The Experts below are selected from a list of 327 Experts worldwide ranked by ideXlab platform
Bijan Vosoughi-vahdat - One of the best experts on this subject based on the ideXlab platform.
-
EMBC - A Wavelet-packet-based approach for breast cancer classification
Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and, 2011Co-Authors: Meysam Torabi, Seiied-mohammad-javad Razavian, Reza Vaziri, Bijan Vosoughi-vahdatAbstract:In this paper, a new approach for non-invasive diagnosis of breast diseases is tested on the region of the breast without undue influence from the background and medically unnecessary parts of the images. We applied Wavelet packet analysis on the two-dimensional histogram matrices of a large number of breast images to generate the filter banks, namely sub-images. Each of 1250 resulting sub-images are used for computation of 32 two-dimensional histogram matrices. Then informative statistical features (e.g. skewness and kurtosis) are extracted from each matrix. The independent features, using 5-fold cross-validation protocol, are considered as the input sets of supervised classification. We observed that the proposed method improves the detection accuracy of Architectural Distortion disease compared to previous works and also is very effective for diagnosis of Spiculated Mass and MISC diseases.
-
A Wavelet-packet-based approach for breast cancer classification
2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 2011Co-Authors: Meysam Torabi, Seiied-mohammad-javad Razavian, Reza Vaziri, Bijan Vosoughi-vahdatAbstract:In this paper, a new approach for non-invasive diagnosis of breast diseases is tested on the region of the breast without undue influence from the background and medically unnecessary parts of the images. We applied Wavelet packet analysis on the two-dimensional histogram matrices of a large number of breast images to generate the filter banks, namely sub-images. Each of 1250 resulting sub-images are used for computation of 32 two-dimensional histogram matrices. Then informative statistical features (e.g. skewness and kurtosis) are extracted from each matrix. The independent features, using 5-fold cross-validation protocol, are considered as the input sets of supervised classification. We observed that the proposed method improves the detection accuracy of Architectural Distortion disease compared to previous works and also is very effective for diagnosis of Spiculated Mass and MISC diseases.
Mia K. Markey - One of the best experts on this subject based on the ideXlab platform.
-
ICIP - Snakules: Snakes that seek spicules on mammography
2010 IEEE International Conference on Image Processing, 2010Co-Authors: Gautam S. Muralidhar, Alan C. Bovik, Mia K. MarkeyAbstract:We present a new method called “snakules” for the annotation of spicules on mammography. Snakules employs parametric open-ended snakes that are deployed in a region around a suspect Spiculated Mass location that has been identified by a radiologist or a computer-aided detection (CADe) algorithm. The set of convergent snakules deform, grow and adapt to the true spicules in the image, by an attractive process of curve evolution and motion that optimizes the local matching energy. Our results from an initial observer study involving an experienced radiologist demonstrate the strong potential of the method as an image analysis technique to improve the specificity of CADe algorithms.
-
snakules a model based active contour algorithm for the annotation of spicules on mammography
IEEE Transactions on Medical Imaging, 2010Co-Authors: Gautam S. Muralidhar, Alan C. Bovik, David J Giese, Mehul P Sampat, Gary J Whitman, Tamara Miner Haygood, Tanya W Stephens, Mia K. MarkeyAbstract:We have developed a novel, model-based active contour algorithm, termed “snakules”, for the annotation of spicules on mammography. At each suspect Spiculated Mass location that has been identified by either a radiologist or a computer-aided detection (CADe) algorithm, we deploy snakules that are converging open-ended active contours also known as snakes. The set of convergent snakules have the ability to deform, grow and adapt to the true spicules in the image, by an attractive process of curve evolution and motion that optimizes the local matching energy. Starting from a natural set of automatically detected candidate points, snakules are deployed in the region around a suspect Spiculated Mass location. Statistics of prior physical measurements of Spiculated Masses on mammography are used in the process of detecting the set of candidate points. Observer studies with experienced radiologists to evaluate the performance of snakules demonstrate the potential of the algorithm as an image analysis technique to improve the specificity of CADe algorithms and as a CADe prompting tool.
