Sohini Roychowdhury

is this you? claim profile


  • Computer Aided Detection of Anemia-like Pallor

    Paleness or pallor is a manifestation of blood loss or low hemoglobin concentrations in the human blood that can be caused by pathologies such as anemia. This work presents the first automated screening system that utilizes pallor site images, segments, and extracts color and intensity-based features for multi-class classification of patients with high pallor due to anemia-like pathologies, normal patients and patients with other abnormalities. This work analyzes the pallor sites of conjunctiva and tongue for anemia screening purposes. First, for the eye pallor site images, the sclera and conjunctiva regions are automatically segmented for regions of interest. Similarly, for the tongue pallor site images, the inner and outer tongue regions are segmented. Then, color-plane based feature extraction is performed followed by machine learning algorithms for feature reduction and image level classification for anemia. In this work, a suite of classification algorithms image-level classifications for normal (class 0), pallor (class 1) and other abnormalities (class 2). The proposed method achieves 86 recall in eye pallor site images and 98.2 recall in tongue pallor site images for classification of images with pallor. The proposed pallor screening system can be further fine-tuned to detect the severity of anemia-like pathologies using controlled set of local images that can then be used for future benchmarking purposes.

    03/17/2017 ∙ by Sohini Roychowdhury, et al. ∙ 0 share

    read it

  • Automated OCT Segmentation for Images with DME

    This paper presents a novel automated system that segments six sub-retinal layers from optical coherence tomography (OCT) image stacks of healthy patients and patients with diabetic macular edema (DME). First, each image in the OCT stack is denoised using a Wiener deconvolution algorithm that estimates the additive speckle noise variance using a novel Fourier-domain based structural error. This denoising method enhances the image SNR by an average of 12dB. Next, the denoised images are subjected to an iterative multi-resolution high-pass filtering algorithm that detects seven sub-retinal surfaces in six iterative steps. The thicknesses of each sub-retinal layer for all scans from a particular OCT stack are then compared to the manually marked groundtruth. The proposed system uses adaptive thresholds for denoising and segmenting each image and hence it is robust to disruptions in the retinal micro-structure due to DME. The proposed denoising and segmentation system has an average error of 1.2-5.8 μ m and 3.5-26μ m for segmenting sub-retinal surfaces in normal and abnormal images with DME, respectively. For estimating the sub-retinal layer thicknesses, the proposed system has an average error of 0.2-2.5 μ m and 1.8-18 μ m in normal and abnormal images, respectively. Additionally, the average inner sub-retinal layer thickness in abnormal images is estimated as 275μ m (r=0.92) with an average error of 9.3 μ m, while the average thickness of the outer layers in abnormal images is estimated as 57.4μ m (r=0.74) with an average error of 3.5 μ m. The proposed system can be useful for tracking the disease progression for DME over a period of time.

    10/24/2016 ∙ by Sohini Roychowdhury, et al. ∙ 0 share

    read it

  • Automated Selection of Uniform Regions for CT Image Quality Detection

    CT images are widely used in pathology detection and follow-up treatment procedures. Accurate identification of pathological features requires diagnostic quality CT images with minimal noise and artifact variation. In this work, a novel Fourier-transform based metric for image quality (IQ) estimation is presented that correlates to additive CT image noise. In the proposed method, two windowed CT image subset regions are analyzed together to identify the extent of variation in the corresponding Fourier-domain spectrum. The two square windows are chosen such that their center pixels coincide and one window is a subset of the other. The Fourier-domain spectral difference between these two sub-sampled windows is then used to isolate spatial regions-of-interest (ROI) with low signal variation (ROI-LV) and high signal variation (ROI-HV), respectively. Finally, the spatial variance (var), standard deviation (std), coefficient of variance (cov) and the fraction of abdominal ROI pixels in ROI-LV (ν'(q)), are analyzed with respect to CT image noise. For the phantom CT images, var and std correlate to CT image noise (|r|>0.76 (p≪0.001)), though not as well as ν'(q) (r=0.96 (p≪0.001)). However, for the combined phantom and patient CT images, var and std do not correlate well with CT image noise (|r|<0.46 (p≪0.001)) as compared to ν'(q) (r=0.95 (p≪0.001)). Thus, the proposed method and the metric, ν'(q), can be useful to quantitatively estimate CT image noise.

