Integration of color and boundary information for improved region of interest identification in electron magnetic resonance images

The fibrous texture in liver is one of important signs for interpreting the chronic liver diseases in radiologists’ routines. In order to investigate the usefulness of various texture features calculated by computer algorithm on hepatic magnetic resonance (MR) images, 15 texture features were calculated from the gray level co-occurrence matrix (GLCM) within a region of interest (ROI) which was selected from the MR images with 6 stages of hepatic fibrosis. By different combination of 15 features as input vectors, the classifier had different performance in staging the hepatic fibrosis. Each combination of texture features was tested by Support Vector Machine (SVM) with leave one case out method. 173 patients’ MR images including 6 stages of hepatic fibrosis were scanned within recent two years. The result showed that optimal number of features was confirmed from 3 to 7 by investigating the classified accuracy rate between each stage/group. It is evident that angular second moment, entropy, sum average and sum entropy played the most significant role in classification.

Download Full-text

Measurement of tumor resection volumes from computerized images

Journal of Neurosurgery ◽

10.3171/jns.1992.77.1.0151 ◽

1992 ◽

Vol 77 (1) ◽

pp. 151-154 ◽

Cited By ~ 27

Author(s):

Duc H. Duong ◽

Robert C. Rostomily ◽

David R. Haynor ◽

G. Evren Keles ◽

Mitchel S. Berger

Keyword(s):

Magnetic Resonance ◽

Brain Tumors ◽

Tumor Resection ◽

Region Of Interest ◽

Magnetic Resonance Images ◽

Content Type ◽

Slide Scanner ◽

Program Error ◽

Fine Print ◽

Area And Volume

✓ The authors describe a method for quantitation of the area and volume of the resection cavity in patients who have undergone surgery for brain tumors. Using a slide scanner and Image 1.27, a public domain program for the Apple Macintosh II computer, computerized tomography scans and magnetic resonance images can be digitized and analyzed for a particular region of interest, such as the area and volume of tumor on preoperative and postresection scans. Phantom scans were used to analyze the accuracy of the program and the program users. User error was estimated at 2%, program error was 4.5%. This methodology is proposed as a means of retrospectively calculating the extent of tumor resection.

Download Full-text

Semi-automated cardiac segmentation on cine magnetic resonance images using GVF-Snake deformable models

10.54294/ub0ptg ◽

2009 ◽

Author(s):

Constantin Constantinides ◽

Yasmina Chenoune ◽

Nadjia Kachenoura ◽

Elodie Roullot ◽

Elie Mousseaux ◽

...

Keyword(s):

Magnetic Resonance ◽

Ejection Fraction ◽

Region Of Interest ◽

Left Ventricular ◽

Magnetic Resonance Images ◽

Deformable Model ◽

Papillary Muscles ◽

Myocardial Mass ◽

Endocardial Border ◽

Cardiac Segmentation

The segmentation of left ventricular structures is necessary for the evaluation of the ejection fraction (EF) and the myocardial mass (LVM). A semi-automated 2D algorithm using connected filters and a deformable model allowing an accurate endocardial detection was proposed. The epicardial border was deduced using a deformable model restricted inside a region of interest defined from the endocardial border. Papillary muscles were detected using a fuzzy k-means algorithm. The method was applied to the challenge training and validation databases, consisting of 15 subjects each. The evaluation was performed using the tools provided by the challenge. For both datasets, results show a mean Dice metric of 0.89 for endocardial borders (0.92 for epicardial borders). Overall average perpendicular distance was 2.2 mm. Very good correlation was obtained for the EF and LVM parameters. Visual overall rating given by the challenge’s cardiologist was 1.2. Segmentation was robust and performed successfully on both datasets.

Download Full-text

INTEGRATING EDGE DETECTION AND THRESHOLDING APPROACHES TO SEGMENTING FEMORA AND PATELLAE FROM MAGNETIC RESONANCE IMAGES

Biomedical Engineering Applications Basis and Communications ◽

10.4015/s1016237205000020 ◽

2005 ◽

Vol 17 (01) ◽

pp. 1-11 ◽

Cited By ~ 12

Author(s):

JIANN-SHU LEE ◽

YI-NUNG CHUNG

Keyword(s):

