Article

Axial T2 Weighted MR Brain Image Retrieval Using Moment Features

Authors:
  • University of Technology and Applied Sciences Muscat
  • Digital University Kerala (DUK)
To read the full-text of this research, you can request a copy directly from the authors.

Abstract

Magnetic resonance images play a vital role in identifying various brain related problems. Some of the diseases of the brain show abnormalities predominately at a particular anatomical location which on MR appears at a slice at defined level. This paper proposes a novel technique to locate desired slice using Rotational, Scaling and Translational (RST) invariant features derived from a ternary encoded local binary pattern (LBP)image. The LBP image is obtained by labeling each pixel with a code of the texture primitive based on the local neighborhood. The ternary encoding on LBP identifies the boundary of the uniform region and thus reduces the time for calculating moments of different order. The distance function based on the RST features extracted from LBP between query and database image is used to retrieve similar images corresponds to the query image.

No full-text available

Request Full-text Paper PDF

To read the full-text of this research,
you can request a copy directly from the authors.

Conference Paper
This paper aims to develop an efficient content - based image retrieval approach for brain image database. The combination of Cohen-Daubechies-Feauveau (CDF) 9/7 wavelet and Local Ternary Co-occurrence Patterns (LTCoP) is used for feature extraction in solving the brain image retrieval problem. The experimental dataset used for the retrievalpurpose is from OASIS - MRI database. The mean precision rate is calculated for performance evaluation. The effectiveness of our approach is analyzed by comparing its performance with Gabor transform based local ternary co-occurrence pattern. The result shows that our approach is comparatively better than the existing method.
Article
Full-text available
The use of an open source image retrieval system for the retrieval of medical images in the medical case database system, CasImage, is discussed. A subset of the entire case database of more than 40,000 images with a total of 3752 images was taken for the evaluation of the retrieval performance. It was observed that a smaller number of grey levels leads to a better retrieval performance. The content-based image retrieval systems (CBIR) were found to be of great use in managing large medical image databases and PACS.
Article
Full-text available
Traumatic brain injury (TBI) is a major cause of death and disability. Computed Tomography (CT) scan is widely used in the diagnosis of TBI. Nowadays, large amount of TBI CT data is stacked in the hospital radiology department. Such data and the associated patient information contain valuable information for clinical diagnosis and outcome prediction. However, current hospital database system does not provide an efficient and intuitive tool for doctors to search out cases relevant to the current study case. In this paper, we present the TBIdoc system: a content-based image retrieval (CBIR) system which works on the TBI CT images. In this web-based system, user can query by uploading CT image slices from one study, retrieval result is a list of TBI cases ranked according to their 3D visual similarity to the query case. Specifically, cases of TBI CT images often present diffuse or focal lesions. In TBIdoc system, these pathological image features are represented as bin-based binary feature vectors. We use the Jaccard-Needham measure as the similarity measurement. Based on these, we propose a 3D similarity measure for computing the similarity score between two series of CT slices. nDCG is used to evaluate the system performance, which shows the system produces satisfactory retrieval results. The system is expected to improve the current hospital data management in TBI and to give better support for the clinical decision-making process. It may also contribute to the computer-aided education in TBI.
Conference Paper
Full-text available
This paper presents the MultiWaveMed system, which is a new software allowing to index and retrieve medical images through the comparison of their texture features. The features are extracted by wavelet transforms, and are organized in feature vectors. The system extracts the image texture features, computes the distance between the query image to all images in the database, through the comparison of their features, and retrieve de n most similar images regarding this kind of feature. The proposed system has implemented both Daubechies and Gabor wavelets. The feature vectors extracted from the images are used to organize the images through access methods, which are the basis to perform the query-by-content operations over the images. The focus of this paper is to show the utility of the wavelet transforms on medical image characterization and their suitability for image indexing and retrieval.
Conference Paper
Full-text available
This work aims at supporting the retrieval and indexing of medical images by extracting and organizing intrinsic features of them, more specifically texture attributes from images. A tool for obtaining the relevant textures was implemented This tool retrieves and classifies images using the extracted values, and allows the user to issue similarity queries. The application of the proposed method on images has given encouraging results that motivate to apply the method as a basis to more experiments, at diversified contexts. The accuracy degree obtained from the precision and recall plots was always over 90% for queries asking for similar images for up to 20% of the database.
Article
Full-text available