    08/13/2016 ∙ by Maitham D Naeemi, et al. ∙ 0 share

    read it

  • Blind Analysis of CT Image Noise Using Residual Denoised Images

    CT protocol design and quality control would benefit from automated tools to estimate the quality of generated CT images. These tools could be used to identify erroneous CT acquisitions or refine protocols to achieve certain signal to noise characteristics. This paper investigates blind estimation methods to determine global signal strength and noise levels in chest CT images. Methods: We propose novel performance metrics corresponding to the accuracy of noise and signal estimation. We implement and evaluate the noise estimation performance of six spatial- and frequency- based methods, derived from conventional image filtering algorithms. Algorithms were tested on patient data sets from whole-body repeat CT acquisitions performed with a higher and lower dose technique over the same scan region. Results: The proposed performance metrics can evaluate the relative tradeoff of filter parameters and noise estimation performance. The proposed automated methods tend to underestimate CT image noise at low-flux levels. Initial application of methodology suggests that anisotropic diffusion and Wavelet-transform based filters provide optimal estimates of noise. Furthermore, methodology does not provide accurate estimates of absolute noise levels, but can provide estimates of relative change and/or trends in noise levels.

    05/24/2016 ∙ by Sohini Roychowdhury, et al. ∙ 0 share

    read it

  • Classification of Large-Scale Fundus Image Data Sets: A Cloud-Computing Framework

    Large medical image data sets with high dimensionality require substantial amount of computation time for data creation and data processing. This paper presents a novel generalized method that finds optimal image-based feature sets that reduce computational time complexity while maximizing overall classification accuracy for detection of diabetic retinopathy (DR). First, region-based and pixel-based features are extracted from fundus images for classification of DR lesions and vessel-like structures. Next, feature ranking strategies are used to distinguish the optimal classification feature sets. DR lesion and vessel classification accuracies are computed using the boosted decision tree and decision forest classifiers in the Microsoft Azure Machine Learning Studio platform, respectively. For images from the DIARETDB1 data set, 40 of its highest-ranked features are used to classify four DR lesion types with an average classification accuracy of 90.1 classification of red lesion regions and hemorrhages from microaneurysms, accuracies of 85 data set, 40 high-ranked features can classify minor blood vessels with an accuracy of 83.5 systems can significantly enhance the borderline classification performances in automated screening systems.

    03/26/2016 ∙ by Sohini Roychowdhury, et al. ∙ 0 share

    read it

  • A generalized flow for multi-class and binary classification tasks: An Azure ML approach

    The constant growth in the present day real-world databases pose computational challenges for a single computer. Cloud-based platforms, on the other hand, are capable of handling large volumes of information manipulation tasks, thereby necessitating their use for large real-world data set computations. This work focuses on creating a novel Generalized Flow within the cloud-based computing platform: Microsoft Azure Machine Learning Studio (MAMLS) that accepts multi-class and binary classification data sets alike and processes them to maximize the overall classification accuracy. First, each data set is split into training and testing data sets, respectively. Then, linear and nonlinear classification model parameters are estimated using the training data set. Data dimensionality reduction is then performed to maximize classification accuracy. For multi-class data sets, data centric information is used to further improve overall classification accuracy by reducing the multi-class classification to a series of hierarchical binary classification tasks. Finally, the performance of optimized classification model thus achieved is evaluated and scored on the testing data set. The classification characteristics of the proposed flow are comparatively evaluated on 3 public data sets and a local data set with respect to existing state-of-the-art methods. On the 3 public data sets, the proposed flow achieves 78-97.5 classification accuracy. Also, the local data set, created using the information regarding presence of Diabetic Retinopathy lesions in fundus images, results in 85.3-95.7 than the existing methods. Thus, the proposed generalized flow can be useful for a wide range of application-oriented "big data sets".

    03/26/2016 ∙ by Matthew Bihis, et al. ∙ 0 share

    read it

  • Facial Expression Detection using Patch-based Eigen-face Isomap Networks

    Automated facial expression detection problem pose two primary challenges that include variations in expression and facial occlusions (glasses, beard, mustache or face covers). In this paper we introduce a novel automated patch creation technique that masks a particular region of interest in the face, followed by Eigen-value decomposition of the patched faces and generation of Isomaps to detect underlying clustering patterns among faces. The proposed masked Eigen-face based Isomap clustering technique achieves 75 and 66-73 faces in around 1 second per image. Also, betweenness centrality, Eigen centrality and maximum information flow can be used as network-based measures to identify the most significant training faces for expression classification tasks. The proposed method can be used in combination with feature-based expression classification methods in large data sets for improving expression classification accuracies.

    11/11/2015 ∙ by Sohini Roychowdhury, et al. ∙ 0 share

    read it