Research Interests:
The shape and size of the aortic lumen can be associated with several aortic diseases. Automated computer segmentation can provide a mechanism for extracting the main features of the aorta that may be used as a diagnostic aid for... more
The shape and size of the aortic lumen can be associated with several aortic diseases. Automated computer segmentation can provide a mechanism for extracting the main features of the aorta that may be used as a diagnostic aid for physicians. This article presents a new fully automated algorithm to extract the aorta geometry for either normal (with and without contrast) or abnormal computed tomography (CT) cases. The algorithm we propose is a fast incremental technique that computes the 3D geometry of the aortic lumen from an initial contour located inside it. Our approach is based on the optimization of the 3D orientation of the cross sections of the aorta. The method uses a robust ellipse estimation algorithm and an energy-based optimization technique to automatically track the centerline and the cross sections. The optimization involves the size and eccentricity of the ellipse which best fits the aorta contour on each cross-sectional plane. The method works directly on the origina...
Research Interests:
The development of a total digital high resolution mammography display system must meet a number of requirements that remain a challenge nowadays, most probably because of the special nature of breast imaging. In this paper, we discuss... more
The development of a total digital high resolution mammography display system must meet a number of requirements that remain a challenge nowadays, most probably because of the special nature of breast imaging. In this paper, we discuss our particular approach to address some problems concerning the complexity of soft-copy diagnosis in digital mammography, such as image quality and user interface evaluation. Based on the experience obtained in the previous implementation of a medical image browser, a more ambitious project is being developed at the Department of Radiology of the University of Santiago de Compostela (Spain) in collaboration with the Department of Medical Informatics of INTELSIS, an emerging software company in our country. This new system will provide complete support to display, store and analyze mammographic studies in digital format.
Research Interests: Biomedical Engineering, Digital Mammography, User Interface, Image Quality, Software, and 11 moreBreast Imaging, PACS, DICOM, Diagnostic Imaging, Mammography, Computer User Interface Design, High Resolution, Medical Image, Radiology Information Systems, User Interface Evaluation, and Medical Informatic
A digital image network has been installed at the Department of Radiology of the University of Santiago de Compostela, Spain, to create a "limited' Picture Archiving and Communication... more
A digital image network has been installed at the Department of Radiology of the University of Santiago de Compostela, Spain, to create a "limited' Picture Archiving and Communication System (PACS). This experience is being dedicated to address problems associated with digital techniques in a research environment. The backbone of the system is a multiprotocol ethernet network. Attached to the network are a number of advanced devices such as DEC VAX and UNIX workstations. Currently, a high resolution film digitizer and a laser printer are under evaluation for radiologic image research. During a period of nine years, 1987 to 1995, experimental and clinical trials have been conducted on different film based digital radiography apparatus primarily dedicated to chest and breast imaging. Several research projects have been completed. In this paper we describe the results of these investigations and discuss the advantages and disadvantages of this digital technique. The results of the different completed studies will be presented separately. A description of the physical characteristics of the limited PACS system dedicated to a research environment will serve as background.
Research Interests:
The receiver operating characteristic (ROC) curve is the most widely used measure for statistically evaluating the discriminatory capacity of continuous biomarkers. It is well known that, in certain circumstances, the markers’... more
The receiver operating characteristic (ROC) curve is the most widely used measure for statistically evaluating the discriminatory capacity of continuous biomarkers. It is well known that, in certain circumstances, the markers’ discriminatory capacity can be affected by factors, and several ROC regression methodologies have been proposed to incorporate covariates in the ROC framework. An in-depth simulation study of different ROC regression models and their application in the emerging field of automatic detection of tumour masses is presented. In the simulation study different scenarios were considered and the models were compared to each other on the basis of the mean squared error criterion. The application of the reviewed ROC regression techniques in evaluating computer-aided diagnostic (CAD) schemes can become a major factor in the development of such systems in Radiology.
