Special Issue "Machine Learning for Medical Imaging"

Quicklinks

A special issue of Algorithms (ISSN 1999-4893).

Deadline for manuscript submissions: closed (31 December 2009)

Special Issue Editor

Guest Editor
Dr. Kenji Suzuki (Website)

Associate Professor of Electrical and Computer Engineering, Medical Imaging Research Center, Illinois Institute of Technology, Chicago, IL 60616, USA
Phone: +1 312 567 5232
Interests: machine learning in medical imaging, computation intelligence in medical imaging, computer-aided detection and diagnosis, medical image processing and analysis

Special Issue Information

Summary: Medical imaging is an indispensable tool of patients’ healthcare in modern medicine. Machine leaning plays an essential role in the medical imaging field, including medical image analysis, computer-aided diagnosis, organ/lesion segmentation, image fusion, image-guided therapy, image annotation and image retrieval, because objects such as lesions and anatomy in medical images cannot be modeled accurately by simple equations; thus, tasks in medical imaging require learning from examples. Because of its essential needs, machine learning for medical imaging is one of the most promising, growing fields. As medical imaging has been advancing with the introduction of new imaging modalities and methodologies such as cone-beam/multi-slice CT, positron-emission tomography (PET)-CT, tomosynthesis, diffusion-weighted magnetic resonance imaging (MRI), electrical impedance tomography and diffuse optical tomography, new machine-learning algorithms/applications are demanded in the medical imaging field. Areas of interest in this special issue are all aspects of machine-learning research for medical imaging/images including, but not limited to:
  • Computer-aided detection/diagnosis (e.g., for lung cancer, breast cancer, colon cancer, liver cancer, acute disease, chronic disease, osteoporosis)
  • Machine learning (e.g., with support vector machines, statistical methods, manifold-space-based methods, artificial neural networks) applications to medical images with 2D, 3D and 4D data.
  • Multi-modality fusion (e.g., PET/CT, projection X-ray/CT, X-ray/ultrasound)
  • Medical image analysis (e.g., pattern recognition, classification, segmentation) of lesions, lesion stage, organs, anatomy, status of disease and medical data
  • Image reconstruction (e.g., expectation maximization (EM) algorithm, statistical methods) for medical images (e.g., CT, PET, MRI, X-ray)
  • Biological image analysis (e.g., biological response monitoring, biomarker tracking/detection)
  • Image fusion of multiple modalities, multiple phases and multiple angles
  • Image retrieval (e.g., lesion similarity, context-based)
  • Gene data analysis (e.g., genotype/phenotype classification/identification)
  • Molecular/pathologic image analysis
  • Dynamic, functional, physiologic, and anatomic imaging.

Keywords

  • computer-aided diagnosis
  • artificial neural networks
  • support vector machines
  • manifold, classification
  • pattern recognition
  • image reconstruction
  • medical image analysis
  • statistical pattern recognition
  • segmentation
  • image fusion
  • image retrieval
  • biological imaging
  • multiple modalities
  • gene
  • X-ray
  • CT
  • MRI
  • PET
  • ultrasound

Published Papers (11 papers)

View options order results:
result details:
Displaying articles 1-11
Export citation of selected articles as:

Research

Jump to: Review

Open AccessArticle Edge Detection from MRI and DTI Images with an Anisotropic Vector Field Flow Using a Divergence Map
Algorithms 2012, 5(4), 636-653; doi:10.3390/a5040636
Received: 31 July 2012 / Revised: 5 November 2012 / Accepted: 3 December 2012 / Published: 13 December 2012
Cited by 1 | PDF Full-text (1412 KB) | HTML Full-text | XML Full-text
Abstract
The aim of this work is the extraction of edges from Magnetic Resonance Imaging (MRI) and Diffusion Tensor Imaging (DTI) images by a deformable contour procedure, using an external force field derived from an anisotropic flow. Moreover, we introduce a divergence map [...] Read more.
The aim of this work is the extraction of edges from Magnetic Resonance Imaging (MRI) and Diffusion Tensor Imaging (DTI) images by a deformable contour procedure, using an external force field derived from an anisotropic flow. Moreover, we introduce a divergence map in order to check the convergence of the process. As we know from vector calculus, divergence is a measure of the magnitude of a vector field convergence at a given point. Thus by means level curves of the divergence map, we have automatically selected an initial contour for the deformation process. If the initial curve includes the areas from which the vector field diverges, it will be able to push the curve towards the edges. Furthermore the divergence map highlights the presence of curves pointing to the most significant geometric parts of boundaries corresponding to high curvature values. In this way, the skeleton of the extracted object will be rather well defined and may subsequently be employed in shape analysis and morphological studies. Full article
(This article belongs to the Special Issue Machine Learning for Medical Imaging)
Open AccessArticle Recognition of Pulmonary Nodules in Thoracic CT Scans Using 3-D Deformable Object Models of Different Classes
Algorithms 2010, 3(2), 125-144; doi:10.3390/a3020125
Received: 1 February 2010 / Revised: 16 February 2010 / Accepted: 22 March 2010 / Published: 31 March 2010
Cited by 3 | PDF Full-text (404 KB) | HTML Full-text | XML Full-text
Abstract
The present paper describes a novel recognition method of pulmonary nodules (i.e., cancer candidates) in thoracic computed tomography scans by use of three-dimensional spherical and cylindrical models that represent nodules and blood vessels, respectively. The anatomical validity of these object [...] Read more.
The present paper describes a novel recognition method of pulmonary nodules (i.e., cancer candidates) in thoracic computed tomography scans by use of three-dimensional spherical and cylindrical models that represent nodules and blood vessels, respectively. The anatomical validity of these object models and their fidelity to computed tomography scans are evaluated based on the Bayes theorem. The nodule recognition is employed by the maximum a posteriori estimation. The proposed method is applied to 26 actual computed tomography scans, and experimental results are shown. Full article
(This article belongs to the Special Issue Machine Learning for Medical Imaging)
Open AccessArticle Breast Cancer Detection with Gabor Features from Digital Mammograms
Algorithms 2010, 3(1), 44-62; doi:10.3390/a3010044
Received: 28 October 2009 / Revised: 14 January 2010 / Accepted: 14 January 2010 / Published: 19 January 2010
Cited by 19 | PDF Full-text (831 KB) | HTML Full-text | XML Full-text
Abstract
A new breast cancer detection algorithm, named the “Gabor Cancer Detection” (GCD) algorithm, utilizing Gabor features is proposed. Three major steps are involved in the GCD algorithm, preprocessing, segmentation (generating alarm segments), and classification (reducing false alarms). In preprocessing, a digital mammogram [...] Read more.
A new breast cancer detection algorithm, named the “Gabor Cancer Detection” (GCD) algorithm, utilizing Gabor features is proposed. Three major steps are involved in the GCD algorithm, preprocessing, segmentation (generating alarm segments), and classification (reducing false alarms). In preprocessing, a digital mammogram is down-sampled, quantized, denoised and enhanced. Nonlinear diffusion is used for noise suppression. In segmentation, a band-pass filter is formed by rotating a 1-D Gaussian filter (off center) in frequency space, termed as “Circular Gaussian Filter” (CGF). A CGF can be uniquely characterized by specifying a central frequency and a frequency band. A mass or calcification is a space-occupying lesion and usually appears as a bright region on a mammogram. The alarm segments (suspicious to be masses/calcifications) can be extracted out using a threshold that is adaptively decided upon the histogram analysis of the CGF-filtered mammogram. In classification, a Gabor filter bank is formed with five bands by four orientations (horizontal, vertical, 45 and 135 degree) in Fourier frequency domain. For each mammographic image, twenty Gabor-filtered images are produced. A set of edge histogram descriptors (EHD) are then extracted from 20 Gabor images for classification. An EHD signature is computed with four orientations of Gabor images along each band and five EHD signatures are then joined together to form an EHD feature vector of 20 dimensions. With the EHD features, the fuzzy C-means clustering technique and k-nearest neighbor (KNN) classifier are used to reduce the number of false alarms. The experimental results tested on the DDSM database (University of South Florida) show the promises of GCD algorithm in breast cancer detection, which achieved TP (true positive rate) = 90% at FPI (false positives per image) = 1.21 in mass detection; and TP = 93% at FPI = 1.19 in calcification detection. Full article
(This article belongs to the Special Issue Machine Learning for Medical Imaging)
Figures

