Gautam S Muralidhar

University of Texas at Austin, Austin, Texas, United States

Are you Gautam S Muralidhar?

Claim your profile

Publications (22)13.26 Total impact

  • Gautam S Muralidhar, Alan C. Bovik, Mia Kathleen Markey
    [Show abstract] [Hide abstract]
    ABSTRACT: BACKGROUND Estimating depth reliably from a pair of stereo mammogram images is the first step towards developing quantitative tools for interpreting stereo mammography data. An important problem that needs to be solved in order to elucidate depth is the stereo disparity estimation problem. However, the disparity estimation problem on stereo mammograms is challenging, since nearly all of the 3-D structural information of interest exists as a complex network of multi-layered, heavily occluded curvilinear structures. Towards addressing this difficult problem, we formulate a new stereo model that employs a new singularity index as a constraint to obtain better estimates of disparity along critical curvilinear structures such as blood vessels and spicules. EVALUATION Twenty synthetic stereo images were generated with ground truth disparity data. The synthetic stereo images are comprised of an inverse power law background, with curvilinear structures superimposed to provide a gross resemblance to real mammograms. We compared our algorithm to a conventional visible light stereo disparity estimation algorithm. The percentage of pixels with an erroneous disparity estimate greater than 1 pixel was used as the performance measure. The singularity index driven stereo algorithm performed significantly better than the conventional algorithm on the synthetic images (Wilcoxon signed rank p-value < 0.0001). The new stereo algorithm was also found to operate favorably when evaluated qualitatively on real stereo mammogram pairs provided by Emory University. DISCUSSION Stereo mammography has shown promise in improving upon the sensitivity of breast cancer detection and reducing the number of unnecessary patient recalls. The advent of stereo mammographic imaging, while still nascent, has opened the door for the development of quantitative tools for visualizing and interpreting stereo mammograms. We have taken the first step towards quantitative stereo mammography by developing a new disparity estimation algorithm. CONCLUSION The singularity driven stereo disparity estimation algorithm is promising for estimating disparity on stereo mammogram images.
    Radiological Society of North America 2013 Scientific Assembly and Annual Meeting; 12/2013
  • [Show abstract] [Hide abstract]
    ABSTRACT: The purpose of this study was to evaluate stereoscopic perception of low-dose breast tomosynthesis projection images. In this Institutional Review Board exempt study, craniocaudal breast tomosynthesis cases (N = 47), consisting of 23 biopsy-proven malignant mass cases and 24 normal cases, were retrospectively reviewed. A stereoscopic pair comprised of two projection images that were ±4° apart from the zero angle projection was displayed on a Planar PL2010M stereoscopic display (Planar Systems, Inc., Beaverton, OR, USA). An experienced breast imager verified the truth for each case stereoscopically. A two-phase blinded observer study was conducted. In the first phase, two experienced breast imagers rated their ability to perceive 3D information using a scale of 1-3 and described the most suspicious lesion using the BI-RADS® descriptors. In the second phase, four experienced breast imagers were asked to make a binary decision on whether they saw a mass for which they would initiate a diagnostic workup or not and also report the location of the mass and provide a confidence score in the range of 0-100. The sensitivity and the specificity of the lesion detection task were evaluated. The results from our study suggest that radiologists who can perceive stereo can reliably interpret breast tomosynthesis projection images using stereoscopic viewing.
    Journal of Digital Imaging 11/2013; · 1.10 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: We propose a family of image quality assessment (IQA) models based on natural scene statistics (NSS), that can predict the subjective quality of a distorted image without reference to a corresponding distortionless image, and without any training results on human opinion scores of distorted images. These `completely blind' models compete well with standard non-blind image quality indices in terms of subjective predictive performance when tested on the large publicly available `LIVE' Image Quality database.
    Proc SPIE 03/2013;
  • G.S. Muralidhar, A.C. Bovik, M.K. Markey
    [Show abstract] [Hide abstract]
    ABSTRACT: We analyze the noise sensitivity of a new singularity index that was designed to detect impulse singularities in signals of arbitrary dimensionality while rejecting step-like singularities see Muralidhar, IEEE Signal Process. Lett., vol. 20, no. 1, pp. 7-10, 2013 and Muralidhar , Proc. IEEE Int. Conf. Image Process., 2012. For example, the index responds strongly to curvilinear masses (ridges) in images, while weakly to jump discontinuities (edges). We analyze the detection power of the index in the presence of noise. Our analysis is geared towards answering the following questions: a) in the presence of noise only, what is the probability of falsely detecting an impulse given a threshold; b) given an impulse submerged in noise, what is the probability of detecting it given a threshold; and c) since the index is designed to be edge suppressing, what is the probability of incorrectly detecting an edge submerged in noise given a threshold. We compare the detection power of the index with that of a nominal impulse detector, the second derivative operator. Simulations and example applications in 1-D and 2-D reveal the efficacy of the new singularity index for correctly detecting impulses submerged in noise, while suppressing edges. A software version of the 2-D singularity index can be downloaded from: http://live.ece.utexas.edu/research/SingularityIndex/SingularityIndexCode.zip.
