The Experts below are selected from a list of 2187 Experts worldwide ranked by ideXlab platform
Il-lyong Jung - One of the best experts on this subject based on the ideXlab platform.
-
APSIPA - Robust view synthesis under varying illumination conditions using segment-based disparity estimation
2012Co-Authors: Il-lyong JungAbstract:An intermediate view synthesis scheme under varying illumination conditions is proposed in this work. First, we estimate the disparity map based on Cumulative color Histograms. Since the Cumulative Histogram of an image represents the brightness ranks of pixels, the disparity estimation is robust against varying illumination conditions. More specifically, we divide each image into segments, and compute the Cumulative Histogram of the representative values for these segments. Then, we estimate the disparity map based on the similarity of the Cumulative Histograms between stereo images. Second, we transform the colors of stereo images adaptively using the disparity map. Finally, we synthesize intermediate views using the transformed stereo images and the disparity map. Simulation results demonstrate that the proposed algorithm provides better disparity maps and intermediate views under varying illumination conditions than the conventional techniques.
-
VCIP - Histogram-Based stereo matching under varying illumination conditions
2012 Visual Communications and Image Processing, 2012Co-Authors: Il-lyong JungAbstract:A Histogram-based matching algorithm for stereo images captured under different illumination conditions is proposed in this work. The Cumulative Histogram of an image represents the ranks of relative pixel brightness, which are robust to illumination changes. Therefore, we design the matching cost based on the similarity of the Cumulative Histograms of stereo images. As an optional mode, the proposed algorithm can evaluate the Histograms for foreground objects and the background separately to alleviate occlusion artifacts. To determine the disparity of each pixel, the proposed algorithm adaptively aggregates matching costs based on the color similarity and the geometric proximity of neighboring pixels. Then, it refines false disparities at occluded pixels using more reliable disparities of non-occluded pixels. Experimental results demonstrate that the proposed algorithm provides higher quality disparity maps than the conventional methods under varying illumination conditions.
Tae Jin Yun - One of the best experts on this subject based on the ideXlab platform.
-
Prognosis prediction of non-enhancing T2 high signal intensity lesions in glioblastoma patients after standard treatment: application of dynamic contrast-enhanced MR imaging
'Springer Fachmedien Wiesbaden GmbH', 2018Co-Authors: Rihyeon Kim, Seung Hong Choi, Ji Hoon Kim, Tae Jin Yun, Soon-tae Lee, Chul-kee Park, Tae Min Kim, Sun-won Park, Chul-ho Sohn, Sung-hye ParkAbstract:Objectives To identify candidate imaging biomarkers for early disease progression in glioblastoma multiforme (GBM) patients by analysis of dynamic contrast-enhanced (DCE) MR parameters of non-enhancing T2 high signal intensity (SI) lesions. Methods Forty-nine GBM patients who had undergone preoperative DCE MR imaging and received standard treatment were retrospectively included. According to the Response Assessment in Neuro-Oncology criteria, patients were classified into progression (n = 21) or non-progression (n = 28) groups. We analysed the pharmacokinetic parameters of Ktrans, Ve and Vp within non-enhancing T2 high SI lesions of each tumour. The best percentiles of each parameter from Cumulative Histograms were identified by the area under the receiver operating characteristic curve (AUC) and were compared using multivariate stepwise logistic regression. Results For the differentiation of early disease progression, the highest AUC values were found in the 99th percentile of Ktrans (AUC 0.954), the 97th percentile of Ve (AUC 0.815) and the 94th percentile of Vp (AUC 0.786) (all p < 0.05). The 99th percentile of Ktrans was the only significant independent variable from the multivariate stepwise logistic regression (p = 0.002). Conclusions We found that the Ktrans of non-enhancing T2 high SI lesions in GBMpatients holds potential as a candidate prognostic marker in future prospective studies. Key Points • DCE MR imaging provides candidate prognostic marker of GBM after standard treatment. • Cumulative Histogram was applied to include entire nonenhancing T2 high SI lesions. • The 99th percentile value of Ktrans was the most likely potential biomarker. (c) European Society of Radiology 20167
-
gliomas application of Cumulative Histogram analysis of normalized cerebral blood volume on 3 t mri to tumor grading
PLOS ONE, 2013Co-Authors: Hyungjin Kim, Seung Hong Choi, Ji Hoon Kim, Inseon Ryoo, Soo Chin Kim, Jeong A Yeom, Hwaseon Shin, Seung Chai Jung, Leum A Lee, Tae Jin YunAbstract:Background Glioma grading assumes significant importance in that low- and high-grade gliomas display different prognoses and are treated with dissimilar therapeutic strategies. The objective of our study was to retrospectively assess the usefulness of a Cumulative normalized cerebral blood volume (nCBV) Histogram for glioma grading based on 3 T MRI. Methods From February 2010 to April 2012, 63 patients with astrocytic tumors underwent 3 T MRI with dynamic susceptibility contrast perfusion-weighted imaging. Regions of interest containing the entire tumor volume were drawn on every section of the co-registered relative CBV (rCBV) maps and T2-weighted images. The percentile values from the Cumulative nCBV Histograms and the other Histogram parameters were correlated with tumor grades. Cochran’s Q test and the McNemar test were used to compare the diagnostic accuracies of the Histogram parameters after the receiver operating characteristic curve analysis. Using the parameter offering the highest diagnostic accuracy, a validation process was performed with an independent test set of nine patients. Results The 99th percentile of the Cumulative nCBV Histogram (nCBV C99), mean and peak height differed significantly between low- and high-grade gliomas (P = <0.001, 0.014 and <0.001, respectively) and between grade III and IV gliomas (P = <0.001, 0.001 and <0.001, respectively). The diagnostic accuracy of nCBV C99 was significantly higher than that of the mean nCBV (P = 0.016) in distinguishing high- from low-grade gliomas and was comparable to that of the peak height (P = 1.000). Validation using the two cutoff values of nCBV C99 achieved a diagnostic accuracy of 66.7% (6/9) for the separation of all three glioma grades. Conclusion Cumulative Histogram analysis of nCBV using 3 T MRI can be a useful method for preoperative glioma grading. The nCBV C99 value is helpful in distinguishing high- from low-grade gliomas and grade IV from III gliomas.