Open AccessArticle A Robust and Fast System for CTC Computer-Aided Detection of Colorectal Lesions
Algorithms 2010, 3(1), 21-43; doi:10.3390/a3010021
Received: 9 November 2009 / Revised: 14 December 2009 / Accepted: 23 December 2009 / Published: 5 January 2010
Cited by 24 | PDF Full-text (2432 KB) | HTML Full-text | XML Full-text
Abstract
We present a complete, end-to-end computer-aided detection (CAD) system for identifying lesions in the colon, imaged with computed tomography (CT). This system includes facilities for colon segmentation, candidate generation, feature analysis, and classification. The algorithms have been designed to offer robust performance [...] Read more.
We present a complete, end-to-end computer-aided detection (CAD) system for identifying lesions in the colon, imaged with computed tomography (CT). This system includes facilities for colon segmentation, candidate generation, feature analysis, and classification. The algorithms have been designed to offer robust performance to variation in image data and patient preparation. By utilizing efficient 2D and 3D processing, software optimizations, multi-threading, feature selection, and an optimized cascade classifier, the CAD system quickly determines a set of detection marks. The colon CAD system has been validated on the largest set of data to date, and demonstrates excellent performance, in terms of its high sensitivity, low false positive rate, and computational efficiency. Full article
(This article belongs to the Special Issue Machine Learning for Medical Imaging)
Figures

