Lucy S. Goodenday

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 cardiologists 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.

Bayesian learning for cardiac SPECT image interpretation

In this paper, we describe a system for automating the diagnosis of myocardial perfusion from single-photon emission computerized tomography (SPECT) images of male and female hearts. Initially we had several thousand of SPECT images, other clinical data and physician-interpreters descriptions of the images. The images were divided into segments based on the Yale system. Each segment was described by the physician as showing one of the following conditions: normal perfusion, reversible perfusion defect, partially reversible perfusion defect, fixed perfusion defect, defect showing reverse redistribution, equivocal defect or artifact. The physicians diagnosis of overall left ventricular (LV) perfusion, based on the above descriptions, categorizes a study as showing one or more of eight possible conditions: normal, ischemia, infarct and ischemia, infarct, reverse redistribution, equivocal, artifact or LV dysfunction. Because of the complexity of the task, we decided to use the knowledge discovery approach, consisting of these steps: problem understanding, data understanding, data preparation, data mining, evaluating the discovered knowledge and its implementation. After going through the data preparation step, in which we constructed normal gender-specific models of the LV and image registration, we ended up with 728 patients for whom we had both SPECT images and corresponding diagnoses. Another major contribution of the paper is the data mining step, in which we used several new Bayesian learning classification methods. The approach we have taken, namely the six-step knowledge discovery process has proven to be very successful in this complex data mining task and as such the process can be extended to other medical data mining projects.

Using fuzzy sets to diagnose coronary artery stenosis

The use of fuzzy sets to represent perfusion defects and to generate expert results to help in diagnosis is reported. Retrospective data collected from 91 patients who underwent both stress thallium-201 myocardial scintigraphy and coronary arteriography were used. Of the total, 64 scans were chosen at random for training, and the remaining 27 scans were used for testing data. It was found that 17 rules generated by fuzzy set theory performed as well as 68 rules specified by cardiologists in diagnosing coronary artery stenosis.<<ETX>>

Issues in automating cardiac SPECT diagnosis

Discusses the computational complexity involved in knowledge discovery when working with images. Data mining and general knowledge discovery techniques appear to be useful for classification of SPECT cardiac images. Creation and mining of the database has illustrated the importance of precision in data input, which is not always present in the narrative, or even in graphics-coded descriptions of images provided by physicians. Using data mining techniques on the raw images themselves may actually improve diagnosis and help clean the database. At the moment, these are time-consuming tasks, but methods are available to improve time requirements. As in all diagnostic systems, addition of more representative cases in each classification should improve performafice. Such techniques may also have application in the quality control of diagnostic laboratories.

A novel algorithm for classification of SPECT images of a human heart

Describes a semi-automated procedure for analyzing single photon emission computed tomography (SPECT) images of a human heart and classifying the images into one of several categories: normal, infarct, ischemia, infarct and ischemia, reverse re-distribution, artifact and equivocal. The procedure aids the physician in the interpretation of SPECT images and consists of two steps. The first step processes the reconstructed SPECT images. These images contain multiple slices of 64/spl times/64 pixels with 16 bits resolution. Scanned images are converted into numerical format by using boundary extraction, region of interest (ROI) selection, and segmentation techniques. A new algorithm was developed to extract a rectangular ROI from each image. The second step involves automatic classification of the processed images into one of the seven categories, listed above, using a knowledge-based system employing machine learning algorithms (C4.5 and CLIP3) and fuzzy logic modeling, to generate classification rules. The performance of the system is measured in terms of accuracy, the gold standard being interpretation of the images by experienced cardiologists. The accuracy of the system using the rules generated by the machine learning algorithms were 94% and 81%, respectively. Accuracy, after the fuzzy linguistic variables were specified from the rules generated by the C4.5 and CLIP3 algorithms, was 91% and 86%, respectively. Overall, the system performance closely approximated that of an experienced cardiologist.

A neuro-fuzzy algorithm for diagnosis of coronary artery stenosis.