Research Interests: Econometrics, Statistics, Data Analysis, Comparative Study, Mean square error, and 13 moreROC Curve, Computer System, Receiving Operating Characteristic, Regression Model, Simulation Study, B spline, Computer Aided Diagnosis, Computational Statistics and Data Analysis, Statistical Regression, Automatic Detection, Mean Error, Breast cancer detection, and Statistical evaluation
Research Interests:
A computerized scheme to detect masses and clustered microcalcifications has been tested, using 320 mammograms selected from the mammographic screening program undergoing at the Galicia Community (Spain). After the digitization, the... more
A computerized scheme to detect masses and clustered microcalcifications has been tested, using 320 mammograms selected from the mammographic screening program undergoing at the Galicia Community (Spain). After the digitization, the breast border was calculated. To detect the masses, a bilateral substraction technique was used. For the detection of microcalcifications a wavelet-based algorithm was used. Performance of the system was evaluated using Free-Response Receiver Operating Characteristic (FROC) analysis. For masses, the sensitivity was 61.91% with a mean number of 1.48 false positives per image. The sensitivity achieved for microcalcifications was 66.00% at a false positive detection rate of 1.58. The areas under the Alternative FROC (AFROC) curves were A 1 =0.541 and A 1 =0.473, respectively.
Research Interests:
To compare the accuracy with which simulated solitary pulmonary nodules can be identified on digital images of the chest that are unprocessed, processed with adaptive spatial filtering, or processed with global filtering. Six experienced... more
To compare the accuracy with which simulated solitary pulmonary nodules can be identified on digital images of the chest that are unprocessed, processed with adaptive spatial filtering, or processed with global filtering. Six experienced chest radiologists evaluated 408 test radiographs (136 from each of the three types, half with simulated nodules) and judged whether a nodule was present. Data from the 2,448 observations were evaluated by means of a receiver operating characteristic curve with location methods. Accuracy was significantly better with the adaptive filter technique than with the global technique (P < .05), and it was better with adaptive filtering than with no processing in the detection of pulmonary nodules in the mediastinal-subdiaphragmatic areas (P < .05). No significant difference was found between no processing and global filtering. Adaptive filtration is superior to global filtration in the identification of solitary pulmonary nodules and is superior to n...
Research Interests:
We propose a model to simulate clustered microcalcifications on digital mammograms. The simulation model is based on the gray-level, size and number of microcalcifications per cluster. All the parameters describing the individual... more
We propose a model to simulate clustered microcalcifications on digital mammograms. The simulation model is based on the gray-level, size and number of microcalcifications per cluster. All the parameters describing the individual microcalcifications and clusters were randomly sampled from the values of the real clustered mirocalcifications (extracted in a feature analysis process) present in the mammogram, the exception being the center of the cluster, that was interactively positioned to ensure the location of all the microcalcifications inside the breast. Subsequently, a database of clustered microcalcifications was created. These clusters of microcalcifications from this database were tested from indistinguishability from real ones. Two radiologists and one physicist were asked to indicate wether the microcalcifications were either real or simulated. The responses of the readers were evaluated with an ROC analysis, and the area under the curve was calculated. The average ROC area was 0.54+0.05, indicating that there was not statistical difference between real and simulated clustered microcalcifications.
Research Interests:
ABSTRACT
Research Interests:
ABSTRACT Computed tomography (CT) for non-clinical applications is constantly evolving in many different fields, from industry, laboratory and metrology applications. The Technological Center AIMEN, in collaboration with the University of... more
ABSTRACT Computed tomography (CT) for non-clinical applications is constantly evolving in many different fields, from industry, laboratory and metrology applications. The Technological Center AIMEN, in collaboration with the University of Santiago de Compostela, has implemented a dual-detector computed tomography system. A specific visualisation tool has been developed including 3D rendering and image reconstruction, following the modular capabilities of the CT system. Software capabilities include CT reconstruction for different geometries, special filtering, higher computer memory requirements, basic knowledge extraction, etc., resulting in flexible software with possibilities for further applications development. This new tool is adapted to the emerging needs of an open CT system which is built in a modular configuration to answer new challenges, as those for dimensional metrology (improving its spatial resolution and image quality) and specific analysis for non-destructive testing.
