Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Videos

Vector-entropy optimization-based neural-network approach to image reconstruction from projections.

Y Wang¹, F M Wahl

¹Dept. of Life Sci. and Biomed. Eng., Zhejiang Univ.

IEEE Transactions on Neural Networks

|January 1, 1997

Summary

This summary is machine-generated.

Related Concept Videos

Maximizing the Directional Derivative

Maximizing the Directional Derivative

The directional derivative is a central concept in multivariable calculus that describes how a function changes at a given point when moving in a specified direction. This direction is represented by a unit vector, ensuring that only the orientation influences the rate of change. By varying the direction, different rates of change can be observed, demonstrating that the directional derivative depends strongly on the chosen direction.The directional derivative is computed using the gradient...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

CT-based manual segmentation and evaluation of paranasal sinuses.

European archives of oto-rhino-laryngology : official journal of the European Federation of Oto-Rhino-Laryngological Societies (EUFOS) : affiliated with the German Society for Oto-Rhino-Laryngology - Head and Neck Surgery·2008

Same author

Using robotic systems in order to determine biomechanical properties of soft tissues.

Studies in health technology and informatics·2008

Same author

Design of an enhanced hybrid fuzzy P+ID controller for a mechanical manipulator.

IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics : a publication of the IEEE Systems, Man, and Cybernetics Society·2008

Same author

[Evaluation of force data with a force/torque sensor during FESS. A step towards robot-assisted surgery].

HNO·2008

Same author

3D endoscopic approach for endonasal sinus surgery.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2007

Same author

Comparison between manual and semi-automatic segmentation of nasal cavity and paranasal sinuses from CT images.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2007

This study introduces a novel neural network model for image reconstruction, enhancing accuracy and image quality. The multiobjective decision-making approach outperforms traditional methods in simulations and real-world data.

Area of Science:

Medical Imaging
Computational Neuroscience
Artificial Intelligence

Background:

Image reconstruction is crucial in medical imaging, often relying on iterative algorithms.
Conventional methods like MART and convolution have limitations in accuracy and image quality.
Neural network models offer potential for improved image reconstruction.

Purpose of the Study:

To propose a novel multiobjective decision-making based neural-network model for image reconstruction.
To develop and evaluate a weighted sum optimization-based neural-network algorithm for this task.
To compare the proposed method against conventional iterative reconstruction techniques.

Main Methods:

A hybrid model combining Hopfield's neural network with multiobjective decision-making.

Related Experiment Videos

Development of a weighted sum optimization algorithm utilizing Euler's iteration.

Application to computer-generated noisy projections and Siemens Somatson DR scanner data.

Main Results:

The proposed method demonstrated superior reconstruction accuracy compared to MART and convolution.
Computer simulations showed significant improvements in image quality.
Enhanced convergence behavior was observed compared to conventional algorithms.

Conclusions:

The multiobjective decision-making based neural-network model offers a promising advancement in image reconstruction.
This approach yields higher accuracy and better image quality than existing methods.
The algorithm is effective for both simulated and real-world medical imaging data.