BIOMAT Database Logo BIOMAT Database Logo

An artificial neural network for lesion detection on single-photon emission computed tomographic images. 1992

C E Floyd, and G D Tourassi
Department of Radiology, Duke University Medical Center, Duke University, Durham, North Carolina 27710.

OBJECTIVE An artificial neural network (ANN) has been developed to detect nonactive circular lesions on single-slice, single-photon emission computed tomographic (SPECT) images reconstructed using filtered back projection (FBP). METHODS The neural network is a single-layer perception which learns to identify features on the SPECT image using supervised training with a modified delta rule. The network was trained on a set of SPECT images containing clinically realistic levels of noise. The trained network was applied to a set of 120 images, and the detection performance was evaluated at several decision thresholds using receiver operating characteristic (ROC) analysis. RESULTS The trained neural network performed better than human observers for the same detection task with the same images as reflected by a significantly larger ROC curve area. CONCLUSIONS ANN can be trained successfully to perform lesion detection on reconstructed SPECT images.

UI MeSH Term Description Entries
D008961 Models, Structural A representation, generally small in scale, to show the structure, construction, or appearance of something. (From Random House Unabridged Dictionary, 2d ed) Model, Structural,Structural Model,Structural Models
D004867 Equipment Design Methods and patterns of fabricating machines and related hardware. Design, Equipment,Device Design,Medical Device Design,Design, Medical Device,Designs, Medical Device,Device Design, Medical,Device Designs, Medical,Medical Device Designs,Design, Device,Designs, Device,Designs, Equipment,Device Designs,Equipment Designs
D006801 Humans Members of the species Homo sapiens. Homo sapiens,Man (Taxonomy),Human,Man, Modern,Modern Man
D012372 ROC Curve A graphic means for assessing the ability of a screening test to discriminate between healthy and diseased persons; may also be used in other studies, e.g., distinguishing stimuli responses as to a faint stimuli or nonstimuli. ROC Analysis,Receiver Operating Characteristic,Analysis, ROC,Analyses, ROC,Characteristic, Receiver Operating,Characteristics, Receiver Operating,Curve, ROC,Curves, ROC,ROC Analyses,ROC Curves,Receiver Operating Characteristics
D012985 Software Design Specifications and instructions applied to the software. Flowcharts (Computer),Flow Charts (Computer),Flowcharts,Chart, Flow (Computer),Charts, Flow (Computer),Design, Software,Designs, Software,Flow Chart (Computer),Flowchart,Flowchart (Computer),Software Designs
D015588 Observer Variation The failure by the observer to measure or identify a phenomenon accurately, which results in an error. Sources for this may be due to the observer's missing an abnormality, or to faulty technique resulting in incorrect test measurement, or to misinterpretation of the data. Two varieties are inter-observer variation (the amount observers vary from one another when reporting on the same material) and intra-observer variation (the amount one observer varies between observations when reporting more than once on the same material). Bias, Observer,Interobserver Variation,Intraobserver Variation,Observer Bias,Inter-Observer Variability,Inter-Observer Variation,Interobserver Variability,Intra-Observer Variability,Intra-Observer Variation,Intraobserver Variability,Inter Observer Variability,Inter Observer Variation,Inter-Observer Variabilities,Inter-Observer Variations,Interobserver Variabilities,Interobserver Variations,Intra Observer Variability,Intra Observer Variation,Intra-Observer Variabilities,Intra-Observer Variations,Intraobserver Variabilities,Intraobserver Variations,Observer Variations,Variabilities, Inter-Observer,Variabilities, Interobserver,Variabilities, Intra-Observer,Variabilities, Intraobserver,Variability, Inter-Observer,Variability, Interobserver,Variability, Intra-Observer,Variability, Intraobserver,Variation, Inter-Observer,Variation, Interobserver,Variation, Intra-Observer,Variation, Intraobserver,Variation, Observer,Variations, Inter-Observer,Variations, Interobserver,Variations, Intra-Observer,Variations, Intraobserver,Variations, Observer
D015899 Tomography, Emission-Computed, Single-Photon A method of computed tomography that uses radionuclides which emit a single photon of a given energy. The camera is rotated 180 or 360 degrees around the patient to capture images at multiple positions along the arc. The computer is then used to reconstruct the transaxial, sagittal, and coronal images from the 3-dimensional distribution of radionuclides in the organ. The advantages of SPECT are that it can be used to observe biochemical and physiological processes as well as size and volume of the organ. The disadvantage is that, unlike positron-emission tomography where the positron-electron annihilation results in the emission of 2 photons at 180 degrees from each other, SPECT requires physical collimation to line up the photons, which results in the loss of many available photons and hence degrades the image. CAT Scan, Single-Photon Emission,CT Scan, Single-Photon Emission,Radionuclide Tomography, Single-Photon Emission-Computed,SPECT,Single-Photon Emission-Computed Tomography,Tomography, Single-Photon, Emission-Computed,Single-Photon Emission CT Scan,Single-Photon Emission Computer-Assisted Tomography,Single-Photon Emission Computerized Tomography,CAT Scan, Single Photon Emission,CT Scan, Single Photon Emission,Emission-Computed Tomography, Single-Photon,Radionuclide Tomography, Single Photon Emission Computed,Single Photon Emission CT Scan,Single Photon Emission Computed Tomography,Single Photon Emission Computer Assisted Tomography,Single Photon Emission Computerized Tomography,Tomography, Single-Photon Emission-Computed
D016571 Neural Networks, Computer A computer architecture, implementable in either hardware or software, modeled after biological neural networks. Like the biological system in which the processing capability is a result of the interconnection strengths between arrays of nonlinear processing nodes, computerized neural networks, often called perceptrons or multilayer connectionist models, consist of neuron-like units. A homogeneous group of units makes up a layer. These networks are good at pattern recognition. They are adaptive, performing tasks by example, and thus are better for decision-making than are linear learning machines or cluster analysis. They do not require explicit programming. Computational Neural Networks,Connectionist Models,Models, Neural Network,Neural Network Models,Neural Networks (Computer),Perceptrons,Computational Neural Network,Computer Neural Network,Computer Neural Networks,Connectionist Model,Model, Connectionist,Model, Neural Network,Models, Connectionist,Network Model, Neural,Network Models, Neural,Network, Computational Neural,Network, Computer Neural,Network, Neural (Computer),Networks, Computational Neural,Networks, Computer Neural,Networks, Neural (Computer),Neural Network (Computer),Neural Network Model,Neural Network, Computational,Neural Network, Computer,Neural Networks, Computational,Perceptron