Mathieu Hatt - One of the best experts on this subject based on the ideXlab platform.
-
Do clinical, histological or immunohistochemical primary tumour characteristics translate into different ^18F-FDG PET/CT volumetric and heterogeneity features in stage II/III breast cancer?
European Journal of Nuclear Medicine and Molecular Imaging, 2015Co-Authors: David Groheux, Mohamed Majdoub, Florent Tixier, Catherine Cheze Rest, Antoine Martineau, Pascal Merlet, Marc Espié, Anne Roquancourt, Elif Hindié, Mathieu HattAbstract:Purpose The aim of this retrospective study was to determine if some features of baseline ^18F-FDG PET images, including volume and heterogeneity, reflect clinical, histological or immunohistochemical characteristics in patients with stage II or III breast cancer (BC). Methods Included in the present retrospective analysis were 171 prospectively recruited patients with stage II/III BC treated consecutively at Saint-Louis hospital. Primary tumour volumes were semiautomatically delineated on pretreatment ^18F-FDG PET images. The parameters extracted included SUV_max, SUV_mean, metabolically active tumour volume (MATV), total lesion glycolysis (TLG) and heterogeneity quantified using the area under the curve of the Cumulative Histogram and textural features. Associations between clinical/histopathological characteristics and ^18F-FDG PET features were assessed using one-way analysis of variance. Areas under the ROC curves (AUC) were used to quantify the discriminative power of the features significantly associated with clinical/histopathological characteristics. Results T3 tumours (>5 cm) exhibited higher textural heterogeneity in ^18F-FDG uptake than T2 tumours (AUC
-
Comparison of tumor volumes and heterogeneity parameters derived from MRGlu maps and static SUV images in 18F-FDG PET
Society of nuclear medicine annual meeting 2012, 2012Co-Authors: Florent Tixier, Mathieu Hatt, Eric Visser, Catherine Cheze-le Rest, Dimitris VisvikisAbstract:Objectives: Metabolically active tumor volume (MATV) and tumor activity distribution heterogeneity parameters derived from 18F-FDG PET images were recently shown to have an impact in patient management. In all of these studies, static FDG-PET images were exclusively considered. However, images of the glucose metabolic rate (MRGlu) obtained from dynamic PET acquisitions may contain more accurate information. The objective of this study was to compare MATV and tumor heterogeneity parameters extracted from these two different types of images. Methods: 20 patients with diagnosed non-small cell lung cancer (NSCLC) were enrolled in this retrospective study. All of these patients underwent a dynamic 18F-FDG PET scan which was acquired prior to therapy. Primary tumor delineation was performed using adaptive thresholding and a fuzzy locally adaptive Bayesian algorithm (FLAB). Image derived parameters considered in this study included MATV, heterogeneity (based on textural features and Cumulative Histogram), coefficient of covariance and tumor lesion glycolysis. Pearson's correlation coefficient and Wilcoxon test were used in the comparison. P-values
Young Jun Choi - One of the best experts on this subject based on the ideXlab platform.