    IEEE Transactions on Signal Processing 01/2013; 61(24):6150-6163. · 2.81 Impact Factor
  • G.S. Muralidhar, A.C. Bovik, M.K. Markey
    [Show abstract] [Hide abstract]
    ABSTRACT: We propose a new steerable, multiscale ratio index for detecting impulse singularities in signals of arbitrary dimensionality. For example, it responds strongly to curvilinear masses (ridges) in images, but minimally to step discontinuities. The ratio index employs directional derivatives of gaussians, making it naturally steerable and scalable. Experiments on real images demonstrate the efficacy of the index for detecting multiscale curvilinear structures. A software version of the index can be downloaded from: http://live.ece.utexas.edu/research/SingularityIndex/SingularityIndex.zip.
    IEEE Signal Processing Letters 01/2013; 20(1):7-10. · 1.67 Impact Factor
  • Source
    Juhun Lee, Gautam S Muralidhar, Gregory P Reece, Mia K Markey
    [Show abstract] [Hide abstract]
    ABSTRACT: Quantitative measures of breast morphology can help a breast cancer survivor to understand outcomes of reconstructive surgeries. One bottleneck of quantifying breast morphology is that there are only a few reliable automation algorithms for detecting the breast contour. This study proposes a novel approach for detecting the breast contour, which is based on a parametric active contour model. In addition to employing the traditional parametric active contour model, the proposed approach enforces a mathematical shape constraint based on the catenary curve, which has been previously shown to capture the overall shape of the breast contour reliably [1]. The mathematical shape constraint regulates the evolution of the active contour and helps the contour evolve towards the breast, while minimizing the undesired effects of other structures such as, the nipple/areola and scars. The efficacy of the proposed approach was evaluated on anterior posterior photographs of women who underwent or were scheduled for breast reconstruction surgery including autologous tissue reconstruction. The proposed algorithm shows promising results for detecting the breast contour.
    Conference proceedings: ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference 08/2012; 2012:4450-3.
  • Gautam S Muralidhar, Ajay Gopinath, Alan C Bovik, Adela Ben-Yakar
    [Show abstract] [Hide abstract]
    ABSTRACT: We present an active contour framework for segmenting neuronal axons on 3D confocal microscopy data. Our work is motivated by the need to conduct high throughput experiments involving microfluidic devices and femtosecond lasers to study the genetic mechanisms behind nerve regeneration and repair. While most of the applications for active contours have focused on segmenting closed regions in 2D medical and natural images, there haven't been many applications that have focused on segmenting open-ended curvilinear structures in 2D or higher dimensions. The active contour framework we present here ties together a well known 2D active contour model [5] along with the physics of projection imaging geometry to yield a segmented axon in 3D. Qualitative results illustrate the promise of our approach for segmenting neruonal axons on 3D confocal microscopy data.
    Conference proceedings: ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference 08/2012; 2012:4006-9.
  • [Show abstract] [Hide abstract]
    ABSTRACT: The goal of this study was to assess if stereoscopic viewing of breast tomosynthesis projection images impacted mass detection performance when compared to monoscopic viewing. The dataset for this study, provided by Hologic, Inc., contained 47 craniocaudal cases (23 biopsy proven malignant masses and 24 normals). Two projection images that were separated by 8 degrees were chosen to form a stereoscopic pair. The images were preprocessed to enhance their contrast and were presented on a stereoscopic display. Three experienced breast imagers participated in a blinded observer study as readers. Each case was shown twice to each reader - once in the stereoscopic mode, and once in the monoscopic mode in a random order. The readers were asked to make a binary decision on whether they saw a mass for which they would initiate a diagnostic workup or not, and also report the location of the mass and provide a confidence score in the range of 0-100. The binary decisions were analyzed using the sensitivity-specificity measure, while the confidence scores were analyzed using the Receiver Operating Characteristic curve (ROC). We also report a statistical analysis of the difference in partial AUC values greater than 95% sensitivity between the stereoscopic and monoscopic modes.