Magnetic Resonance ◽

Edge Detection ◽

Knee Pain ◽

Pathological Condition ◽

Region Of Interest ◽

Magnetic Resonance Images ◽

Initial Guess ◽

Joint Analysis ◽

Edge Based ◽

The Moment

Anterior knee pain (AKP) is a common pathological condition. The most obvious problem causing knee pain is the abnormal patellar tracking mechanism. For computerized knee joint analysis, how to successfully segment the knee bones is an import issue. This paper presents a simple while effective algorithm for fully automatic femur and patella segmentation for magnetic resonance (MR) knee images through integrating edge detection and thresholding approaches. Based on consideration of computational complexity and accuracy, we develop a compound approach to segment the MR knee images. The moment preserving thresholding is first utilized to gather the bone-outline information employed to estimate the region of interest (ROI). An ROI based wavelet enhancement is proposed to restrict the contrast improvement only around the bone edges. The restriction makes both the adhesion separation of bone and surrounding tissues and the bone contour conservation become possible and avoid harsh thresholding resulting from the global based wavelet enhancement. Cooperating with the morphology operation, stable initial guess of the bone regions can be achieved. To overwhelm the main drawback of the existing edge based segmentation methods, i.e. the necessity of complicated post-processing, a new approach - FLoG is proposed to provide a feasible solution. It converts the edge detection results using LoG into a region-based format through the flow fill operation. The developed onion-growing algorithm can properly combine the initial guess of bone regions with the FLoG outputs in an efficient way. The experimental study shows our method is superior to the conventional ones in meeting the requirement of physicians. This is because our method can perform well in dealing with the tougher conditions, i.e. the partial volume and the soft tissue adhesion conditions. Because of the integration of the thresholding approach with the FLoG edge detector, our algorithm is even robust to unsatisfactory imaging conditions. Hence, our method lends itself to assisting the clinical diagnosis of knee functions.

Download Full-text

Region of Interest Identification for Brain Tumors in Magnetic Resonance Images

2020 28th Iranian Conference on Electrical Engineering (ICEE) ◽

10.1109/icee50131.2020.9260611 ◽

2020 ◽

Author(s):

Fateme Mostafaie ◽

Reihaneh Teimouri ◽

Zahra Nabizadeh Shahre Babak ◽

Nader Karimi ◽

Shadrokh Samavi

Keyword(s):

Magnetic Resonance ◽

Brain Tumors ◽

Region Of Interest ◽

Magnetic Resonance Images

Download Full-text

Magnetic resonance imaging of plantar soft tissue structures of the tarsus and proximal metatarsus in foals and adult horses

Veterinary and Comparative Orthopaedics and Traumatology ◽

10.3415/vcot-12-06-0072 ◽

2013 ◽

Vol 26 (03) ◽

pp. 192-197 ◽

Cited By ~ 6

Author(s):

E. Ludewig ◽

W. Brehm ◽

K.-D. Budras ◽

K. Winter ◽

J. Edinger ◽

...

Keyword(s):

Magnetic Resonance ◽

Soft Tissue ◽

Signal Intensity ◽

Flexor Tendon ◽

Region Of Interest ◽

Magnetic Resonance Images ◽

Suspensory Ligament ◽

Plantar Aspect ◽

Age Related ◽

Tissue Structures

SummaryObjectives: The object of this study was to describe previously defined soft tissue structures by using spin and gradient sequences in a 0.5 Tesla magnetic resonance system in order to improve the characterisation of tendon and ligaments at the plantar region of the equine tarsus and metatarsus while considering possible age-related variations.Methods: Cadaveric hindlimbs from twenty-two Warmblood horses with an age range from one month to twenty-five years were examined in spin and gradient echoes. The proximal suspensory ligament from six limbs was dissected to assign the signal intensities histologically. For statistical analysis, horses were divided into two groups (≤3 years and >3 years) for evaluating signal intensity and homogeneity of the plantar tendons and ligaments.Results: Focal increase of the signal intensity within the deep digital flexor tendon was significantly more present in horses older than three years. Signal alterations of the long plantar ligament were seen without a significant dependency to age. The accessory ligament of the deep digital flexor tendon could not be visualized on all images within the region of interest. The morphology of the proximal suspensory ligament was not affected by age-related changes.Clinical relevance: Spin and gradient echoes in MRI were suitable to identify and assess soft tissue structures at the plantar aspect of the equine tarsus and proximal metatarsus. Age-related appearance must be considered when interpreting magnetic resonance images.

