Technology & Engineering

Content-based Retrieval of Medical Images

Author: Paulo Mazzoncini de Azevedo-Marques

Publisher: Morgan & Claypool Publishers

ISBN:

Category: Technology & Engineering

Page: 143

View: 608

Content-based image retrieval (CBIR) is the process of retrieval of images from a database that are similar to a query image, using measures derived from the images themselves, rather than relying on accompanying text or annotation. To achieve CBIR, the contents of the images need to be characterized by quantitative features; the features of the query image are compared with the features of each image in the database and images having high similarity with respect to the query image are retrieved and displayed. CBIR of medical images is a useful tool and could provide radiologists with assistance in the form of a display of relevant past cases. One of the challenging aspects of CBIR is to extract features from the images to represent their visual, diagnostic, or application-specific information content. In this book, methods are presented for preprocessing, segmentation, landmarking, feature extraction, and indexing of mammograms for CBIR. The preprocessing steps include anisotropic diffusion and the Wiener filter to remove noise and perform image enhancement. Techniques are described for segmentation of the breast and fibroglandular disk, including maximum entropy, a moment-preserving method, and Otsu's method. Image processing techniques are described for automatic detection of the nipple and the edge of the pectoral muscle via analysis in the Radon domain. By using the nipple and the pectoral muscle as landmarks, mammograms are divided into their internal, external, upper, and lower parts for further analysis. Methods are presented for feature extraction using texture analysis, shape analysis, granulometric analysis, moments, and statistical measures. The CBIR system presented provides options for retrieval using the Kohonen self-organizing map and the k-nearest-neighbor method. Methods are described for inclusion of expert knowledge to reduce the semantic gap in CBIR, including the query point movement method for relevance feedback (RFb). Analysis of performance is described in terms of precision, recall, and relevance-weighted precision of retrieval. Results of application to a clinical database of mammograms are presented, including the input of expert radiologists into the CBIR and RFb processes. Models are presented for integration of CBIR and computer-aided diagnosis (CAD) with a picture archival and communication system (PACS) for efficient workflow in a hospital. Table of Contents: Introduction to Content-based Image Retrieval / Mammography and CAD of Breast Cancer / Segmentation and Landmarking of Mammograms / Feature Extraction and Indexing of Mammograms / Content-based Retrieval of Mammograms / Integration of CBIR and CAD into Radiological Workflow
Diagnostic imaging

Radon Projections as Image Descriptors for Content-based Retrieval of Medical Images

Author: Aditya Sriram

Publisher:

ISBN:

Category: Diagnostic imaging

Page: 62

View: 835

Clinical analysis and medical diagnosis of diverse diseases adopt medical imaging techniques to empower specialists to perform their tasks by visualizing internal body organs and tissues for classifying and treating diseases at an early stage. Content-Based Image Retrieval (CBIR) systems are a set of computer vision techniques to retrieve similar images from a large database based on proper image representations. Particularly in radiology and histopathology, CBIR is a promising approach to effectively screen, understand, and retrieve images with similar level of semantic descriptions from a database of previously diagnosed cases to provide physicians with reliable assistance for diagnosis, treatment planning and research. Over the past decade, the development of CBIR systems in medical imaging has expedited due to the increase in digitized modalities, an increase in computational efficiency (e.g., availability of GPUs), and progress in algorithm development in computer vision and artificial intelligence. Hence, medical specialists may use CBIR prototypes to query similar cases from a large image database based solely on the image content (and no text). Understanding the semantics of an image requires an expressive descriptor that has the ability to capture and to represent unique and invariant features of an image. Radon transform, one of the oldest techniques widely used in medical imaging, can capture the shape of organs in form of a one-dimensional histogram by projecting parallel rays through a two-dimensional object of concern at a specific angle. In this work, the Radon transform is re-designed to (i) extract features and (ii) generate a descriptor for content-based retrieval of medical images. Radon transform is applied to feed a deep neural network instead of raw images in order to improve the generalization of the network. Specifically, the framework is composed of providing Radon projections of an image to a deep autoencoder, from which the deepest layer is isolated and fed into a multi-layer perceptron for classification. This approach enables the network to (a) train much faster as the Radon projections are computationally inexpensive compared to raw input images, and (b) perform more accurately as Radon projections can make more pronounced and salient features to the network compared to raw images. This framework is validated on a publicly available radiography data set called "Image Retrieval in Medical Applications" (IRMA), consisting of 12,677 train and 1,733 test images, for which an classification accuracy of approximately 82% is achieved, outperforming all autoencoder strategies reported on the Image Retrieval in Medical Applications (IRMA) dataset. The classification accuracy is calculated by dividing the total IRMA error, a calculation outlined by the authors of the data set, with the total number of test images. Finally, a compact handcrafted image descriptor based on Radon transform was designed in this work that is called "Forming Local Intersections of Projections" (FLIP). The FLIP descriptor has been designed, through numerous experiments, for representing histopathology images. The FLIP descriptor is based on Radon transform wherein parallel projections are applied in a local 3x3 neighborhoods with 2 pixel overlap of gray-level images (staining of histopathology images is ignored). Using four equidistant projection directions in each window, the characteristics of the neighborhood is quantified by taking an element-wise minimum between each adjacent projection in each window. Thereafter, the FLIP histogram (descriptor) for each image is constructed. A multi-resolution FLIP (mFLIP) scheme is also proposed which is observed to outperform many state-of-the-art methods, among others deep features, when applied on the histopathology data set KIMIA Path24. Experiments show a total classification accuracy of approximately 72% using SVM classification, which surpasses the current benchmark of approximately 66% on the KIMIA Path24 data set.
Computers