    Proc SPIE 02/2012;
  • Conference Paper: A new singularity index
    G.S. Muralidhar, A.C. Bovik, M.K. Markey
    [Show abstract] [Hide abstract]
    ABSTRACT: We propose a new ratio index for the detection of impulse-like singularities in signals of arbitrary dimensionality. We show that the new singularity index responds strongly to singularities that are like impulses or smoothed impulses in cross section. For example, it responds strongly to curvilinear masses (ridges) in images, while responding minimally to edge-like singularities. The ratio index employs directional derivatives of gaussians, which makes the index naturally scalable.
    Image Processing (ICIP), 2012 19th IEEE International Conference on; 01/2012
  • Source
    A. Mittal, G.S. Muralidhar, J. Ghosh, A.C. Bovik
    [Show abstract] [Hide abstract]
    ABSTRACT: We propose a highly unsupervised, training free, no reference image quality assessment (IQA) model that is based on the hypothesis that distorted images have certain latent characteristics that differ from those of “natural” or “pristine” images. These latent characteristics are uncovered by applying a “topic model” to visual words extracted from an assortment of pristine and distorted images. For the latent characteristics to be discriminatory between pristine and distorted images, the choice of the visual words is important. We extract quality-aware visual words that are based on natural scene statistic features [1]. We show that the similarity between the probability of occurrence of the different topics in an unseen image and the distribution of latent topics averaged over a large number of pristine natural images yields a quality measure. This measure correlates well with human difference mean opinion scores on the LIVE IQA database [2].
    IEEE Signal Processing Letters 01/2012; 19(2):75-78. · 1.67 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: PURPOSE We evaluated the feasibility of characterizing breast masses as seen on breast tomosynthesis projection images using a stereoscopic (stereo) display. METHOD AND MATERIALS Tomosynthesis data were provided by Hologic, Inc. (Bedford, MA, USA). Each case was comprised of 15 projections that spanned an angular range of 15 degrees. Two projection images that were ± 4 degrees apart from the zero angle projection were chosen to form a stereo pair. In this study, we used only the craniocaudal stereo pairs from 47 cases. The images had their contrast enhanced and were displayed on a Planar PL2010M stereo display (Planar Systems, Inc., Beaverton, OR, USA). The 47 cases were comprised of 23 biopsy proven masses and 24 normals. An experienced breast imager who did not participate in the observer study verified the truth for each case stereoscopically. Two experienced breast imagers participated in a blinded observer study as readers after passing the Randot stereo acuity test. The readers were asked to describe the most suspicious abnormality using the BI-RADS® (American College of Radiology) descriptors. The readers were also asked to describe the lesion subtlety on a scale of 1-5. The AC1 and AC2 (weighted AC1) coefficients were used as alternatives to the Kappa coefficient to assess the inter-reader agreement. RESULTS The sensitivities achieved by the two readers in detecting the correct abnormality were 86.9% and 91.3%, while the specificities achieved were 79.1% and 83.3%. Good inter-reader agreement was observed for BI-RADS® mass margin and assessment ratings (AC1 = 0.64 and 0.73, respectively), while excellent inter-reader agreement was observed for mass subtlety ratings (AC2 = 0.94). Moderate agreement was observed for BI-RADS® mass shape ratings (AC1 = 0.28). CONCLUSION Breast masses can be reliably characterized on breast tomosynthesis projections with stereoscopic viewing. CLINICAL RELEVANCE/APPLICATION Breast tomosynthesis projections are amenable to stereoscopic viewing, which has the potential to aid in image interpretation and treatment planning.
    Radiological Society of North America 2011 Scientific Assembly and Annual Meeting; 11/2011
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Accurate segmentation of magnetic resonance (MR) images of the brain to differentiate features such as soft tissue, tumor, edema and necrosis is critical for both diagnosis and treatment purposes. Region-based formulations of geometric active contour models are popular choices for segmentation of MR and other medical images. Most of the traditional region-based formulations model local region intensity by assuming a piecewise constant approximation. However, the piecewise constant approximation rarely holds true for medical images such as MR images due to the presence of noise and bias field, which invariably results in a poor segmentation of the image. To overcome this problem, we have developed a probabilistic region-based active contour model for automatic segmentation of MR images of the brain. In our approach, a mixture of Gaussian distributions is used to accurately model the arbitrarily shaped local region intensity distribution. Prior spatial information derived from probabilistic atlases is also integrated into the level set evolution framework for guiding the segmentation process. Our experiments with a series of publicly available brain MR images show that the proposed active contour model gives stable and accurate segmentation results when compared to the traditional region based formulations.
