Determination of border irregularity in dermoscopic color images of pigmented skin lesions.

Malignant melanoma, which is the most dangerous type of skin cancer, is commonly diagnosed in all people, regardless of age, gender, or race. In the last several years an increasing melanoma incidence and mortality rate has been observed worldwide. In this research we present a new approach to the detection and classification of border irregularity, one of the major parameter in a widely used diagnostic algorithm ABCD rule of dermoscopy. Accurate assessment of irregular borders is clinically important due to a significantly different occurrence in benign and malignant skin lesions. In this paper we describe a complex algorithm containing following steps: image enhancement, lesion segmentation, border irregularity detection as well as classification. The algorithm has been tested on 300 dermoscopic images and achieved a detection of 79% and classification accuracy of 90%. Compared to state-of-the-art, we obtain improved classification accuracy.

Determination of border irregularity in dermoscopic color images of pigmented skin lesions.

Malignant melanoma, which is the most dangerous type of skin cancer, is commonly diagnosed in all people, regardless of age, gender, or race. In the last several years an increasing melanoma incidence and mortality rate has been observed worldwide. In this research we present a new approach to the detection and classification of border irregularity, one of the major parameter in a widely used diagnostic algorithm ABCD rule of dermoscopy. Accurate assessment of irregular borders is clinically important due to a significantly different occurrence in benign and malignant skin lesions. In this paper we describe a complex algorithm containing following steps: image enhancement, lesion segmentation, border irregularity detection as well as classification. The algorithm has been tested on 300 dermoscopic images and achieved a detection of 79% and classification accuracy of 90%. Compared to state-of-the-art, we obtain improved classification accuracy.

Pairwise comparisons and visual perceptions of equal area polygons.

The number of studies related to visual perception has been plentiful in recent years. Participants rated the areas of five randomly generated shapes of equal area, using a reference unit area that was displayed together with the shapes. Respondents were 179 university students from Canada and Poland. The average error estimated by respondents using the unit square was 25.75%. The error was substantially decreased to 5.51% when the shapes were compared to one another in pairs. This gain of 20.24% for this two-dimensional experiment was substantially better than the 11.78% gain reported in the previous one-dimensional experiments. This is the first statistically sound two-dimensional experiment demonstrating that pairwise comparisons improve accuracy.

Assessment of electrocardiogram visual interpretation strategy based on scanpath analysis.

Automated ECG interpretation systems are supposed to follow human expert reasoning. Despite well-established standards, the visual interpretation strategy of the human is still undisclosed today. This paper presents a new approach to the interpretation process research based on eyetrack features captured from a human expert during biosignal visual inspection. This approach required a set of visual tasks consisting in ECG interpretation by volunteers of different degrees of expertise. The recorded eyeglobe trajectories were analysed in the context of medical data represented in the displayed ECG traces and revealed interesting information on diagnostic data distribution and principles of interpretation strategies. The scanpath-derived data make benefit of oculomotoric habits gathering in everyday practice, unconscious mutual perception-recognition interactions and are not affected by human memory or verbalization limits. For these reasons, they provide more objective assessment than any other method willingly controlled by the human. Besides new information about the ECG contents and quantitative descriptions of medical data distribution, our experiment reveals some eyetrack parameters as distinctive for interpretation skills estimation.

Knowledge discovery approach to automated cardiac SPECT diagnosis.

The paper describes a computerized process of myocardial perfusion diagnosis from cardiac single proton emission computed tomography (SPECT) images using data mining and knowledge discovery approach. We use a six-step knowledge discovery process. A database consisting of 267 cleaned patient SPECT images (about 3000 2D images), accompanied by clinical information and physician interpretation was created first. Then, a new user-friendly algorithm for computerizing the diagnostic process was designed and implemented. SPECT images were processed to extract a set of features, and then explicit rules were generated, using inductive machine learning and heuristic approaches to mimic cardiologist's diagnosis. The system is able to provide a set of computer diagnoses for cardiac SPECT studies, and can be used as a diagnostic tool by a cardiologist. The achieved results are encouraging because of the high correctness of diagnoses.

New aspects of using the structural graph-grammar based techniques for recognition of selected medical images.

This report will describe the application of syntactic pattern recognition methods for analysis of morphology and recognition of pathologic symptoms of chronic diseases such as upper urinary tract disorders. Detection of these lesions will be assisted by the special graph-grammar developed in our institute for efficient analysis and recognition of such lesions. We present key points of methodology and practical results of its application.

