ABSTRACT
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.
Subject(s)
Artificial Intelligence , Myocardial Infarction/diagnosis , Myocardial Reperfusion , Tomography, Emission-Computed, Single-Photon , Databases, Factual , Decision Making, Computer-Assisted , HumansABSTRACT
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.
Subject(s)
Diagnostic Imaging , Pattern Recognition, Automated , Humans , Urologic Diseases/diagnosisABSTRACT
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.
Subject(s)
Coronary Angiography/methods , Coronary Stenosis/diagnostic imaging , Image Processing, Computer-Assisted , Medical Informatics , Artificial Intelligence , Coronary Angiography/statistics & numerical data , Humans , Pattern Recognition, Automated , Radiographic Image EnhancementSubject(s)
Pancreatic Neoplasms/diagnostic imaging , Algorithms , Biomedical Engineering , Cholangiopancreatography, Endoscopic Retrograde , Constriction, Pathologic , Dilatation, Pathologic , Humans , Image Processing, Computer-Assisted , Pancreatic Cyst/diagnostic imaging , Pancreatic Cyst/pathology , Pancreatic Ducts/diagnostic imaging , Pancreatic Ducts/pathology , Pancreatic Neoplasms/pathology , Pattern Recognition, AutomatedABSTRACT
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.