu (original) (raw)
Papers by Nabil Bouhouch
United European Gastroenterology Journal, 2019
Background and objectivePost‐endoscopic retrograde cholangiopancreatography (ERCP) pancreatitis (... more Background and objectivePost‐endoscopic retrograde cholangiopancreatography (ERCP) pancreatitis (PEP) is the most prevalent complication after ERCP with an incidence of 3.5%. PEP severity is classified according to either the consensus criteria or the revised Atlanta criteria. In this international cohort study we investigated which classification is the strongest predictor of PEP‐related mortality.MethodsWe reviewed 13,384 consecutive ERCPs performed between 2012 and 2017 in eight hospitals. We gathered data on all pancreatitis‐related adverse events and compared the predictive capabilities of both classifications. Furthermore, we investigated the correlation between the two classifications and identified reasons underlying length of stay.ResultsThe total sample consisted of 387 patients. The revised Atlanta criteria have a higher sensitivity (100 vs. 55%), specificity (98 vs. 72%) and positive predictive value (58 vs. 5%). There is a significant difference (p < 0.001) between t...
1 Feature selection based on SVM significance maps fo r classification of dementia Esther Bron*, ... more 1 Feature selection based on SVM significance maps fo r classification of dementia Esther Bron*, Marion Smits, John van Swieten, Wiro Niessen, and Stefan Klein 1 Biomedical Imaging Group Rotterdam, Departments of Medical Informatics and Radiology, Erasmus MC, Rotterdam, The Netherlands 2 Department of Radiology, Erasmus MC, Rotterdam, The Netherlands 3 Department of Neurology, Erasmus MC, Rotterdam, The Netherlands 4 Imaging Physics, Applied Sciences, Delft University of Technology, The Netherlands *Corresponding author: e.bron@erasmusmc.nl Support vector machine significance maps (SVM p-maps) previously showed clusters of significantly different voxels in dementia-related brain regions. We propose a novel feature selection method for classification of dementia based on these p-maps. In our approach, the SVM p-maps are calculated on the training set with a time-efficient analytic approximation. The features that are most significant on the p-map are selected for classification with ...
2014 IEEE International Ultrasonics Symposium, 2014
Being an established marker for cancer growth, neovascularization is probed by several approaches... more Being an established marker for cancer growth, neovascularization is probed by several approaches with the aim of cancer imaging. Recently, analysis of the dispersion kinetics of ultrasound contrast agents (UCAs) has been proposed as a promising approach for localizing neovascularization in prostate cancer. Determined by multipath trajectories through the microvasculature, dispersion enables characterization of the microvascular architecture and, therefore, localization of cancer neovascularization. Analysis of the spatiotemporal similarity among indicator dilution curves (IDCs) measured at each pixel by dynamic contrast-enhanced ultrasound imaging has been proposed to assess the local dispersion kinetics of UCAs. Only linear similarity measures, such as temporal correlation or spectral coherence, have been used up until now. Here we investigate the use of nonlinear similarity measures by estimation of the statistical dependency between IDCs. In particular, dispersion maps are generated by estimation of the mutual information between IDCs. The method is tested for prostate cancer localization and the results compared with the histology results in 15 patients referred for radical prostatectomy because of biopsy-proven prostate cancer. With sensitivity and specificity equal to 84% and 85%, respectively, and receiver operating characteristic curve area equal to 0.92, our results outperformed those obtained by any other parameter, motivating further validation with a larger dataset and with other types of cancer.
IEEE Transactions on Biomedical Engineering, 2016
The role of angiogenesis in cancer growth has stimulated research aimed at non-invasive cancer de... more The role of angiogenesis in cancer growth has stimulated research aimed at non-invasive cancer detection by blood perfusion imaging. Recently, contrast ultrasound dispersion imaging was proposed as an alternative method for angiogenesis imaging. After the intravenous injection of an ultrasoundcontrast- agent bolus, dispersion can be indirectly estimated from the local similarity between neighboring time-intensity curves (TICs) measured by ultrasound imaging. Up until now, only linear similarity measures have been investigated. Motivated by the promising results of this approach in prostate cancer (PCa), we developed a novel dispersion estimation method based on mutual information, thus including nonlinear similarity, to further improve its ability to localize PCa. First, a simulation study was performed to establish the theoretical link between dispersion and mutual information. Next, the method&amp;amp;amp;amp;amp;amp;amp;amp;amp;#39;s ability to localize PCa was validated in vivo in 23 patients (58 datasets) referred for radical prostatectomy by comparison with histology. A monotonic relationship between dispersion and mutual information was demonstrated. The in-vivo study resulted in a receiver operating characteristic (ROC) curve area equal to 0.77, which was superior (p=0.21-0.24) to that obtained by linear similarity measures (0.74-0.75) and (p&amp;amp;amp;amp;amp;amp;amp;amp;amp;lt;0.05) to that by conventional perfusion parameters (0.70). Mutual information between neighboring TICs can be used to indirectly estimate contrast dispersion and can lead to more accurate PCa localization. An improved PCa localization method can possibly lead to better grading and staging of tumors, and support focal-treatment guidance. Moreover, future employment of the method in other types of angiogenic cancer can be considered.
