A feed forward neural network for classification of bull's-eye myocardial perfusion images

Identification of hypoperfused areas in myocardial perfusion single-photon emission tomography studies can be aided by bull's-eye representation of raw counts, lesion extent and lesion severity, the latter two being produced by comparison of the raw bull's-eye data with a normal data base. An artificial intelligence technique which is presently becoming widely popular and which is particularly suitable for pattern recognition is that of artificial neural network. We have studied the ability of feed forward neural networks to extract patterns from bull's-eye data by assessing their capability to predict lesion presence without direct comparison with a normal data base. Studies were undertaken on both simulation data and on real stress-rest data obtained from 410 male patients undergoing routine thallium-201 myocardial perfusion scintigraphy. The ability of trained neural networks to predict lesion presence was quantified by calculating the areas under receiver operating characteristic curves. Figures as high as 0.96 for non-preclassified patient data were obtained, corresponding to an accuracy of 92%. The results demonstrate that neural networks can accurately classify patterns from bull's-eye myocardial perfusion images and detect the presence of hypoperfused areas without the need for comparison with a normal data base. Preliminary work suggests that this technique could be used to study perfusion patterns in the myocardium and their correlation with clinical parameters.

[1]  A Murray,et al.  Development of a neural network screening aid for diagnosing lower limb peripheral vascular disease from photoelectric plethysmography pulse waveforms. , 1993, Physiological measurement.

[2]  C. Metz.  Basic principles of ROC analysis. , 1978, Seminars in nuclear medicine.

[3]  G. W. Gross,et al.  Neural networks in radiologic diagnosis. II. Interpretation of neonatal chest radiographs. , 1990, Investigative radiology.

[4]  J. Hanley,et al.  The meaning and use of the area under a receiver operating characteristic (ROC) curve. , 1982, Radiology.

[5]  Y. Wu,et al.  Potential usefulness of an artificial neural network for differential diagnosis of interstitial lung diseases: pilot study. , 1990, Radiology.

[6]  Russell C. Eberhart,et al.  Neural network PC tools: a practical guide , 1990 .

[7]  C E Floyd,et al.  An artificial neural network for lesion detection on single-photon emission computed tomographic images. , 1992, Investigative radiology.

[8]  Philip D. Wasserman,et al.  Neural computing - theory and practice , 1989 .

[9]  William G. Baxt,et al.  Use of an Artificial Neural Network for Data Analysis in Clinical Decision-Making: The Diagnosis of Acute Coronary Occlusion , 1990, Neural Computation.

[10]  H Fujita,et al.  Application of artificial neural network to computer-aided diagnosis of coronary artery disease in myocardial SPECT bull's-eye images. , 1992, Journal of nuclear medicine : official publication, Society of Nuclear Medicine.

[11]  William G. Baxt,et al.  Improving the Accuracy of an Artificial Neural Network Using Multiple Differently Trained Networks , 1992, Neural Computation.

[12]  A. Detsky,et al.  Neural networks: what are they? , 1991, Annals of internal medicine.

[13]  J W Clark,et al.  Neural network modelling , 1991, Physics in medicine and biology.

[14]  C. Shufflebarger,et al.  What is neutral network , 1992 .

[15]  P. Cheron,et al.  Correlation of 99Tcm-sestamibi SPECT with coronary angiography in general hospital practice. , 1993, Nuclear medicine communications.

[16]  R. Scott,et al.  Artificial intelligence: its use in medical diagnosis. , 1993, Journal of nuclear medicine : official publication, Society of Nuclear Medicine.

[17]  B L Holman,et al.  A neural network classifier for cerebral perfusion imaging. , 1994, Journal of nuclear medicine : official publication, Society of Nuclear Medicine.

[18]  Anil K. Jain,et al.  Artificial Neural Networks , 2010 .

[19]  W. Baxt.  Analysis of the clinical variables driving decision in an artificial neural network trained to identify the presence of myocardial infarction. , 1992, Annals of emergency medicine.

[20]  David G. Bounds,et al.  A comparison of neural network and other pattern recognition approaches to the diagnosis of low back disorders , 1990, Neural Networks.

[21]  W. Baxt.  Use of an artificial neural network for the diagnosis of myocardial infarction. , 1991, Annals of internal medicine.

[22]  D S Berman,et al.  Quantification of rotational thallium-201 myocardial tomography. , 1985, Journal of nuclear medicine : official publication, Society of Nuclear Medicine.

[23]  J M Boone,et al.  Neural networks in radiology: an introduction and evaluation in a signal detection task. , 1990, Medical physics.

[24]  Metin Akay,et al.  Noninvasive diagnosis of coronary artery disease using a neural network algorithm , 1993, Biological Cybernetics.

[25]  J R Stratton,et al.  Quantitation of size of relative myocardial perfusion defect by single-photon emission computed tomography. , 1984, Circulation.

[26]  E. Depuey,et al.  Quantitative rotational thallium-201 tomography for identifying and localizing coronary artery disease. , 1988, Circulation.

[27]  J. Scott,et al.  Neural network analysis of ventilation-perfusion lung scans. , 1993, Radiology.

[28]  J. M. Thome,et al.  Application of an artificial neural network in radiographic diagnosis , 1991, Journal of Digital Imaging.

[29]  J. Kippenhan,et al.  Evaluation of a neural-network classifier for PET scans of normal and Alzheimer's disease subjects. , 1992, Journal of nuclear medicine : official publication, Society of Nuclear Medicine.

[30]  B. H. Blott,et al.  Review of neural network applications in medical imaging and signal processing , 1992, Medical and Biological Engineering and Computing.

[31]  J M Boone,et al.  Neural networks in radiologic diagnosis. I. Introduction and illustration. , 1990, Investigative radiology.

[32]  C. Metz.  ROC Methodology in Radiologic Imaging , 1986, Investigative radiology.

[33]  M L Meistrell,et al.  Evaluation of neural network performance by receiver operating characteristic (ROC) analysis: examples from the biotechnology domain. , 1989, Computer methods and programs in biomedicine.

[34]  P. Camici,et al.  Syndrome X: radionuclide studies of myocardial perfusion in patients with chest pain and normal coronary arteriograms , 2004, European Journal of Nuclear Medicine.