Research Interests:
Research Interests:
The aim of this study was to compare a semiautomatic segmentation method to quantify the function of both ventricles in magnetic resonance imaging (MRI) with the manual tracing method. We examined 17 patients with diverse cardiovascular... more
The aim of this study was to compare a semiautomatic segmentation method to quantify the function of both ventricles in magnetic resonance imaging (MRI) with the manual tracing method. We examined 17 patients with diverse cardiovascular diseases on a 1.5 Tesla MRI unit (Magnetom Symphony Quantum; Siemens Medical Systems, Erlangen, Germany) using the following parameters: maximum gradient, 30 mT/m; and slew rate, 125 T/m/s. In all studies, we acquired images in cine mode in the short axis (SSFP, 6mm slice thickness, from the base to the ventricular apex) with breath holding. To reduce the user interaction, we used only one image per patient to initiate the semiautomatic method. The semiautomatic method was based on a specifically designed algorithm of regional growth and border detection. We quantified the end-diastolic volume (EDV), end-systolic volume (ESV), and the ejection fraction (EF) for both ventricles in all patients. No significant differences between the two segmentation techniques were found in the quantification of either ventricle (p&gt;0.05). The difference in the volumes, although nearly significant, are clinically irrelevant. The correlation for the estimation of left ventricular function was excellent (r&gt;0.9), and the correlation for the estimation of right ventricular function was good (r&gt;0.7). Our semiautomatic segmentation method enables the function of both ventricles to be quantified as accurately as the conventional method.
Research Interests:
Research Interests:
Research Interests:
Research Interests:
This study sought to develop a completely automatic method for image segmentation of the thoracic aorta. We used a total of 4682 images from 10 consecutive patients. The proposed method is based on the use of level set and region growing,... more
This study sought to develop a completely automatic method for image segmentation of the thoracic aorta. We used a total of 4682 images from 10 consecutive patients. The proposed method is based on the use of level set and region growing, automatically initialized using the Hough transform. The results obtained were compared to those of manual segmentation as performed by an external expert radiologist. Concordance between the developed method and manual segmentation ranged from 92.79 to 95.77% in the descending regions of the aorta and from 90.68 to 96.54% in the ascending regions, with a mean value of 93.83% being obtained for total segmentation.
Research Interests:
Research Interests:
Accurate determination of the diameter is an important step for diagnosis and follow-up of aortic abnormalities such as aneurysms, caused by dilation of the vessel lumen. In this work we focus on the development of an automatic method for... more
Accurate determination of the diameter is an important step for diagnosis and follow-up of aortic abnormalities such as aneurysms, caused by dilation of the vessel lumen. In this work we focus on the development of an automatic method for measuring the calibre of the thoracic aorta. The method is based on the application of principal component analysis on normal planes extracted from the aorta to establish the main axis of each section of the vessel. Two experiments were performed in order to test the accuracy and the rotational invariance of the developed method. Accuracy was determined by using a database of 15 clinical cases, where our method and a commercial software, which was considered as the gold standard, were compared. For the rotational invariance check, phantom images in different orientations were obtained and the diameter was measured with the proposed method. For clinical cases, a good agreement was observed between our method and the gold standard. The Bland Altman plots indicated that all of the values were within the acceptable limits of agreement with a bias of 0.2mm between both methods. For phantom cases, an ANOVA test revealed that the results achieved for the data sets acquired for the different orientations were not statistically different (F=1.88, p=0.153), which demonstrates the robustness of the method for rotations. The proposed method is applicable for measuring the diameter in all tested cases, and the results achieved underscored the capability of our approach for automatic characterization of thoracic aortic aneurysms.
Research Interests:
Page 1. J. Crespo, V. Maojo, and F. Martin (Eds.): ISMDA 2001, LNCS 2199, pp. 181-185, 2001. Springer-Verlag Berlin Heidelberg 2001 Improvement of a Mammographic CAD System for Mass Detection Arturo J. Méndez1 ...