-
prediction of pseudoprogression in patients with glioblastomas using the initial and final area under the curves ratio derived from dynamic contrast enhanced t1 weighted perfusion mr imaging
American Journal of Neuroradiology, 2013Co-Authors: Young Jun ChoiAbstract:BACKGROUND AND PURPOSE: Dynamic contrast-enhanced T1-weighted perfusion MR imaging is much less susceptible to artifacts, and its high spatial resolution allows accurate characterization of the vascular microenvironment of the lesion. The purpose of this study was to test the predictive value of the initial and final area under the time signal-intensity curves ratio derived from dynamic contrast-enhanced perfusion MR imaging to differentiate pseudoprogression from early tumor progression in patients with glioblastomas. MATERIALS AND METHODS: Seventy-nine consecutive patients who showed new or enlarged, contrast-enhancing lesions within the radiation field after concurrent chemoradiotherapy were assessed by use of conventional and dynamic contrast-enhanced perfusion MR imaging. The bimodal Histogram parameters of the area under the time signal-intensity curves ratio, which included the mean area under the time signal-intensity curves ratio at a higher curve (mAUCRH), 3 Cumulative Histogram parameters (AUCR50, AUCR75, and AUCR90), and the area under the time signal-intensity curves ratio at mode (AUCRmode), were calculated and correlated with the final pathologic or clinical diagnosis. The best predictor for differentiation of pseudoprogression from early tumor progression was determined by receiver operating characteristic curve analyses. RESULTS: Seventy-nine study patients were subsequently classified as having pseudoprogression (n=37, 46.8%) or early tumor progression (n=42, 53.2%). There were statistically significant differences of mAUCRH, AUCR50, AUCR75, AUCR90, and AUCRmode between the 2 groups (P CONCLUSIONS: A bimodal Histogram analysis of the area under the time signal-intensity curves ratio derived from dynamic contrast-enhanced perfusion MR imaging can be a potential, noninvasive imaging biomarker for monitoring early treatment response in patients with glioblastomas.
Roman Melnyk - One of the best experts on this subject based on the ideXlab platform.
-
cloudiness images multilevel segmentation by piecewise linear approximation of Cumulative Histogram
International Journal of Computing, 2020Co-Authors: Roman Melnyk, Ruslan Tushnytskyy, Roman KvitAbstract:The Ramer-Douglas-Peucker algorithm for piecewise approximation is used for image multilevel segmentation. The Cumulative Histogram is selected as a function for approximation. The algorithm allows you to determine threshold values of continuous and discrete images. The algorithm is used to separate cloudiness from background and to calculate cloudiness intensity. The found points of the approximated function have been accepted to change pixel intensity by proposed formulas. The algorithm efficiency is compared with those based on ordinary and Cumulative Histograms. By controlling the number of points for piecewise linear approximation function, the necessary segmentation accuracy can be achieved. The algorithm complexity is linear to the number of image pixels and to the number of intensity steps. The developed algorithm is applied to the satellite map images to separate clouds of different intensity. The extracted clouds of different intensity are used to classify regions by cloudiness with a developed clustering algorithm. Testing and experimental results are presented.
-
face image barcodes by distributed Cumulative Histogram and clustering
2020 IEEE 15th International Conference on Advanced Trends in Radioelectronics Telecommunications and Computer Engineering (TCSET), 2020Co-Authors: Roman Melnyk, Yurii KalychakAbstract:Two generations of distributed Cumulative Histogram are in the base of the proposed approach to determine face features. The rough barcodes of the face image were obtained. The clustering K-means algorithm was applied to features to get more contrast bands of color. Then rough barcodes were transformed to real barcodes by highlighting the maximal bands and remaining all other as black background.
-
modification of swir face images for their comparison by distributed Cumulative Histogram features
2019 IEEE 14th International Conference on Computer Sciences and Information Technologies (CSIT), 2019Co-Authors: Roman Melnyk, Ruslan Tushnytskyy, Yuriy KalychakAbstract:A method for distance reduction between Cumulative Histograms of the SWIR face images is considered. Categories of distributed Cumulative Histogram (DCH) and segmented DCH are proposed. A distance matrix by statistical features is clustered for face images classification.
-
distributed Cumulative Histogram features for similarity graph decomposition of face images
2019 IEEE 14th International Conference on Computer Sciences and Information Technologies (CSIT), 2019Co-Authors: Roman Melnyk, Ruslan TushnytskyyAbstract:The method for extraction of face distributed features from pixel intensity columns and rows is developed. For the processed images the biggest difference was observed. The application of the developed statistical features for use in the classification of faces is demonstrated.
-
ANALYSIS OF CLOUDINESS BY SEGMENTATION AND MONITORING OF SATELLITE MAP IMAGES
International Journal of Computing, 2019Co-Authors: Roman Melnyk, Yurii Kalychak, Roman KvitAbstract:The algorithm of the dynamic threshold segmentation of images using clipping plane in a three-dimensional XYZ image space is proposed. To build the clipping plane of the dynamic threshold the precession and nutation angles as the base threshold values are found. The developed algorithm is applied to the satellite map images to get cloudiness intensity. The satellite map images are transformed by segmentation and inversion. The segmented and inverted images are scanned to receive the distributed Cumulative Histograms. By the help of so-called cloudiness meter the statistical data is processed for calculation and monitoring of cloudiness in Ukraine. The formulas to create an image of the distributed Cumulative Histogram are considered. Formulas to reconstruct images of the rotated satellite map images are proposed. The satellite weather map images were taken from the Wunderground services. The clustering algorithm is used to classify the regions of Ukraine by cloudiness intensity, which were created distributed Cumulative images. The clustering algorithm is based on the agglomerative procedure.