Image understanding methods in biomedical informatics and digital imaging.

This paper will present new possibilities for the application of image recognition methods and AI application in biomedical informatics as well as semantically oriented analysis of 2D images of coronary arteries originating from coronography examinations. In particular this paper presents the possibilities for computer analysis and recognition of local stenoses of the lumen of coronary arteries via the application of syntactic methods of pattern recognition. Such stenoses are the result of the appearance of arteriosclerosis plaques, which in consequence lead to different forms of ischemic cardiovascular diseases. Such diseases may be seen in the form of stable or unstable disturbances of heart rhythm or infarction. Analysis of the correct morphology of these artery lumina is made possible with the application of syntactic analysis and pattern recognition methods, in particular with the attribute, context-free grammar of look-ahead LR(1) type.

Syntactic analysis and languages of shape feature description in computer-aided diagnosis and recognition of cancerous and inflammatory lesions of organs in selected x-ray images.

We present new algorithms for the recognition of morphologic changes and shape feature analysis, which have been proposed to be used in a diagnosis of pathologic symptoms characteristic of cancerous and inflammatory lesions. These methods have been used so far for early detection and diagnosis of neoplastic changes in pancreas and chronic pancreatitis based on x-ray images acquired by endoscopic retrograde cholangiopancreatography (ERCP). Preliminary processing of x-ray images involves binarization, and, subsequently, pancreatic ducts shown in the pictures are subjected to the straightening transformation, which enables obtaining two-dimensional width graphs that show contours of objects with their morphologic changes. Recognition of such changes was performed using attributed context-free grammars. Correct description and diagnosis of some symptoms (e.g., large cavitary projections) required two-dimensional analysis of width graphs. In such cases, languages of shape feature description with special multidirectional sinquad distribution were additionally applied.

Anti-staphylococcal serine proteinase and other serum factors in phagocytosis.

The interactions between polymorphonuclear cells (PMN), Staphylococcus saprophyticus cells and rabbit antibodies against Staphylococcus aureus V8 serine proteinase or normal rabbit serum proteins were investigated. The effect of opsonization on phagocytosis due to human peripheral polymorphonuclear cells was measured. The results were as follows: phagocytosis index values were relatively increased after the incubation of PMN cells with anti-serine proteinase gamma-globulin serum fraction, anti-serine proteinase IgG, non-immunized rabbit serum or with complement.

Staphylococcal dermonecrotic reactions in guinea pigs.

The aim of this study was to compare the dermonecrotic reactions caused by staphylococci. A total of 40 previously biochemically characterized strains of the cocci were used. The organisms were injected intracutaneously into guinea pigs and then dermonecrotic reactions at 24, 48 and 72 h were observed and statistically analysed. From the mathematical point of view the data from experiment were not exhaustive, so it was impossible to use one of the standard methods of statistical analysis. A specially written program for this study was used in statistical analysis. All tested strains of staphylococci had the capacity to induce early or late skin reactions in guinea pigs. Their activity did not seem to be directly related to any of properties of coagulase-positive staphylococci of Staphylococcus aureus genus. Also the immunological aspects of skin reactions in guinea pigs are discussed.

Evaluation of the effect of staphylococcal serine proteinase on phagocytosis.

Correlations between values of phagocytosis index and values of concentrations of staphylococcal serine proteinase were analysed. Preincubation of granulocytes with the proteinase stimulated phagocytosis of three bacterial strains: S. saprophyticus, S. aureus VS and S. aureus Smith diffuse. Significant correlations were also observed for S. saprophyticus strain in phagocytosis performed with or without bovine serum. Specific rabbit IgG anti-serine proteinase effected the increase of phagocytosis index only in the case of S. aureus Smith diffuse. Summary statistical analysis for all experimental conditions exhibits significant correlations also for S. aureus VS strain. No significant correlations were noted for the three remaining strains taken from patients.

Computer evaluation of antiviral activities of some thiosemicarbazones in experiments in vivo.

A new mathematical method based on 3-, 4- or 6-point parallel-line assays was applied for working out a computer programme used to evaluate the activity of some new isatin-beta-thiosemicarbazone derivatives against vaccinia virus, studied in vivo.