Research Interests:
Research Interests:
A newly developed lossy compression and transmission scheme valid for telemedicine is described. The system uses computed tomography (CT) images and is based on JPEG2000. Different compression rates were applied to different regions... more
A newly developed lossy compression and transmission scheme valid for telemedicine is described. The system uses computed tomography (CT) images and is based on JPEG2000. Different compression rates were applied to different regions within the image. JPEG2000 with the Maxshift algorithm to encode a region of interest (ROI) was used. The ROI is an area in the image that is expected to exhibit a better quality than the rest of it at any decoding bit rate. ROIs were delimited by using several processes of thresholding and growing regions. Compressed images were encapsulated using the DICOM format with JPEG2000 Transfer Syntax before transmission. DICOM Storage Service Class was then used to transmit those images. The system was evaluated by transmitting several series of CT images via integrated services digital network (128 kbps). Results obtained after decompression with and without the Maxshift algorithm were compared.
Research Interests:
In many biomedical applications, interest lies in being able to distinguish between two possible states of a given response variable, depending on the values of certain continuous predictors. If the number of predictors, p, is high, or if... more
In many biomedical applications, interest lies in being able to distinguish between two possible states of a given response variable, depending on the values of certain continuous predictors. If the number of predictors, p, is high, or if there is redundancy among them, it then becomes important to decide on the selection of the best subset of predictors that will be able to obtain the models with greatest discrimination capacity. With this aim in mind, logistic generalized additive models were considered and receiver operating characteristic (ROC) curves were applied in order to determine and compare the discriminatory capacity of such models. This study sought to develop bootstrap-based tests that allow for the following to be ascertained: (a) the optimal number q &amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;lt; or = p of predictors; and (b) the model or models including q predictors, which display the largest AUC (area under the ROC curve). A simulation study was conducted to verify the behaviour of these tests. Finally, the proposed method was applied to a computer-aided diagnostic system dedicated to early detection of breast cancer.
Research Interests: Statistics, Nonparametric Statistics, Breast Cancer, Kernel Smoothing, Humans, and 10 moreVariable Selection, Female, Regression Analysis, Bootstrap, ROC Curve, Public health systems and services research, Generalized Additive Models, Non-parametric Regression, Area Under Curve, and Breast Neoplasms
Research Interests:
Total lung capacity (TLC) is a very important parameter in the study of pulmonary function. In the pulmonary function laboratory, it is normally obtained using plethysmography or helium dilution techniques. Several authors have developed... more
Total lung capacity (TLC) is a very important parameter in the study of pulmonary function. In the pulmonary function laboratory, it is normally obtained using plethysmography or helium dilution techniques. Several authors have developed methods of calculating the TLC using postero-anterior (PA) and lateral chest radiographs. These methods have not been often used in clinical practice. In the present work, we have developed and automated computer-based method for the calculation of TLC, by determining the pulmonary contours from digital PA and lateral radiographs of the thorax. The automatic tracing of the pulmonary borders is carried out using: (1) a group of reference lines is determined in each radiograph; (2) a family of rectangular regions of interest (ROIs) defined, which include the pulmonary borders, and in each of them the pulmonary border is identified using edge enhancement and thresholding techniques; (3) removing outlaying points from the preliminary boundary set; and (4) the pulmonary border is corrected and completed by means of interpolation, extrapolation, and arc fitting. The TLC is calculated using a computerized form of the radiographic ellipses method of Barnhard. The pulmonary borders were automatically traced in a total of 65 normal radiographs (65 PA and 65 lateral views of the same patients). Three radiologists carried out a subjective evaluation of the automatic tracing of the pulmonary borders, with a finding of no error or only one minor error in 67.7% of the PA evaluations, and in 75.9% of the laterals. Comparing the automatically traced borders with borders traced manually by an expert radiologists, we obtained a precision of 0.990 +/- 0.001 for the PA view, and 0.985 +/- 0.002 for the lateral. The values of TLC obtained by the automatic calculation described here showed a high correlation (r = 0.98) with those obtained by applying the manual Barnhard method.