-
Snakules for automatic classification of candidate Spiculated Mass locations on mammography
2010 IEEE Southwest Symposium on Image Analysis & Interpretation (SSIAI), 2010Co-Authors: Gautam S. Muralidhar, Mia K. Markey, Alan C. BovikAbstract:In this paper, we describe a novel approach for the automatic classification of candidate Spiculated Mass locations on mammography. Our approach is based on “Snakules” - an evidence-based active contour algorithm that we have recently developed for the annotation of spicules on mammography. We use snakules to extract features characteristic of spicules and Spiculated Masses, and use these features to classify whether a region of a mammogram contains a Spiculated Mass or not. The results from our initial classification experiment demonstrate the strong potential of snakules as an image analysis technique to extract features specific to spicules and Spiculated Masses, which can subsequently be used to distinguish true Spiculated Mass locations from non-lesion locations on a mammogram and improve the specificity of computer-aided detection (CADe) algorithms.
-
Snakules: Snakes that seek spicules on mammography
2010 IEEE International Conference on Image Processing, 2010Co-Authors: Gautam S. Muralidhar, Alan C. Bovik, Mia K. MarkeyAbstract:We present a new method called “snakules” for the annotation of spicules on mammography. Snakules employs parametric open-ended snakes that are deployed in a region around a suspect Spiculated Mass location that has been identified by a radiologist or a computer-aided detection (CADe) algorithm. The set of convergent snakules deform, grow and adapt to the true spicules in the image, by an attractive process of curve evolution and motion that optimizes the local matching energy. Our results from an initial observer study involving an experienced radiologist demonstrate the strong potential of the method as an image analysis technique to improve the specificity of CADe algorithms.
Meysam Torabi - One of the best experts on this subject based on the ideXlab platform.
-
EMBC - A Wavelet-packet-based approach for breast cancer classification
Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and, 2011Co-Authors: Meysam Torabi, Seiied-mohammad-javad Razavian, Reza Vaziri, Bijan Vosoughi-vahdatAbstract:In this paper, a new approach for non-invasive diagnosis of breast diseases is tested on the region of the breast without undue influence from the background and medically unnecessary parts of the images. We applied Wavelet packet analysis on the two-dimensional histogram matrices of a large number of breast images to generate the filter banks, namely sub-images. Each of 1250 resulting sub-images are used for computation of 32 two-dimensional histogram matrices. Then informative statistical features (e.g. skewness and kurtosis) are extracted from each matrix. The independent features, using 5-fold cross-validation protocol, are considered as the input sets of supervised classification. We observed that the proposed method improves the detection accuracy of Architectural Distortion disease compared to previous works and also is very effective for diagnosis of Spiculated Mass and MISC diseases.
-
A Wavelet-packet-based approach for breast cancer classification
2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 2011Co-Authors: Meysam Torabi, Seiied-mohammad-javad Razavian, Reza Vaziri, Bijan Vosoughi-vahdatAbstract:In this paper, a new approach for non-invasive diagnosis of breast diseases is tested on the region of the breast without undue influence from the background and medically unnecessary parts of the images. We applied Wavelet packet analysis on the two-dimensional histogram matrices of a large number of breast images to generate the filter banks, namely sub-images. Each of 1250 resulting sub-images are used for computation of 32 two-dimensional histogram matrices. Then informative statistical features (e.g. skewness and kurtosis) are extracted from each matrix. The independent features, using 5-fold cross-validation protocol, are considered as the input sets of supervised classification. We observed that the proposed method improves the detection accuracy of Architectural Distortion disease compared to previous works and also is very effective for diagnosis of Spiculated Mass and MISC diseases.
Gautam S. Muralidhar - One of the best experts on this subject based on the ideXlab platform.
-
ICIP - Snakules: Snakes that seek spicules on mammography
2010 IEEE International Conference on Image Processing, 2010Co-Authors: Gautam S. Muralidhar, Alan C. Bovik, Mia K. MarkeyAbstract:We present a new method called “snakules” for the annotation of spicules on mammography. Snakules employs parametric open-ended snakes that are deployed in a region around a suspect Spiculated Mass location that has been identified by a radiologist or a computer-aided detection (CADe) algorithm. The set of convergent snakules deform, grow and adapt to the true spicules in the image, by an attractive process of curve evolution and motion that optimizes the local matching energy. Our results from an initial observer study involving an experienced radiologist demonstrate the strong potential of the method as an image analysis technique to improve the specificity of CADe algorithms.
