Mehul P. Sampat

Complex Wavelet Structural Similarity: A New Image Similarity Index

We introduce a new measure of image similarity called the complex wavelet structural similarity (CW-SSIM) index and show its applicability as a general purpose image similarity index. The key idea behind CW-SSIM is that certain image distortions lead to consistent phase changes in the local wavelet coefficients, and that a consistent phase shift of the coefficients does not change the structural content of the image. By conducting four case studies, we have demonstrated the superiority of the CW-SSIM index against other indices (e.g., Dice, Hausdorff distance) commonly used for assessing the similarity of a given pair of images. In addition, we show that the CW-SSIM index has a number of advantages. It is robust to small rotations and translations. It provides useful comparisons even without a preprocessing image registration step, which is essential for other indices. Moreover, it is computationally less expensive.

Early CNS neurodegeneration in radiologically isolated syndrome

Objective: Increasing evidence indicates that the thalamus may be a location of early neurodegeneration in multiple sclerosis (MS). Our objective was to identify the presence of gray matter volume loss and thinning in patients with radiologically isolated syndrome (RIS). Methods: Sixty-three participants were included in this case-control study. Twenty-one patients with RIS were age- and sex-matched to 42 healthy controls in a 1:2 ratio. All participants underwent brain MRIs on a single 3T scanner. After lesion segmentation and inpainting, 1 mm3-isometric T1-weighted images were submitted to FreeSurfer (v5.2). Normalized cortical and deep gray matter volumes were compared between patients with RIS and controls using t tests, and thalamic volumes were correlated with white matter lesion volumes using Pearson correlation. Exploratory cortical thickness maps were created. Results: Although traditional normalized total gray and white matter volumes were not statistically different between patients with RIS and controls, normalized left (0.0046 ± 0.0005 vs 0.0049 ± 0.0004, p = 0.006), right (0.0045 ± 0.0005 vs 0.0048 ± 0.0004, p = 0.008), and mean (0.0045 ± 0.0005 vs 0.0049 ± 0.0004, p = 0.004) thalamic volumes were significantly lower in patients with RIS (n = 21, mean age 41.9 ± 12.7 years) than in controls (n = 42, mean age 41.4 ± 11.2 years). Thalamic volumes correlated modestly with white matter lesion volumes (range: r = −0.35 to −0.47). Conclusion: Our data provide novel evidence of thalamic atrophy in RIS and are consistent with previous reports in early MS stages. Thalamic volume loss is present early in CNS demyelinating disease and should be further investigated as a metric associated with neurodegeneration.

Evidence based detection of spiculated masses and architectural distortions

Mass detection algorithms generally consist of two stages. The aim of the first stage is to detect all potential masses. In the second stage, the aim is to reduce the false-positives by classifying the detected objects as masses or normal tissue. In this paper, we present a new evidence based, stage-one algorithm for the detection of spiculated masses and architectural distortions. By evidence based, we mean that we use the statistics of the physical characteristics of these abnormalities to determine the parameters of the detection algorithm. Our stage-one algorithm consists of two steps, an enhancement step followed by a filtering step. In the first step, we propose a new technique for the enhancement of spiculations in which a linear filter is applied to the Radon transform of the image. In the second step, we filter the enhanced images with a new class of linear image filters called Radial Spiculation Filters. We have invented these filters specifically for detecting spiculated masses and architectural distortions that are marked by converging lines or spiculations. These filters are highly specific narrowband filters, which are designed to match the expected structures of these abnormalities and form a new class of wavelet-type filterbanks derived from optimal theories of filtering. A key aspect of this work is that each parameter of the filter has been incorporated to capture the variation in physical characteristics of spiculated masses and architectural distortions and that the parameters of the stage-one detection algorithm are determined by the physical measurements.

Supervised parametric and non-parametric classification of chromosome images

This paper describes a fully automatic chromosome classification algorithm for Multiplex Fluorescence In Situ Hybridization (M-FISH) images using supervised parametric and non-parametric techniques. M-FISH is a recently developed chromosome imaging method in which each chromosome is labelled with 5 fluors (dyes) and a DNA stain. The classification problem is modelled as a 25-class 6-feature pixel-by-pixel classification task. The 25 classes are the 24 types of human chromosomes and the background, while the six features correspond to the brightness of the dyes at each pixel. Maximum likelihood estimation, nearest neighbor and k-nearest neighbor methods are implemented for the classification. The highest classification accuracy is achieved with the k-nearest neighbor method and k=7 is an optimal value for this classification task.