    Conference proceedings: ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference 08/2011; 2011:2821-4.
  • [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, we review the role played by breast magnetic resonance imaging in the detection and diagnosis of breast cancer. This is followed by a discussion of clinical decision support systems in medicine and their contributions in breast magnetic resonance imaging interpretation. We conclude by discussing the future of computer-aided diagnosis in breast magnetic resonance imaging. Mt Sinai J Med 78:280–290, 2011. © 2011 Mount Sinai School of Medicine
    Mount Sinai Journal of Medicine A Journal of Translational and Personalized Medicine 02/2011; 78(2):280 - 290. · 1.99 Impact Factor
  • Source
    G.S. Muralidhar, A.C. Bovik, M.K. Markey
    [Show abstract] [Hide abstract]
    ABSTRACT: 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.
    Image Processing (ICIP), 2010 17th IEEE International Conference on; 10/2010
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: 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.
    IEEE transactions on medical imaging. 10/2010; 29(10):1768-80.
  • Source
    Gautam S. Muralidhar, Mia K. Markey, Alan C. Bovik
    [Show abstract] [Hide abstract]
    ABSTRACT: 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.
    Image Analysis & Interpretation (SSIAI), 2010 IEEE Southwest Symposium on; 06/2010
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: We evaluated the use of a stylus as a computer interface for radiographic image annotation. Our case study concerned the annotation of spiculated lesions on mammograms. Three experienced radiologists annotated 20 mammograms depicting spiculated lesions. We evaluated the interobserver agreement in annotations marked with a stylus versus those marked with a mouse using the intraclass correlation coefficient. Better agreement in annotating spicule width was observed with the stylus, suggesting that it is easier to accurately annotate subtle regions on an image using a stylus.
    Journal of Digital Imaging 09/2009; 23(6):701-5. · 1.10 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: Purpose: We are developing a model‐based framework for the detection of spiculated masses on mammography, the current performance of which is 88% sensitivity with 2.7 false positives per image. The goal of this study is to identify features that uniquely characterize the true positive (TP) and false positive (FP) detections from this system. Method and Materials: A two alternative‐forced‐choice observer experiment was used. For each of the 47 cases of spiculated masses, the true lesion location and the highest‐ranked FP from the CAD were shown to the observer (radiologist). The observer was not told if he/she was looking at the true lesion location or FP and the order in which these were shown was random. The radiologist visually inspected these images to pick the one that corresponds to the true lesion location. We then compared this decision to the ground truth to analyze the TP and FP detections that were incorrectly determined by the radiologist. Results: The radiologist correctly identified the true lesion location and false positive for all 47 cases. These data suggest that the radiologist could easily dismiss the false positives marked by the CAD algorithm. Conclusion: While false positive detections remain a challenge with the current version of our model‐based framework for the detection of spiculated masses on mammography, this study implies that those false positives may be recognizable as such by the radiologists and suggests future directions for reducing the number of false positive marks.
    Medical Physics 05/2008; 35(6):2644-2644. · 2.91 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: We have developed a novel technique to automatically identify a region of interest (ROI) surrounding a spiculated lesion on a mammogram. Our proposed approach for determining the size of the ROI depends on the response of a set of unique spiculation filters (SF). The design of these filters is based on manually annotated physical characteristics of spicules. The accuracy of our algorithm is measured in terms of the percentage of spicule pixels located inside the identified ROI. Spicules on each image were identified by an experienced radiologist to serve as a reference to determine the percentage of spicules located in the ROI. On average, 94 percent of spicule pixels were located inside the ROI identified by our algorithm.
    Image Analysis and Interpretation, 2008. SSIAI 2008. IEEE Southwest Symposium on; 04/2008
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Automated analysis of fluorescence microscopy images of endothelial cells labeled for actin is important for quantifying changes in the actin cytoskeleton. The current manual approach is laborious and inefficient. The goal of our work is to develop automated image analysis methods, thereby increasing cell analysis throughput. In this study, we present preliminary results on comparing different algorithms for cell segmentation and image denoising.
    AMIA ... Annual Symposium proceedings / AMIA Symposium. AMIA Symposium 02/2008;