Open AccessArticle A Clinical Decision Support Framework for Incremental Polyps Classification in Virtual Colonoscopy
Algorithms 2010, 3(1), 1-20; doi:10.3390/a3010001
Received: 28 September 2009 / Accepted: 6 October 2009 / Published: 4 January 2010
Cited by 4 | PDF Full-text (405 KB) | HTML Full-text | XML Full-text
Abstract
We present in this paper a novel dynamic learning method for classifying polyp candidate detections in Computed Tomographic Colonography (CTC) using an adaptation of the Least Square Support Vector Machine (LS-SVM). The proposed technique, called Weighted Proximal Support Vector Machines (WP-SVM [...] Read more.
We present in this paper a novel dynamic learning method for classifying polyp candidate detections in Computed Tomographic Colonography (CTC) using an adaptation of the Least Square Support Vector Machine (LS-SVM). The proposed technique, called Weighted Proximal Support Vector Machines (WP-SVM), extends the offline capabilities of the SVM scheme to address practical CTC applications. Incremental data are incorporated in the WP-SVM as a weighted vector space, and the only storage requirements are the hyperplane parameters. WP-SVM performance evaluation based on 169 clinical CTC cases using a 3D computer-aided diagnosis (CAD) scheme for feature reduction comparable favorably with previously published CTC CAD studies that have however involved only binary and offline classification schemes. The experimental results obtained from iteratively applying WP-SVM to improve detection sensitivity demonstrate its viability for incremental learning, thereby motivating further follow on research to address a wider range of true positive subclasses such as pedunculated, sessile, and flat polyps, and over a wider range of false positive subclasses such as folds, stool, and tagged materials. Full article
(This article belongs to the Special Issue Machine Learning for Medical Imaging)
Open AccessArticle Image Similarity to Improve the Classification of Breast Cancer Images
Algorithms 2009, 2(4), 1503-1525; doi:10.3390/a2041503
Received: 12 October 2009 / Revised: 20 November 2009 / Accepted: 25 November 2009 / Published: 1 December 2009
PDF Full-text (677 KB) | HTML Full-text | XML Full-text
Abstract
Techniques in image similarity can be used to improve the classification of breast cancer images. Breast cancer images in the mammogram modality have an abundance of non-cancerous structures that are similar to cancer, which make classification of images as containing cancer especially [...] Read more.
Techniques in image similarity can be used to improve the classification of breast cancer images. Breast cancer images in the mammogram modality have an abundance of non-cancerous structures that are similar to cancer, which make classification of images as containing cancer especially difficult to work with. Only the cancerous part of the image is relevant, so the techniques must learn to recognize cancer in noisy mammograms and extract features from that cancer to appropriately classify images. There are also many types or classes of cancer with different characteristics over which the system must work. Mammograms come in sets of four, two images of each breast, which enables comparison of the left and right breast images to help determine relevant features and remove irrelevant features. In this work, image feature clustering is done to reduce the noise and the feature space, and the results are used in a distance function that uses a learned threshold in order to produce a classification. The threshold parameter of the distance function is learned simultaneously with the underlying clustering and then integrated to produce an agglomeration that is relevant to the images. This technique can diagnose breast cancer more accurately than commercial systems and other published results. Full article
(This article belongs to the Special Issue Machine Learning for Medical Imaging)
Open AccessArticle Predicting Radiological Panel Opinions Using a Panel of Machine Learning Classifiers
Algorithms 2009, 2(4), 1473-1502; doi:10.3390/a2041473
Received: 27 September 2009 / Revised: 27 October 2009 / Accepted: 11 November 2009 / Published: 30 November 2009
Cited by 23 | PDF Full-text (650 KB) | HTML Full-text | XML Full-text
Abstract
This paper uses an ensemble of classifiers and active learning strategies to predict radiologists’ assessment of the nodules of the Lung Image Database Consortium (LIDC). In particular, the paper presents machine learning classifiers that model agreement among ratings in seven semantic characteristics: [...] Read more.
This paper uses an ensemble of classifiers and active learning strategies to predict radiologists’ assessment of the nodules of the Lung Image Database Consortium (LIDC). In particular, the paper presents machine learning classifiers that model agreement among ratings in seven semantic characteristics: spiculation, lobulation, texture, sphericity, margin, subtlety, and malignancy. The ensemble of classifiers (which can be considered as a computer panel of experts) uses 64 image features of the nodules across four categories (shape, intensity, texture, and size) to predict semantic characteristics. The active learning begins the training phase with nodules on which radiologists’ semantic ratings agree, and incrementally learns how to classify nodules on which the radiologists do not agree. Using our proposed approach, the classification accuracy of the ensemble of classifiers is higher than the accuracy of a single classifier. In the long run, our proposed approach can be used to increase consistency among radiological interpretations by providing physicians a “second read”. Full article
(This article belongs to the Special Issue Machine Learning for Medical Imaging)
Open AccessArticle CADrx for GBM Brain Tumors: Predicting Treatment Response from Changes in Diffusion-Weighted MRI
Algorithms 2009, 2(4), 1350-1367; doi:10.3390/a2041350
Received: 1 August 2009 / Revised: 22 September 2009 / Accepted: 3 November 2009 / Published: 16 November 2009
Cited by 5 | PDF Full-text (1074 KB) | HTML Full-text | XML Full-text
Abstract
The goal of this study was to develop a computer-aided therapeutic response (CADrx) system for early prediction of drug treatment response for glioblastoma multiforme (GBM) brain tumors with diffusion weighted (DW) MR images. In conventional Macdonald assessment, tumor response is assessed nine [...] Read more.
The goal of this study was to develop a computer-aided therapeutic response (CADrx) system for early prediction of drug treatment response for glioblastoma multiforme (GBM) brain tumors with diffusion weighted (DW) MR images. In conventional Macdonald assessment, tumor response is assessed nine weeks or more post-treatment. However, we will investigate the ability of DW-MRI to assess response earlier, at five weeks post treatment. The apparent diffusion coefficient (ADC) map, calculated from DW images, has been shown to reveal changes in the tumor’s microenvironment preceding morphologic tumor changes. ADC values in treated brain tumors could theoretically both increase due to the cell kill (and thus reduced cell density) and decrease due to inhibition of edema. In this study, we investigated the effectiveness of features that quantify changes from pre- and post-treatment tumor ADC histograms to detect treatment response. There are three parts to this study: first, tumor regions were segmented on T1w contrast enhanced images by Otsu’s thresholding method, and mapped from T1w images onto ADC images by a 3D region of interest (ROI) mapping tool using DICOM header information; second, ADC histograms of the tumor region were extracted from both pre- and five weeks post-treatment scans, and fitted by a two-component Gaussian mixture model (GMM). The GMM features as well as standard histogram-based features were extracted. Finally, supervised machine learning techniques were applied for classification of responders or non-responders. The approach was evaluated with a dataset of 85 patients with GBM under chemotherapy, in which 39 responded and 46 did not, based on tumor volume reduction. We compared adaBoost, random forest and support vector machine classification algorithms, using ten-fold cross validation, resulting in the best accuracy of 69.41% and the corresponding area under the curve (Az) of 0.70. Full article
(This article belongs to the Special Issue Machine Learning for Medical Imaging)