United European Gastroenterology Journal, 2019
Background and objectivePost‐endoscopic retrograde cholangiopancreatography (ERCP) pancreatitis (... more Background and objectivePost‐endoscopic retrograde cholangiopancreatography (ERCP) pancreatitis (PEP) is the most prevalent complication after ERCP with an incidence of 3.5%. PEP severity is classified according to either the consensus criteria or the revised Atlanta criteria. In this international cohort study we investigated which classification is the strongest predictor of PEP‐related mortality.MethodsWe reviewed 13,384 consecutive ERCPs performed between 2012 and 2017 in eight hospitals. We gathered data on all pancreatitis‐related adverse events and compared the predictive capabilities of both classifications. Furthermore, we investigated the correlation between the two classifications and identified reasons underlying length of stay.ResultsThe total sample consisted of 387 patients. The revised Atlanta criteria have a higher sensitivity (100 vs. 55%), specificity (98 vs. 72%) and positive predictive value (58 vs. 5%). There is a significant difference (p < 0.001) between t...
1 Feature selection based on SVM significance maps fo r classification of dementia Esther Bron*, ... more 1 Feature selection based on SVM significance maps fo r classification of dementia Esther Bron*, Marion Smits, John van Swieten, Wiro Niessen, and Stefan Klein 1 Biomedical Imaging Group Rotterdam, Departments of Medical Informatics and Radiology, Erasmus MC, Rotterdam, The Netherlands 2 Department of Radiology, Erasmus MC, Rotterdam, The Netherlands 3 Department of Neurology, Erasmus MC, Rotterdam, The Netherlands 4 Imaging Physics, Applied Sciences, Delft University of Technology, The Netherlands *Corresponding author: e.bron@erasmusmc.nl Support vector machine significance maps (SVM p-maps) previously showed clusters of significantly different voxels in dementia-related brain regions. We propose a novel feature selection method for classification of dementia based on these p-maps. In our approach, the SVM p-maps are calculated on the training set with a time-efficient analytic approximation. The features that are most significant on the p-map are selected for classification with ...
2014 IEEE International Ultrasonics Symposium, 2014
Being an established marker for cancer growth, neovascularization is probed by several approaches... more Being an established marker for cancer growth, neovascularization is probed by several approaches with the aim of cancer imaging. Recently, analysis of the dispersion kinetics of ultrasound contrast agents (UCAs) has been proposed as a promising approach for localizing neovascularization in prostate cancer. Determined by multipath trajectories through the microvasculature, dispersion enables characterization of the microvascular architecture and, therefore, localization of cancer neovascularization. Analysis of the spatiotemporal similarity among indicator dilution curves (IDCs) measured at each pixel by dynamic contrast-enhanced ultrasound imaging has been proposed to assess the local dispersion kinetics of UCAs. Only linear similarity measures, such as temporal correlation or spectral coherence, have been used up until now. Here we investigate the use of nonlinear similarity measures by estimation of the statistical dependency between IDCs. In particular, dispersion maps are generated by estimation of the mutual information between IDCs. The method is tested for prostate cancer localization and the results compared with the histology results in 15 patients referred for radical prostatectomy because of biopsy-proven prostate cancer. With sensitivity and specificity equal to 84% and 85%, respectively, and receiver operating characteristic curve area equal to 0.92, our results outperformed those obtained by any other parameter, motivating further validation with a larger dataset and with other types of cancer.
IEEE Transactions on Biomedical Engineering, 2016
The role of angiogenesis in cancer growth has stimulated research aimed at non-invasive cancer de... more The role of angiogenesis in cancer growth has stimulated research aimed at non-invasive cancer detection by blood perfusion imaging. Recently, contrast ultrasound dispersion imaging was proposed as an alternative method for angiogenesis imaging. After the intravenous injection of an ultrasoundcontrast- agent bolus, dispersion can be indirectly estimated from the local similarity between neighboring time-intensity curves (TICs) measured by ultrasound imaging. Up until now, only linear similarity measures have been investigated. Motivated by the promising results of this approach in prostate cancer (PCa), we developed a novel dispersion estimation method based on mutual information, thus including nonlinear similarity, to further improve its ability to localize PCa. First, a simulation study was performed to establish the theoretical link between dispersion and mutual information. Next, the method&amp;amp;amp;amp;amp;amp;amp;amp;amp;#39;s ability to localize PCa was validated in vivo in 23 patients (58 datasets) referred for radical prostatectomy by comparison with histology. A monotonic relationship between dispersion and mutual information was demonstrated. The in-vivo study resulted in a receiver operating characteristic (ROC) curve area equal to 0.77, which was superior (p=0.21-0.24) to that obtained by linear similarity measures (0.74-0.75) and (p&amp;amp;amp;amp;amp;amp;amp;amp;amp;lt;0.05) to that by conventional perfusion parameters (0.70). Mutual information between neighboring TICs can be used to indirectly estimate contrast dispersion and can lead to more accurate PCa localization. An improved PCa localization method can possibly lead to better grading and staging of tumors, and support focal-treatment guidance. Moreover, future employment of the method in other types of angiogenic cancer can be considered.