A model-based framework for the detection of spiculated masses on mammography

The detection of lesions on mammography is a repetitive and fatiguing task. Thus, computer-aided detection systems have been developed to aid radiologists. The detection accuracy of current systems is much higher for clusters of microcalcifications than for spiculated masses. In this article, the authors present a new model-based framework for the detection of spiculated masses. The authors have invented a new class of linear filters, spiculated lesion filters, for the detection of converging lines or spiculations. These filters are highly specific narrowband filters, which are designed to match the expected structures of spiculated masses. As a part of this algorithm, the authors have also invented a novel technique to enhance spicules on mammograms. This entails filtering in the radon domain. They have also developed models to reduce the false positives due to normal linear structures. A key contribution of this work is that the parameters of the detection algorithm are based on measurements of physical properties of spiculated masses. The results of the detection algorithm are presented in the form of free-response receiver operating characteristic curves on images from the Mammographic Image Analysis Society and Digital Database for Screening Mammography databases.

In vivo evidence of glutamate toxicity in multiple sclerosis

There is increasing evidence that altered glutamate (Glu) homeostasis is involved in the pathophysiology of multiple sclerosis (MS). The aim of this study was to evaluate the in vivo effects of excess brain Glu on neuroaxonal integrity measured by N‐acetylaspartate (NAA), brain volume, and clinical outcomes in a large, prospectively followed cohort of MS subjects.

Detection of spiculated lesions in mammograms

In this paper, we present a new technique for the detection of spiculated masses in digitized mammograms. The techniques consist of two stages, enhancement of spiculations followed by the detection of the location where they converge. We describe a new algorithm for the enhancement and a new set of linear image filters which we have created for the detection stage. We have tested the algorithm on digitized mammograms obtained from the digital database for screening mammography (DDSM). Results of the detection algorithm are shown. Finally we show that the algorithm may be modified for the detection of architectural distortions.

Pixel-by-pixel classification of MFISH images

Multiplex Fluorescence In-Situ Hybridization (M-FISH) is a recently developed chromosome imaging method in which each chromosome is labelled with 5 fluors (dyes) and is also counterstained with DAPI. This paper proposes an automatic pixel by pixel classification algorithm for M-FISH images using a Bayes classifier. The M-FISH pixel classification was approached as a 25 class 6 feature pattern recognition problem. The classifier was trained and tested on non-overlapping data sets and an overall classification accuracy of 95% was obtained.

Snakules: A Model-Based Active Contour Algorithm for the Annotation of Spicules on Mammography

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.

Medulla Oblongata Volume: A Biomarker of Spinal Cord Damage and Disability in Multiple Sclerosis

BACKGROUND AND PURPOSE: While brain MR imaging is routinely performed, the MR imaging assessment of spinal cord pathology in multiple sclerosis (MS) is less frequent in clinical practice. The purpose of this study was to determine whether measurements of medulla oblongata volume (MOV) on routine brain MR imaging could serve as a biomarker of spinal cord damage and disability in MS. MATERIALS AND METHODS: We identified 45 patients with MS with both head and cervical spinal cord MR imaging and 29 age-matched and sex-matched healthy control subjects with head MR imaging. Disability was assessed by the expanded disability status scale (EDSS) and ambulation index (AI). MOV and upper cervical cord volume (UCCV) were manually segmented; semiautomated segmentation was used for brain parenchymal fraction (BPF). These measures were compared between groups, and linear regression models were built to predict disability. RESULTS: In the patients, MOV correlated significantly with UCCV (r = 0.67), BPF (r = 0.45), disease duration (r = −0.64), age (r = −0.47), EDSS score (r = −0.49) and AI (r = −0.52). Volume loss of the medulla oblongata was −0.008 cm3/year of age in patients with MS, but no significant linear relationship with age was found for healthy control subjects. The patients had a smaller MOV (mean ± SD, 1.02 ± 0.17 cm3) than healthy control subjects (1.15 ± 0.15 cm3), though BPF was unable to distinguish between these 2 groups. MOV was smaller in patients with progressive MS (secondary- progressive MS, 0.88 ± 0.19 cm3 and primary-progressive MS, 0.95 ± 0.30 cm3) than in patients with relapsing-remitting MS (1.08 ± 0.15 cm3). A model including both MOV and BPF better predicted AI than BPF alone (P = .04). Good reproducibility in MOV measurements was demonstrated for intrarater (intraclass correlation coefficient, 0.97), interrater (0.79), and scan rescan data (0.81). CONCLUSION: MOV is associated with disability in MS and can serve as a biomarker of spinal cord damage.