Research Interests:
A computerized scheme to detect clustered microcalcifications in digital mammograms has been developed. Detection of individual microcalcifications in regions of interest (ROIs) was also performed. The mammograms were previously... more
A computerized scheme to detect clustered microcalcifications in digital mammograms has been developed. Detection of individual microcalcifications in regions of interest (ROIs) was also performed. The mammograms were previously classified into fatty and dense, according to their breast tissue. The most appropriate wavelet basis and reconstruction levels were selected. To select the wavelet basis, 40 profiles of microcalcifications were decomposed and reconstructed using different types of wavelet functions and different combinations of wavelet coefficients. The symlets with a basis of length 8 were chosen for fatty tissue. For dense tissue, the Daubechies&#39; wavelets with a four-element basis were employed. Two methods to detect individual microcalcifications were evaluated: (a) two-dimensional wavelet transform, and (b) one-dimensional wavelet transform. The second technique yielded the best results, and was used to detect clustered microcalcifications in the complete mammogram. When detecting individual microcalcifications by using two-dimensional wavelet transform we have obtained, for fatty ROIs, a sensitivity of 71.11% at a false positive rate of 7.13 per image. For dense ROIs the sensitivity was 60.76% and the false positive rate, 7.33. The areas (A1) under the AFROC curves were 0.33+/-0.04 and 0.28+/-0.02, respectively. The one-dimensional wavelet transform method yielded 80.44% of sensitivity and 6.43 false positives per image (A1=0.39+/-0.03) for fatty ROIs, and 62.17% and 5.82 false positives per image (A1=0.37+/-0.02) for dense ROIs. For the detection of clusters of microcalcifications in the entire mammogram, the sensitivity was 80.00% with 0.94 false positives per image (A1=0.77+/-0.09) for fatty mammograms, and 72.85% of sensitivity at a false positive detection rate of 2.21 per image (A1=0.64+/-0.07) for dense mammograms. Globally, a sensitivity of 76.43% at a false positive detection rate of 1.57 per image was obtained.
Research Interests:
We have developed a model to simulate clustered microcalcifications on digital mammograms. Wavelet transform techniques were used to detect real clustered microcalcifications. A feature analysis process was applied to automatically... more
We have developed a model to simulate clustered microcalcifications on digital mammograms. Wavelet transform techniques were used to detect real clustered microcalcifications. A feature analysis process was applied to automatically extract the features describing the individual simulated microcalcifications and clusters from the values of the real clustered microcalcifications present in the mammogram. Subsequently, a database of simulated and real clustered microcalcifications was created. Clusters of microcalcifications from this database were tested for indistinguishability from real ones. Two radiologists and one physicist were asked to indicate whether the microcalcifications were either real or simulated. The responses of the readers were evaluated with a ROC analysis and the area under the curve was calculated. The average ROC area was 0.54 +/- 0.03, indicating there was no statistical difference between real and simulated clustered microcalcifications. The method allows for the creations of simulated clustered microcalcifications that are virtually indistinguishable from real microcalcifications in digital mammograms and could be used to evaluate different image processing techniques.
Research Interests:
Research Interests: Engineering, Algorithms, Mass Spectrometry, Magnetic Resonance Spectroscopy, Near Infrared, and 15 moreComputer Simulation, Ultraviolet, Calibration, Nmr, Physical sciences, Magnetic Resonance, Artifacts, Derivative, Spectrum, Magnetic, Reproducibility of Results, Sensitivity and Specificity, Signal to Noise Ratio, Equipment Failure Analysis, and Continuous wavelet transform
The application of a lossy data compression algorithm based on wavelet transform to 2D NMR spectra is presented. We show that this algorithm affords rapid and extreme compression ratios (e.g., 800:1), providing high quality reconstructed... more
The application of a lossy data compression algorithm based on wavelet transform to 2D NMR spectra is presented. We show that this algorithm affords rapid and extreme compression ratios (e.g., 800:1), providing high quality reconstructed 2D spectra. The algorithm was evaluated to ensure that qualitative and quantitative information are retained in the compressed NMR spectra. Whilst the maximum compression ratio that can be achieved depends on the number of signals and on the difference between the most and the least intense peaks (dynamic range), a compression ratio of 80:1 is affordable even for the challenging case of homonuclear 2D experiments of large biomolecules.