The aging population and the growing amount of medical data have increased the need for automated tools in the neurology departments. Although the researchers have been developing computerized methods to help the medical expert, these efforts have primarily emphasized to improve the effectiveness in single patient data, such as computing a brain lesion size. However, patient-to-patient comparison that should help improve diagnosis and therapy has not received much attention. To this effect, this paper introduces a fast and robust region-of-interest retrieval method for brain MR images. We make the following various contributions to the domains of brain MR image analysis, and search and retrieval system: 1) we show the potential and robustness of local structure information in the search and retrieval of brain MR images; 2) we provide analysis of two complementary features, local binary patterns (LBPs) and Kanade-Lucas-Tomasi feature points, and their comparison with a baseline method; 3) we show that incorporating spatial context in the features substantially improves accuracy; and 4) we automatically extract dominant LBPs and demonstrate their effectiveness relative to the conventional LBP approach. Comprehensive experiments on real and simulated datasets revealed that dominant LBPs with spatial context is robust to geometric deformations and intensity variations, and have high accuracy and speed even in pathological cases. The proposed method can not only aid the medical expert in disease diagnosis, or be used in scout (localizer) scans for optimization of acquisition parameters, but also supports low-power handheld devices.
Article
Full-text available
Content-based visual information retrieval (CBVIR) or content-based image retrieval (CBIR) has been one on the most vivid research areas in the field of computer vision over the last 10 years. The availability of large and steadily growing amounts of visual and multimedia data, and the development of the Internet underline the need to create thematic access methods that offer more than simple text-based queries or requests based on matching exact database fields. Many programs and tools have been developed to formulate and execute queries based on the visual or audio content and to help browsing large multimedia repositories. Still, no general breakthrough has been achieved with respect to large varied databases with documents of differing sorts and with varying characteristics. Answers to many questions with respect to speed, semantic descriptors or objective image interpretations are still unanswered.
Article
Full-text available
We propose a method to handle approximate searching by image content in medical image databases. Image content is represented by attributed relational graphs holding features of objects and relationships between objects. The method relies on the assumption that a fixed number of “labeled” or “expected” objects (e.g., “heart”, “lungs”, etc.) are common in all images of a given application domain in addition to a variable number of “unexpected” or “unlabeled” objects (e.g., “tumor”, “hematoma”, etc.). The method can answer queries by example, such as “find all X-rays that are similar to Smith's X-ray”. The stored images are mapped to points in a multidimensional space and are indexed using state-of-the-art database methods (R-trees). The proposed method has several desirable properties: (a) Database search is approximate, so that all images up to a prespecified degree of similarity (tolerance) are retrieved. (b) It has no “false dismissals” (i.e., all images qualifying query selection criteria are retrieved). (c) It is much faster than sequential scanning for searching in the main memory and on the disk (i.e., by up to an order of magnitude), thus scaling-up well for large databases
Article
Full-text available
Presents a review of 200 references in content-based image retrieval. The paper starts with discussing the working conditions of content-based retrieval: patterns of use, types of pictures, the role of semantics, and the sensory gap. Subsequent sections discuss computational steps for image retrieval systems. Step one of the review is image processing for retrieval sorted by color, texture, and local geometry. Features for retrieval are discussed next, sorted by: accumulative and global features, salient points, object and shape features, signs, and structural combinations thereof. Similarity of pictures and objects in pictures is reviewed for each of the feature types, in close connection to the types and means of feedback the user of the systems is capable of giving by interaction. We briefly discuss aspects of system engineering: databases, system architecture, and evaluation. In the concluding section, we present our view on: the driving force of the field, the heritage from computer vision, the influence on computer vision, the role of similarity and of interaction, the need for databases, the problem of evaluation, and the role of the semantic gap
Article
Full-text available
We propose a novel image retrieval framework centered around classification-driven search for a weighted similarity metric for image retrieval. This approach is firmly rooted in Bayes decision theory. Given a well-defined image set, we argue that image classification and image retrieval share fundamentally the same goal. Thus, the distance metric defining a classifier that performs well on the image set should also generate good results when used as the similarity metric for image retrieval. In this paper we report our methodology and initial results on neuroradiological image retrieval, where the approximate bilateral symmetry of normal human brains is exploited. 1 Introduction Existing "content-based" image retrieval systems depend on general visual properties such as color and texture to classify diverse, two-dimensional (2D) images [4, 12, 15, 11, 10, 13]. These general visual cues often fail to be effective discriminators for image sets taken within a single domain, where images ...