-
snakules a model based active contour algorithm for the annotation of spicules on mammography
IEEE Transactions on Medical Imaging, 2010Co-Authors: Gautam S. Muralidhar, Alan C. Bovik, David J Giese, Mehul P Sampat, Gary J Whitman, Tamara Miner Haygood, Tanya W Stephens, Mia K. MarkeyAbstract:We have developed a novel, model-based active contour algorithm, termed “snakules”, for the annotation of spicules on mammography. At each suspect Spiculated Mass location that has been identified by either a radiologist or a computer-aided detection (CADe) algorithm, we deploy snakules that are converging open-ended active contours also known as snakes. The set of convergent snakules have the ability to deform, grow and adapt to the true spicules in the image, by an attractive process of curve evolution and motion that optimizes the local matching energy. Starting from a natural set of automatically detected candidate points, snakules are deployed in the region around a suspect Spiculated Mass location. Statistics of prior physical measurements of Spiculated Masses on mammography are used in the process of detecting the set of candidate points. Observer studies with experienced radiologists to evaluate the performance of snakules demonstrate the potential of the algorithm as an image analysis technique to improve the specificity of CADe algorithms and as a CADe prompting tool.
-
Snakules for automatic classification of candidate Spiculated Mass locations on mammography
2010 IEEE Southwest Symposium on Image Analysis & Interpretation (SSIAI), 2010Co-Authors: Gautam S. Muralidhar, Mia K. Markey, Alan C. BovikAbstract:In this paper, we describe a novel approach for the automatic classification of candidate Spiculated Mass locations on mammography. Our approach is based on “Snakules” - an evidence-based active contour algorithm that we have recently developed for the annotation of spicules on mammography. We use snakules to extract features characteristic of spicules and Spiculated Masses, and use these features to classify whether a region of a mammogram contains a Spiculated Mass or not. The results from our initial classification experiment demonstrate the strong potential of snakules as an image analysis technique to extract features specific to spicules and Spiculated Masses, which can subsequently be used to distinguish true Spiculated Mass locations from non-lesion locations on a mammogram and improve the specificity of computer-aided detection (CADe) algorithms.
-
Snakules: Snakes that seek spicules on mammography
2010 IEEE International Conference on Image Processing, 2010Co-Authors: Gautam S. Muralidhar, Alan C. Bovik, Mia K. MarkeyAbstract:We present a new method called “snakules” for the annotation of spicules on mammography. Snakules employs parametric open-ended snakes that are deployed in a region around a suspect Spiculated Mass location that has been identified by a radiologist or a computer-aided detection (CADe) algorithm. The set of convergent snakules deform, grow and adapt to the true spicules in the image, by an attractive process of curve evolution and motion that optimizes the local matching energy. Our results from an initial observer study involving an experienced radiologist demonstrate the strong potential of the method as an image analysis technique to improve the specificity of CADe algorithms.
Hilde Bosmans - One of the best experts on this subject based on the ideXlab platform.
-
a new test method to assess the representation of Spiculated Mass like targets in digital mammography and breast tomosynthesis
Medical Imaging 2019: Physics of Medical Imaging, 2019Co-Authors: Elisabeth Salomon, Friedrich Semturs, Lesley Cockmartin, Michael Figl, Hilde Bosmans, Johann HummelAbstract:In this work we tested different materials for 3D printing of Spiculated Mass models for their incorporation into an existing 3D structured phantom for performance testing of FFDM and DBT. Counting the number of spicules as a function of dose was then evaluated as a possible extra test feature expressing conspicuity next to detectability. Seven printable materials were exposed together with a PMMA step wedge and material samples with known linear attenuation coefficient to determine PMMA equivalent thickness and linear attenuation coefficient, respectively. Next, two models of Spiculated Masses were created each with a different complexity in terms of number of spicules. The visibility of the number of spicules of a 3D printed Spiculated Mass model loosely placed in the phantom or embedded into two different printing materials was assessed for FFDM and DBT. Vero White pure was chosen as the most appropriate material for the printing of Masses whereas Vero Clear and Tango+ were chosen as background materials. The visibility of spicules was best in the loose Mass models and better in the background material Tango+ compared to Vero Clear. While the discrimination of the different spicules could be assessed in FFDM and DBT, as expected only a limited dose sensitivity was found for the visibility of spicules evaluated for the different background materials and at different beam energies.