Download Full-text

Novel Method for Evaluating Spatial Resolution of Magnetic Resonance Images

10.21203/rs.3.rs-823953/v1 ◽

2021 ◽

Author(s):

tomokazu takeuchi ◽

Norio Hayashi ◽

Yuta Asai ◽

Yuka Kayaoka ◽

Kiichi Yoshida

Keyword(s):

Magnetic Resonance ◽

Spatial Resolution ◽

Nickel Sulfate ◽

Region Of Interest ◽

Volume Effect ◽

Magnetic Resonance Images ◽

Periodic Pattern ◽

International Electrotechnical Commission ◽

Modulation Transfer ◽

Edge Image

Abstract Purpose Recently, several methods for evaluating the spatial resolution of magnetic resonance imaging (MRI) have been reported. However, these methods are not simple and can only be used for specific devices. The International Electrotechnical Commission (IEC) 62464-1 recommends a method that uses a periodic array pattern to evaluate the spatial resolution of an MRI device. In this study, we develop a new method (the ladder method) and evaluate its measurement accuracy by adapting the IEC method to evaluate the spatial resolution. Methods First, the adaptation of the IEC method is analyzed by simulating the ladder method using a phantom with a periodic pattern, which is constructed using acrylic plates and a nickel sulfate aqueous solution. Subsequently, the ladder method is evaluated in terms of spatial resolution by dividing the standard deviation (SD) by the average signal in the region of interest (ROI) on the ladder phantom image. To evaluate the precision of the ladder method, it is compared with the modulation transfer function (MTF) using a magnitude image with the partial volume effect of the edge image. Results The simulation result shows that the evaluation of the spatial resolution using the ladder method is viable, in which a coefficient of correlation of 0.90 or higher is obtained for all evaluations using the ladder and MTF methods. ConclusionsThe ladder method can be assessed using only the signal mean value and SD in the ROI on the target image. Therefore, the ladder method is a promising method as a substitute for the MTF.

Download Full-text

Ensemble of ROI-based convolutional neural network classifiers for staging the Alzheimer disease spectrum from magnetic resonance imaging

PLoS ONE ◽

10.1371/journal.pone.0242712 ◽

2020 ◽

Vol 15 (12) ◽

pp. e0242712

Author(s):

Samsuddin Ahmed ◽

Byeong C. Kim ◽

Kun Ho Lee ◽

Ho Yub Jung ◽

Keyword(s):

Neural Network ◽

Magnetic Resonance ◽

Alzheimer Disease ◽

Convolutional Neural Network ◽

Region Of Interest ◽

Volumetric Analysis ◽

Ensemble Classifier ◽

Magnetic Resonance Images ◽

Disease Spectrum ◽

Preclinical Ad

Patches from three orthogonal views of selected cerebral regions can be utilized to learn convolutional neural network (CNN) models for staging the Alzheimer disease (AD) spectrum including preclinical AD, mild cognitive impairment due to AD, and dementia due to AD and normal controls. Hippocampi, amygdalae and insulae were selected from the volumetric analysis of structured magnetic resonance images (MRIs). Three-view patches (TVPs) from these regions were fed to the CNN for training. MRIs were classified with the SoftMax-normalized scores of individual model predictions on TVPs. The significance of each region of interest (ROI) for staging the AD spectrum was evaluated and reported. The results of the ensemble classifier are compared with state-of-the-art methods using the same evaluation metrics. Patch-based ROI ensembles provide comparable diagnostic performance for AD staging. In this work, TVP-based ROI analysis using a CNN provides informative landmarks in cerebral MRIs and may have significance in clinical studies and computer-aided diagnosis system design.

Download Full-text

GA-BASED OPTIMIZATION OF TAPERING WINDOWS FOR ARTIFACT REDUCTION IN FOURIER ELECTRON MAGNETIC RESONANCE IMAGES

International Journal of Computational Intelligence and Applications ◽

10.1142/s1469026809002503 ◽

2009 ◽

Vol 08 (02) ◽

pp. 111-125

Author(s):

M. SUMATHI ◽

MURALI C. KRISHNA ◽

R. MURUGESAN

Keyword(s):

Magnetic Resonance ◽

Imaging Modality ◽

Single Point ◽

Magnetic Resonance Images ◽

Electron Magnetic Resonance ◽

Artifact Reduction ◽

Conventional Mri ◽

Window Functions ◽

Frequency Components ◽

Ringing Artifact

Optimization of tapering windows for artifact reduction in two-dimensional (2D) Fourier electron magnetic resonance (EMR) tomography using genetic algorithm (GA) is presented. EMR imaging (EMRI) is a fast emerging functional imaging modality for studying free radicals in biological systems. EMRI by single point imaging (SPI) modality is a Fourier imaging technique. The bioclearance of the imaging agent as well as the need to minimize the radio frequency power deposition on the live animals, dictate reduced k-space sampling. This leads to ringing (Gibbs) artifacts in both directions of the 2D image, because, unlike the conventional MRI, SPI is phase encoding in both directions. To dampen the high-frequency components, data tapering windows are multiplicatively applied to provide tolerable blurred resultant image with reduced Gibbs ringing. To find a compromise between blur and ringing artifact, in this paper a method of optimizing the window functions by using GA is proposed. Our experiments suggest GA-based Kaiser window shows better performance by visual as well as quantitative evaluation.

Download Full-text