Article
This article presents a novel scale- and rotation-invariant detector and descriptor, coined SURF (Speeded-Up Robust Features). SURF approximates or even outperforms previously proposed schemes with respect to repeatability, distinctiveness, and robustness, yet can be computed and compared much faster. This is achieved by relying on integral images for image convolutions; by building on the strengths of the leading existing detectors and descriptors (specifically, using a Hessian matrix-based measure for the detector, and a distribution-based descriptor); and by simplifying these methods to the essential. This leads to a combination of novel detection, description, and matching steps. The paper encompasses a detailed description of the detector and descriptor and then explores the effects of the most important parameters. We conclude the article with SURF's application to two challenging, yet converse goals: camera calibration as a special case of image registration, and object recognition. Our experiments underline SURF's usefulness in a broad range of topics in computer vision.
Article
In the past few years, immense improvement was obtained in the field of content-based image retrieval (CBIR). Nevertheless, existing systems still fail when applied to medical image databases. Simple feature-extraction algorithms that operate on the entire image for characterization of color, texture, or shape cannot be related to the descriptive semantics of medical knowledge that is extracted from images by human experts. In this paper, we present a novel multi-step approach, which is specially designed for content-based image retrieval in medical applications (IRMA). In contrast to common approaches, the IRMA-concept is based on a conceptual and algorithmic separation of: (a) image categorization using global features, (b) geometry and contrast registration with respect to prototypes within the categories, (c) extraction of local features, (d) category and query dependent local feature selection, (e) index generation resulting in hierarchical multi-scale blob representations, (f) object identification that links a-priori knowledge on image content to the blobs, and (g) image retrieval processed on the abstract blob-level. The IRMA-concept comprises several benefits when compared to existing CBIR-systems. The image categories enable semantics by prototypes. Furthermore, each image might belong to several categories. A-priori knowledge on both image and query content is adjuncted to indexing. Therefore, the IRMA-concept provides a high mount of content understanding and enables intelligent queries on an abstract level of information. Hence, IRMA promises satisfactory query completion in medical applications.
Article
This paper evaluates the performance both of some texture measures which have been successfully used in various applications and of some new promising approaches proposed recently. For classification a method based on Kullback discrimination of sample and prototype distributions is used. The classification results for single features with one-dimensional feature value distributions and for pairs of complementary features with two-dimensional distributions are presented
Conference Paper
In the past few years, immense improvement was obtained in the field of content-based image retrieval. Nevertheless, existing systems still fail when applied to medical image databases. Simple feature-extraction algorithms that operate on the entire image for characterization of color, texture, or shape cannot be related to the descriptive semantics of medical knowledge that is extracted from images by human experts.
Article
This paper presents a method for extracting distinctive invariant features from images that can be used to perform reliable matching between different views of an object or scene. The features are invariant to image scale and rotation, and are shown to provide robust matching across a substantial range of affine distortion, change in 3D viewpoint, addition of noise, and change in illumination. The features are highly distinctive, in the sense that a single feature can be correctly matched with high probability against a large database of features from many images. This paper also describes an approach to using these features for object recognition. The recognition proceeds by matching individual features to a database of features from known objects using a fast nearest-neighbor algorithm, followed by a Hough transform to identify clusters belonging to a single object, and finally performing verification through least-squares solution for consistent pose parameters. This approach to recognition can robustly identify objects among clutter and occlusion while achieving near real-time performance.
Article
This paper focuses on the use of image-based machine learning techniques in medical image analysis. In particular, we present some variants of local binary patterns (LBP), which are widely considered the state of the art among texture descriptors. After we provide a detailed review of the literature about existing LBP variants and discuss the most salient approaches, along with their pros and cons, we report new experiments using several LBP-based descriptors and propose a set of novel texture descriptors for the representation of biomedical images. The standard LBP operator is defined as a gray-scale invariant texture measure, derived from a general definition of texture in a local neighborhood. Our variants are obtained by considering different shapes for the neighborhood calculation and different encodings for the evaluation of the local gray-scale difference. These sets of features are then used for training a machine-learning classifier (a stand-alone support vector machine). Extensive experiments are conducted using the following three datasets: Our results show that the novel variant named elongated quinary patterns (EQP) is a very performing method among those proposed in this work for extracting information from a texture in all the tested datasets. EQP is based on an elliptic neighborhood and a 5 levels scale for encoding the local gray-scale difference. Particularly interesting are the results on the widely studied 2D-HeLa dataset, where, to the best of our knowledge, the proposed descriptor obtains the highest performance among all the several texture descriptors tested in the literature.