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
The authors present a new algorithm to enhance the edges and contrast of chest and breast radiographs while minimally amplifying image noise. The algorithm consists of a linear combination of an original image and two smoothed images... more
The authors present a new algorithm to enhance the edges and contrast of chest and breast radiographs while minimally amplifying image noise. The algorithm consists of a linear combination of an original image and two smoothed images obtained from it by using different masks and parameters, followed by the application of nonlinear contrast stretching. The result is an image which retains the high median frequency local variations (edge and contrast-enhancing).
Research Interests:
Research Interests: Engineering, Algorithms, Medical Imaging, Data Compression, Digital Mammography, and 15 moreImage segmentation, Image compression, Humans, Wavelet Transform, Contrast sensitivity, Mammography, Medical Image, Calcinosis, Reproducibility of Results, Spatial resolution, Sensitivity and Specificity, Discrete Wavelet Transforms, Region of Interest, Breast Neoplasms, and image resolution
Several investigators have pointed out the possibility of using computer-aided diagnosis (CAD) schemes, as second readers, to help radiologists in the interpretation of images. One of the most important aspects to be considered when the... more
Several investigators have pointed out the possibility of using computer-aided diagnosis (CAD) schemes, as second readers, to help radiologists in the interpretation of images. One of the most important aspects to be considered when the diagnostic imaging systems are analyzed is the evaluation of their diagnostic performance. To perform this task, receiver operating characteristic curves are the method of choice. An important step in nearly all CAD systems is the reduction of false positives, as well as the classification of lesions, using different algorithms, such as neural networks or feature analysis, and several statistical methods. A statistical model more often employed is linear discriminant analysis (LDA). However, LDA implies several limitations in the type of variables that it can analyze. In this work, we have developed a novel approach, based on generalized additive models (GAMs), as an alternative to LDA, which can deal with a broad variety of variables, improving the results produced by using the LDA model. As an application, we have used GAM techniques for reducing the number of false detections in a computerized method to detect clustered microcalcifications, and we have compared this with the results obtained when LDA was applied. Employing LDA, the system achieved a sensitivity of 80.52% at a false-positive rate of 1.90 false detections per image. With the GAM, the sensitivity increased to 83.12% and 1.46 false positives per image.
Research Interests: Engineering, Computer Science, Algorithms, Artificial Intelligence, Image Analysis, and 15 moreNeural Network, Information, Image Classification, Discriminant Analysis, Linear Discriminant Analysis, Generalized Additive Model, Diagnostic Imaging, Generalized Additive Models, Feature Analysis, False Positive Rate, Computer Aided Diagnosis, False Positive, Neural nets, Medical and Health Sciences, and Linear discriminate analysis
Research Interests: Engineering, Computer Science, Artificial Intelligence, Data Compression, Digital Mammography, and 15 moreDigital imaging, Biomedical Imaging, Image compression, Humans, Female, DICOM, Mammography, JPEG, IEEE Transactions, Calcinosis, Computer Aided Detection, Figure of Merit, Compression Ratio, False Positive, and guidelines as topic
... Once digi-tal data are acquired, image processing techniques can be applied to improve diagnostic performance, and the im-age can either be viewed on a cathode-ray tube (CRT) monitor or be printed on film, both after... more
... Once digi-tal data are acquired, image processing techniques can be applied to improve diagnostic performance, and the im-age can either be viewed on a cathode-ray tube (CRT) monitor or be printed on film, both after digital-to-ana-log conversion (DAC). ...