Abstract While cardiovascular diseases are the leading causes of death in developed countries, detection of cardiac abnormalities can reduce mortality rates, through early and accurate diagnosis. One of the main assets used to help in the diagnosis process is the electrocardiogram (ECG). A free software tool for electrocardiogram analysis and diagnosis is presented. The tool, named ECGDT, allows: (1) to detect beats present on the ECG, both in single and multi-channel levels, (2) to identify beat waves, and (3) to diagnose different cardiac abnormalities. System evaluation was performed in two ways: (1) diagnostic capabilities were tested with Receiver Operating Characteristic (ROC) analysis, and (2) Graphical Software Interface (GUI) aspects, such as attraction, efficiency, or novelty, were evaluated employing User Experience Questionnaire (UEQ) scores. For disease diagnosis, the mean Area Under the ROC Curve (AUC) was 0.821. The system was also capable of detecting 100% of several cardiac abnormalities, such as bradycardia or tachycardia. Related to the GUI, all usability estimators scored values ranged between 2.208 and 2.750 (overall positive evaluations are obtained for values over 0.8). ECGDT could serve as an aid in the diagnosis of different medical abnormalities. In addition, the suitability of the developed interface has been proven.

This paper presents an algorithm for background modeling and foreground detection that uses scaling coefficients, which are defined with a new color model called lightness-red-green-blue (LRGB). They are employed to compare two images by finding pixels with scaled lightness. Three backgrounds are used: 1) verified background with pixels that are considered as background; 2) testing background with pixels that are tested several times to check if they belong to the background; and 3) final background that is a combination of the testing and verified background (the testing background is used in places, where the verified background is not defined). If a testing background pixel matches pixels from previous frames (the match is tested using scaling coefficients), it is copied to the verified background, otherwise the pixel is set as the weighted average of the corresponding pixels of the last input images. After the background is computed, foreground objects are detected by using the scaling coefficients and additional criteria. The algorithm was evaluated using the SABS data set, Wallflower data set and a subset of the CDnet 2014 data set. The average F measure and sensitivity with the SABS Data set were 0.7109 and 0.8725, respectively. In the Wallflower data set, the total number of errors was 5280 and the total F-measure was 0.9089. In the CDnet 2014 data set, the F-measure for the baseline test case was 0.8887 and for the shadow test case was 0.8300.

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.

The functionalities of the JPEG2000 standard have led to its incorporation into digital imaging and communications in medicine (DICOM), which makes this compression method available for medical systems. In this study, we evaluated the compression of mammographic images with JPEG2000 (16 : 1, 20 : 1, 40 : 1, 60.4 : 1, 80: 1, and 106 : 1) for applications with a computer-aided detection (CAD) system for clusters of microcalcifications. Jackknife free-response receiver operating characteristic (JAFROC) analysis indicated that differences in the detection of clusters of microcalcifications were not statistically significant for uncompressed versus 16: 1 (T = -0.7780; p = 0.4370), 20 : 1 (T = 1.0361; p = 0.3007), and 40 : 1 (T = 1.6966; p = 0.0904); and statistically significant for uncompressed versus 60.4 : 1 (T = 5.8883; p < 0.008), 80 : 1 (T = 7.8414; p < 0.008), and 106 : 1 (T = 17.5034; p = < 0.008). Although there is a small difference in peak signal-to-noise ratio (PSNR) between compression ratios, the true-positive (TP) and false-positive (FP) rates, and the free-response receiver operating characteristic (FROC), figure of merit values considerably decreased from a 60 : 1 compression ratio. The performance of the CAD system is significantly reduced when using images compressed at ratios greater than 40 : 1 with JPEG2000 compared to uncompressed images. Mammographic images compressed up to 20 : 1 provide a percentage of correct detections by our CAD system similar to uncompressed images, regardless of the characteristics of the cluster. Further investigation is required to determine how JPEG2000 affects the detectability of clusters of microcalcifications as a function of their characteristics.

The authors 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 microcalcifications (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/spl plusmn/0.05, indicating that there was no statistical difference between real and simulated clustered microcalcifications.