Article
Image reference databases (IRDBs) are a recurrent research topic in medical imaging. Most IRDBs are designed to help experienced physicians in diagnostic tasks and require that users have prior extensive knowledge of the field for their use to be fruitful. Therefore, the educational potential of such image collections cannot be exploited thoroughly. In this paper we propose an image-indexing method to extend the functionalities of an existing medical IRDB and allow for its use in educational applications, as well as in computer-assisted diagnosis. Our method, based on the Kahrunen-Leève transform, has been used to develop a content-based search engine for tomographic image databases on which we are presently experimenting and which we aim to integrate into a working radiological IRDB installed at the University of Florence. Results achieved in our preliminary tests are also reported.
Article
The capacity to retrieve images containing objects with shapes similar to a query shape is desirable in medical image databases. We propose a similarity measure and an indexing mechanism for non-rigid comparison of shape which adds this capability to image databases. The (dis-)similarity measure is based on the observations that: (1) the geometry of the same organ in different subjects is not related by a strictly rigid transformation; and (2) the orientation of the organ plays a key role in comparing shape. We propose a similarity measure that computes a non-rigid mapping between curves and uses this mapping to compare oriented shape. We also show how KD-trees can index curves so that retrieval with our similarity measure is efficient. Experiments with real-world data from a database of magnetic resonance images are provided.
Article
Imaging-matching is an important research area in imaging informatics. We have developed and evaluated a novel diagnostic support tool (DST) based on medical image matching using MR brain images. The approach consists of two steps, database generation and image matching. The database contains pre-diagnosed MR brain images. As the images are added to the database, they are registered to the 3D Talairach coordinate system. In addition, regions of interests (ROI) are generated, and image-processing techniques are used to extract relevant image parameters related to the brain and diseases from the ROIs and from the entire MR image. The second step is to retrieve relevant information from the database by performing image matching. In this step, the physician first submits a query image. The DST computes the similarity between the query image and each of the images in the database, and then presents the most similar images to the user. Since the database contains pre-diagnosed images, the retrieved cases tend to contain relevant diagnostic information. To evaluate the usefulness of the DST in a clinical setting, pediatric brain diseases were used. The database contains 2500 pediatric patients between ages 0 and 18 with brain Magnetic Resonance (MR) images of known brain lesions. A testbed was established at the Children's Hospital Los Angeles (CHLA) for acquiring MR images from the PACS server of patients with known lesions. These images were matched against those in the DST pediatric brain MR database. An expert pediatric neuroradiologist evaluated the matched results. We found that in most cases, the image-matching method was able to quickly retrieve images with relevant diagnostic content. The evaluation method and results are given.
Conference Paper
This paper evaluates the performance both of some texture measures which have been successfully used in various applications and of some new promising approaches. For classification a method based on Kullback discrimination of sample and prototype distributions is used. The classification results for single features with one-dimensional feature value distributions and for pairs of complementary features with two-dimensional distributions are presented
Article
Investigates the problem of retrieving similar shapes from a large database; in particular, we focus on medical tumor shapes (finding tumors that are similar to a given pattern). We use a natural similarity function for shape matching, based on concepts from mathematical morphology, and we show how it can be lower-bounded by a set of shape features for safely pruning candidates, thus giving fast and correct output. These features can be organized in a spatial access method, leading to fast indexing for range queries and nearest-neighbor queries. In addition to the lower-bounding, our second contribution is the design of a fast algorithm for nearest-neighbor searching, achieving significant speedup while provably guaranteeing correctness. Our experiments demonstrate that roughly 90% of the candidates can be pruned using these techniques, resulting in up to 27 times better performance compared to sequential scanning
Comparing feature sets for content based image retrieval in a medical case database
  • H Müller
  • A Rosset
  • J.-P Vallét
3D Content-based CT Image Retrieval System for Traumatic Brain Injury
  • S Li
  • T Gong
  • J Wang
  • R Liu
  • C Tan
  • T Y Leong
  • S. Li