Medinfo 2007

Author: Klaus A. Kuhn

Publisher: Ios PressInc

ISBN:

Category: Computers

Page: 1499

View: 593

The papers presented are refereed and from all over the world. They reflect the breadth and depth of the field of biomedical and health informatics, covering topics such as; health information systems, knowledge and data management, education, standards, consumer health and human factors, emerging technologies, sustainability, organizational and economic issues, genomics, and image and signal processing. As this volume carries such a wide collection, it will be of great interest to anyone engaged in biomedical and health informatics research and application.

Automatic Medical Image Classification for Content-based Image Retrieval Systems

Author:

Publisher:

ISBN:

Category:

Page: 82

View: 858

In hospitals today, medical images are normally processed and saved digitally in Picture Archiving and Communication Systems (PACS) along with some text descriptions within Digital Communication (DICOM) standards. Additional information saved with the image could include a doctor's name, patient identification, etc. This information is used to retrieve medical images, but text query statements frequently ask for information that is not a part of these text descriptors or labels. This situation will obviously have a negative effect on the result of a query submitted to retrieve the image. Low-level image features should help avoid this problem. Low-level features are those that are measurable and can be automatically extracted from an image. These features include color, shape, and texture. This research project investigated a method to link low-level features that can be automatically extracted from the image to high-level features that are represented in the textual Image Retrieval for Medical Application (IRMA) code included in test collection of images provided for this project. The second project goal was to use semantic types included in the IRMA codes (e.g. plain radiography from image modality, reproductive system form biological system facet) to expand text queries so a content-based image retrieval system can respond more effectively to specific queries. We used a machine learning approach to identify the link between low-level features and text descriptions to automatically assign the semantic types from IRMA. We used a standard dataset of images released by the ImageCLEF2005 conference to participating groups. We indexed the whole dataset of 9,000 images using the GNU Image Finding Tool (GIFT), and extracted images features using the same application. We used image features, as well as the manually assigned IRMA classification code to train a multi-class support vector machine (SVM Multi-class). Our results showed that some medical images are easily classified using low-level features. These results also showed that the performance of the classifier was affected by the uneven distribution of images in each class of the ImageCLEF2005 campaign dataset. Where the images were unique in any one of the four main facets of the IRMA code, the classifier identified them correctly.
Medical

Medical Imaging 2006

Author: Osman Ratib

Publisher: Society of Photo Optical

ISBN:

Category: Medical

Page: 410

View: 652

Proceedings of SPIE present the original research papers presented at SPIE conferences and other high-quality conferences in the broad-ranging fields of optics and photonics. These books provide prompt access to the latest innovations in research and technology in their respective fields. Proceedings of SPIE are among the most cited references in patent literature.
Computers

Medical Content-Based Retrieval for Clinical Decision Support

Author: Hayit Greenspan

Publisher: Springer

ISBN:

Category: Computers

Page: 145

View: 867

This book constitutes the refereed proceedings of the Third MICCAI Workshop on Medical Content-Based Retrieval for Clinical Decision Support, MCBR-CBS 2012, held in Nice, France, in October 2012. The 10 revised full papers presented together with 2 invited talks were carefully reviewed and selected from 15 submissions. The papers are divided on several topics on image analysis of visual or multimodal medical data (X-ray, MRI, CT, echo videos, time series data), machine learning of disease correlations in visual or multimodal data, algorithms for indexing and retrieval of data from visual or multimodal medical databases, disease model-building and clinical decision support systems based on visual or multimodal analysis, algorithms for medical image retrieval or classification, systems of retrieval or classification using the ImageCLEF collection.
Diagnostic imaging

Medical Image Storage Sysytem [sic] for Metadata-based Retrieval

Author: Selwyn Onyebuchi Igwe

Publisher:

ISBN:

Category: Diagnostic imaging

Page: 348

View: 361

Large image databases have been used in various applications and in recent years. The major prerequisite of these databases is the means by which their contents can be indexed and retrieved. This dissertation presents an attempt to improve image storage using image data representation model that integrates both metadata and content-based image description in ORDBMS (Object Relational Database Management systems). This dissertation research is verified using real examples from the medical domain. Both image and salient objects are considered in this model. A prototype called MISS (Medical Image Storage System) has been realized to validate the key aspect of the approach used. This research work also presents initial work on the design and implementation of a prototype Medical Image Database System for the core medical image modalities. Based on a novel image data model and an original data repository model, this representation also supports salient object-relational data and adheres to the Digital Imaging and Communication in Medicine (DICOM) Standard. This standard, along with storage, metadata retrieval and processing of medical images are widely studied and researched in the domain of medical imaging. The efficiency of any image retrieval is strongly related to the representation of the model. The better the features of the image are represented in the metadata, the more efficient the image retrieval technique is able to satisfy complex queries. An object-relational database such as Oracle's multimedia formerly known as Oracle interMedia can provide a seamless integration of image data and metadata. A sample prototype application is presented in this research work. This representation can be applied to different application areas using the Object-Relational DBMS model. The Image databases are partitioned into similar images either by using a cluster generation technique, or by using external information about the content of the image. It is also important to state that the research study only focuses on efficient medical imaging storage and retrieval using metadata and not on content-based retrieval (CBR) using image processing techniques.
Technology & Engineering

Medical Imaging 2005

Author: Osman Ratib

Publisher: Society of Photo Optical

ISBN:

Category: Technology & Engineering

Page: 558

View: 761

Proceedings of SPIE present the original research papers presented at SPIE conferences and other high-quality conferences in the broad-ranging fields of optics and photonics. These books provide prompt access to the latest innovations in research and technology in their respective fields. Proceedings of SPIE are among the most cited references in patent literature.
Technology & Engineering

Medical Imaging 2004

Author: Osman Ratib

Publisher: Society of Photo Optical

ISBN:

Category: Technology & Engineering

Page: 438

View: 280

Proceedings of SPIE present the original research papers presented at SPIE conferences and other high-quality conferences in the broad-ranging fields of optics and photonics. These books provide prompt access to the latest innovations in research and technology in their respective fields. Proceedings of SPIE are among the most cited references in patent literature.
Business & Economics

Medical Content-Based Retrieval for Clinical Decision Support

Author: Barbara Caputo

Publisher: Springer Science & Business Media

ISBN:

Category: Business & Economics

Page: 119

View: 318

The LNCS series reports state-of-the-art results in computer science research, development, and education, at a high level and in both printed and electronic form. Enjoying tight cooperation with the R&D community, with numerous individuals, as well as with prestigious organizations and societies, LNCS has grown into the most comprehensive computer science research forum available.
Technology & Engineering

Storage and Retrieval for Image and Video Databases VII

Author: Minerva Ming-Yee Yeung

Publisher: Society of Photo Optical

ISBN:

Category: Technology & Engineering

Page: 746

View: 582

A collection of 69 papers which were presented at the IS&T/SPIE Electronic Imaging Symposium, 1999. They appear in 13 sessions on subjects such as: image retrieval applications; multimedia management and retrieval systems; video retrieval; and image browsing.
Content-based image retrieval

Content Based Image Retrieval for Bio-medical Images

Author: Vikas Nahar

Publisher:

ISBN:

Category: Content-based image retrieval

Page: 168

View: 908

"Content Based Image Retrieval System (CBIR) is used to retrieve images similar to the query image. These systems have a wide range of applications in various fields. Medical subject headings, key words, and bibliographic references can be augmented with the images present within the articles to help clinicians to potentially improve the relevance of articles found in the querying process. In this research, image feature analysis and classification techniques are explored to differentiate images found in biomedical articles which have been categorized based on modality and utility. Examples of features examined in this research include: features based on different histograms of the image, texture features, fractal dimensions etc. Classification algorithms used for categorization were 1) Mean shift clustering 2) Radial basis clustering. Different combinations of features were selected for classification purposes and it was observed that features incorporating soft decision based HSV histogram features give the best results. A library of features was then developed which can be used in RapidMiner. Experimental results for various combinations of features have also been included"--Abstract, leaf iii.
Computers

Proceedings

Author: Roland R. Wagner

Publisher: IEEE Computer Society

ISBN:

Category: Computers

Page: 770

View: 332

This volume contains papers from the 1997 Database and Expert Systems Applications (DEXA '97), 8th International Workshop.