Related Publications

C E Floyd, and G D Tourassi
Neural network reconstruction of single-photon emission computed tomography images.
August 1995, Journal of digital imaging,
C E Floyd, and G D Tourassi
Artificial neural network modeling of stress single-photon emission computed tomographic imaging for detecting extensive coronary artery disease.
January 2005, The American journal of cardiology,
C E Floyd, and G D Tourassi
An artificial neural network approach to quantitative single photon emission computed tomographic reconstruction with collimator, attenuation, and scatter compensation.
December 1994, Medical physics,
C E Floyd, and G D Tourassi
A simple method for localising single-photon emission computed tomographic images on an anatomical template.
April 1996, Neuroradiology,
C E Floyd, and G D Tourassi
Routine single-photon-emission computed tomographic brain imaging.
January 1988, American journal of physiologic imaging,
C E Floyd, and G D Tourassi
Single-photon-emission computed tomographic imaging of glioma.
January 1988, American journal of physiologic imaging,
C E Floyd, and G D Tourassi
Myocardial single-photon emission computed tomographic quality assurance.
January 1996, Journal of nuclear cardiology : official publication of the American Society of Nuclear Cardiology,
C E Floyd, and G D Tourassi
Detection of lung tumor by single-photon emission computed tomographic sestamibi imaging.
January 1996, Journal of nuclear cardiology : official publication of the American Society of Nuclear Cardiology,
C E Floyd, and G D Tourassi
Computer-assisted fusion of single-photon emission tomographic and computed tomographic images. Evaluation in complicated inflammatory disease.
January 1992, Investigative radiology,
C E Floyd, and G D Tourassi
Backpropagation Neural Network for Motion Analysis on Blood-pool Gated Single Photon Emission Computed Tomography.
January 2005, Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual Conference,
Copied contents to your clipboard!