In this paper a method of fuzzy decision making applied to diagnosis of coronary artery stenosis is presented. The method uses a neural network approach for the diagnosis of stenosis in the three main coronary arteries (left anterior descending, right coronary artery, and circumflex). First, the knowledge base domain, 201Tl scintigram training data, is explained and the method of preprocessing the original heart images is given. Next, the method of dealing with the uncertainties present in the data using the fuzzy approach is outlined. Finally, the algorithm and the results are discussed and compared with other approaches.

A Bayesian approach for dealing with uncertainties in detection of coronary artery stenosis using a knowledge-based system

A knowledge-based system that combines subjective Bayesian methods with rules specified by cardiologists to diagnose coronary artery stenosis from postexercise myocardial perfusion scintigrams is discussed. This expert system was used to determine which of the three main coronary arteries had the dominant stenosis. The system also indicated when a patient had a normal myocardial perfusion pattern (no stenosis). The system was run on a set of scans from 91 patients, and the results were compared with an existing expert system that uses the Dempster-Shafer theory of evidence for dealing with uncertainties. The system was able to determine the coronary artery with the dominant stenosis over 90% of the time when supplied with prior knowledge that all the patients have single-vessel stenosis. The system was also able to determine with good accuracy whether a patient had a stenosed coronary artery or normal myocardial perfusion when no prior information was available. The program can be used initially to screen out patients with normal scintigrams. Once the patients with normal scintigrams have been removed, the expert system can then be run on the remaining patients and utilize prior knowledge that they have stenosed coronary arteries. This improves the reliability of the diagnosis.<<ETX>>

Hyponatremia in patients treated with lorcainide, a new antiarrhythmic drug

The effects of lorcainide, a new antiarrhythmic drug, on serum electrolytes and osmolality are described in a series of 33 patients with organic heart disease and complex ventricular arrhythmias treated with lorcainide. In eight patients, a mean decrease in serum Na+ of 8.25 +/- 3.2 mEq/L was observed after a single 200 mg intravenous dose of lorcainide. Sixteen of 33 patients developed significant hyponatremia and hypoosmolality during oral treatment with lorcainide. In all except two patients, serum Na+ returned to normal values within 3 to 12 months of continued lorcainide therapy. Low serum Na+ and hypoosmolality in the absence of volume depletion, clinically manifest edema, and unaltered renal, adrenal, cardiac, or thyroid function suggest that this antiarrhythmic drug produced the syndrome of inappropriate antidiuretic hormone secretion (SIADH). SIADH appeared to be transient and asymptomatic in our patients. One patient developed severe hyponatremia with serum Na+ of 108 mEq/L when hydrochlorothiazide was given to control hypertension. It is concluded that SIADH is an important side effect of lorcainide therapy. We recommend that serum Na+ be carefully monitored in patients started on lorcainide therapy, and extreme caution should be exercised in prescribing diuretics to patients with persistent hyponatremia.

An expert system for diagnosis of coronary artery stenosis based on 201Tl scintigrams using the Dempster-Shafer theory of evidence

An expert system for the diagnosis of stenoses in the three main coronary arteries (left anterior descending, right coronary artery and circumflex) is described. First, the knowledge base domain--201Tl scintigrams--is explained and the method of preprocessing the original heart images is given. Next, the method of dealing with the uncertainties present both in the cardiologist-specified rules and the data using the Dempster-Shafer theory of evidence is explained. Finally, the constructed expert system and the results are discussed and several graphical examples are shown.

Design and Testing of a Classification System which Recognizes Coronary Stenosis by Site and Relative Severity, Using Myocardial Tl-201 Scintigrams

The main theme of this paper is an implementation of fuzzy clustering in order to determine whether perfusion patterns exist which are diagnostically specific for the location of stenosis in a particular major coronary artery. During the past decade, Tl-201 myocardial scintigraphy has proven its value for the detection of ischemic heart disease, and, more recently, for establishing prognosis [1]. Other clinically important data, however, such as the site of greatest coronary artery obstruction and its relative severity compared to stenoses in other arteries, has not been as readily derived from planar Tl-201 scintigrams.