Review

Jump to: Research

Open AccessReview Algorithms for Non-Negatively Constrained Maximum Penalized Likelihood Reconstruction in Tomographic Imaging
Algorithms 2013, 6(1), 136-160; doi:10.3390/a6010136
Received: 28 November 2012 / Revised: 18 February 2013 / Accepted: 19 February 2013 / Published: 12 March 2013
PDF Full-text (297 KB) | HTML Full-text | XML Full-text
Abstract
Image reconstruction is a key component in many medical imaging modalities. The problem of image reconstruction can be viewed as a special inverse problem where the unknown image pixel intensities are estimated from the observed measurements. Since the measurements are usually noise [...] Read more.
Image reconstruction is a key component in many medical imaging modalities. The problem of image reconstruction can be viewed as a special inverse problem where the unknown image pixel intensities are estimated from the observed measurements. Since the measurements are usually noise contaminated, statistical reconstruction methods are preferred. In this paper we review some non-negatively constrained simultaneous iterative algorithms for maximum penalized likelihood reconstructions, where all measurements are used to estimate all pixel intensities in each iteration. Full article
(This article belongs to the Special Issue Machine Learning for Medical Imaging)
Open AccessReview Computer-Aided Diagnosis Systems for Brain Diseases in Magnetic Resonance Images
Algorithms 2009, 2(3), 925-952; doi:10.3390/a2030925
Received: 27 March 2009 / Revised: 6 June 2009 / Accepted: 2 July 2009 / Published: 10 July 2009
Cited by 19 | PDF Full-text (2489 KB) | HTML Full-text | XML Full-text
Abstract
This paper reviews the basics and recent researches of computer-aided diagnosis (CAD) systems for assisting neuroradiologists in detection of brain diseases, e.g., asymptomatic unruptured aneurysms, Alzheimer's disease, vascular dementia, and multiple sclerosis (MS), in magnetic resonance (MR) images. The CAD systems [...] Read more.
This paper reviews the basics and recent researches of computer-aided diagnosis (CAD) systems for assisting neuroradiologists in detection of brain diseases, e.g., asymptomatic unruptured aneurysms, Alzheimer's disease, vascular dementia, and multiple sclerosis (MS), in magnetic resonance (MR) images. The CAD systems consist of image feature extraction based on image processing techniques and machine learning classifiers such as linear discriminant analysis, artificial neural networks, and support vector machines. We introduce useful examples of the CAD systems in the neuroradiology, and conclude with possibilities in the future of the CAD systems for brain diseases in MR images. Full article
(This article belongs to the Special Issue Machine Learning for Medical Imaging)
Open AccessReview Computer-Aided Diagnosis in Mammography Using Content-Based Image Retrieval Approaches: Current Status and Future Perspectives
Algorithms 2009, 2(2), 828-849; doi:10.3390/a2020828
Received: 29 April 2009 / Revised: 28 May 2009 / Accepted: 28 May 2009 / Published: 4 June 2009
Cited by 29 | PDF Full-text (178 KB) | HTML Full-text | XML Full-text
Abstract
As the rapid advance of digital imaging technologies, the content-based image retrieval (CBIR) has became one of the most vivid research areas in computer vision. In the last several years, developing computer-aided detection and/or diagnosis (CAD) schemes that use CBIR to search [...] Read more.
As the rapid advance of digital imaging technologies, the content-based image retrieval (CBIR) has became one of the most vivid research areas in computer vision. In the last several years, developing computer-aided detection and/or diagnosis (CAD) schemes that use CBIR to search for the clinically relevant and visually similar medical images (or regions) depicting suspicious lesions has also been attracting research interest. CBIR-based CAD schemes have potential to provide radiologists with “visual aid” and increase their confidence in accepting CAD-cued results in the decision making. The CAD performance and reliability depends on a number of factors including the optimization of lesion segmentation, feature selection, reference database size, computational efficiency, and relationship between the clinical relevance and visual similarity of the CAD results. By presenting and comparing a number of approaches commonly used in previous studies, this article identifies and discusses the optimal approaches in developing CBIR-based CAD schemes and assessing their performance. Although preliminary studies have suggested that using CBIR-based CAD schemes might improve radiologists’ performance and/or increase their confidence in the decision making, this technology is still in the early development stage. Much research work is needed before the CBIR-based CAD schemes can be accepted in the clinical practice. Full article
(This article belongs to the Special Issue Machine Learning for Medical Imaging)

Journal Contact

MDPI AG
Algorithms Editorial Office
St. Alban-Anlage 66, 4052 Basel, Switzerland
algorithms@mdpi.com
Tel. +41 61 683 77 34
Fax: +41 61 302 89 18
Editorial Board
Contact Details Submit to Algorithms
Back to Top