-
comparison of two psychometric functions in analyzing 4 afc detection results using a task based structured phantom for digital mammography
Physica Medica, 2016Co-Authors: Kristina Tri Wigati, Lesley Cockmartin, Nicholas Marshall, D S Soejoko, Hilde BosmansAbstract:Introduction Detectability of Spiculated and non-Spiculated Mass models and microcalcifications, in a structured background phantom of acrylic spheres and water, was studied for digital mammography via the four-alternative forced-choice (4-AFC) paradigm. Purpose To compare the threshold diameters for Mass and microcalcification detection using two types of psychometric curves applied on the contrast-detail data. Material and methods Ten images of the structured phantom were acquired on 23 digital mammography systems under automatic exposure control. The 4-AFC study was performed with in-house developed software and 5 medical physicists as observers. Percentage correctly detected lesions (PC) was obtained for each target type. Two psychometric curves (Weibull and Logistic functions) were applied to determine the threshold diameters and number of detected targets (at PC = 62.5%). Results Both fitting procedures were successfully applied on all systems. After averaging over 23 systems, the threshold diameters for Spiculated and non-Spiculated Masses and microcalcifications, with the Weibull psychometric curves, were 4.0 ± 0.3 mm (R 2 = 0.61 ± 0.08), 4.6 ± 0.7 mm (R 2 = 0.51 ± 0.11), and 0.114 ± 0.003 mm (R 2 = 0.91 ± 0.03) respectively, and the values of 4.0 ± 0.4 mm (R 2 = 0.61 ± 0.08), 4.7 ± 0.6 mm (R 2 = 0.50 ± 0.11), and 0.114 ± 0.003 mm (R 2 = 0.91 ± 0.03) were obtained with the Logistic function. The numbers of detected targets assessed from the two functions were not different (3–4 Spiculated Masses, 1–2 non-Spiculated Masses, and 4 groups of microcalcifications). If the PC values were not completely covering the lower and upper than 62.5%, there will be possibility different results occurred from these two functions. Conclusion Weibull and Logistic curve fits gave similar and reproducible threshold diameters for the structured phantom.
-
Digital Mammography / IWDM - Impact of Clinical Display Device on Detectability of Breast Masses in 2D Digital Mammography: A Virtual Clinical Study
Breast Imaging, 2016Co-Authors: Alaleh Rashidnasab, Nicholas Marshall, Frédéric Bemelmans, Tom Kimpe, Hilde BosmansAbstract:This work investigates the impact of advanced clinical displays on cancer detection in 2D digital mammograms using four-alternative-forced-choice 4AFC and a dataset of images with inserted simulated lesions. Images were displayed on a standard monitor Barco Coronis 5MP mammo and an advanced monitor Barco Coronis Uniti 12MP MDMC-12132. Ill-defined margin and Spiculated Mass models were inserted into mammographic regions of interest using a validated physics-based insertion framework. Experiments were conducted for Mass size of 8---11i¾?mm to 2---3i¾?mm and density of 100i¾?% to 70i¾?% of glandular tissue with 142 trials per condition. Five medical physicists read the dataset on both monitors. Percentage correct PC of detected Masses for average observer and 95i¾?% confidence intervals were determined. Paired t-test and ANOVA analysis were performed. The observers had significantly better detection rates when the dataset was read on the advanced monitor compared to the standard monitor 3i¾?% increase in overall PC, paired p-valuei¾?$$=$$i¾?0.0076.
-
Medical Imaging: Image Perception, Observer Performance, and Technology Assessment - Development and application of a channelized Hotelling observer for DBT optimization on structured background test images with Mass simulating targets
Proceedings of SPIE, 2016Co-Authors: Dimitar Petrov, Lesley Cockmartin, Koen Michielsen, Gouzhi Zhang, Kenneth C. Young, Nicholas Marshall, Hilde BosmansAbstract:Digital breast tomosynthesis (DBT) is a 3D mammography technique that promises better visualization of low contrast lesions than conventional 2D mammography. A wide range of parameters influence the diagnostic information in DBT images and a systematic means of DBT system optimization is needed. The gold standard for image quality assessment is to perform a human observer experiment with experienced readers. Using human observers for optimization is time consuming and not feasible for the large parameter space of DBT. Our goal was to develop a model observer (MO) that can predict human reading performance for standard detection tasks of target objects within a structured phantom and subsequently apply it in a first comparative study. The phantom consists of an acrylic semi-cylindrical container with acrylic spheres of different sizes and the remaining space filled with water. Three types of lesions were included: 3D printed Spiculated and non-Spiculated Mass lesions along with calcification groups. The images of the two Mass lesion types were reconstructed with 3 different reconstruction methods (FBP, FBP with SRSAR, MLTR pr ) and read by human readers. A Channelized Hotelling model observer was created for the non-Spiculated lesion detection task using five Laguerre-Gauss channels, tuned for better performance. For the non-Spiculated Mass lesions a linear relation between the MO and human observer results was found, with correlation coefficients of 0.956 for standard FBP, 0.998 for FBP with SRSAR and 0.940 for MLTRpr. Both the MO and human observer percentage correct results for the Spiculated Masses were close to 100%, and showed no difference from each other for every reconstruction algorithm.