Neural network assisted Gamma knife radiosurgery treatment planning: Basic studies

Y. J. Tseng, W. C. Chu, Pau-Choo Chung, W. Y. Chung, D. H C Pan

Research output: Contribution to journalArticle

Abstract

Due to the extreme accuracy requirement of Gamma knife stereotactic radiosurgery, the treatment planning procedure has been a time consuming and enduring process for neurosurgeons to uphold. For this reason, we propose using artificial neural network to integrate traditional intricate diagnosing procedures to determine multi-focal shots, focal positions and weightings in an automatic or semi-automatic way. We use error-back-propagation neural network algorithm to train 32 phantom cases and 74 real cases acquired from the Neurological Institute of Veterans General Hospital, Taipei. After pre- processing procedure, tumor lesion data was encoded as input vector and the treatment result as the output vector of the artificial neural network. The program was constructed with an object-oriented programming concept that runs on a PC platform. Partial successes have been obtained for simple-shaped tumors, however, for complex-shaped and/or large tumors, further endeavors are required. Discussions on this are included.

Original languageEnglish
Pages (from-to)97-105
Number of pages9
JournalChinese Journal of Medical and Biological Engineering
Volume18
Issue number2
Publication statusPublished - 1998

Fingerprint

Radiosurgery
Tumors
Neural networks
Planning
Veterans Hospitals
Neoplasms
Object oriented programming
Backpropagation
General Hospitals
Therapeutics
Processing

All Science Journal Classification (ASJC) codes

  • Biophysics

Cite this

@article{b45f2ae4ce164c8381203404bcc6f20d,
title = "Neural network assisted Gamma knife radiosurgery treatment planning: Basic studies",
abstract = "Due to the extreme accuracy requirement of Gamma knife stereotactic radiosurgery, the treatment planning procedure has been a time consuming and enduring process for neurosurgeons to uphold. For this reason, we propose using artificial neural network to integrate traditional intricate diagnosing procedures to determine multi-focal shots, focal positions and weightings in an automatic or semi-automatic way. We use error-back-propagation neural network algorithm to train 32 phantom cases and 74 real cases acquired from the Neurological Institute of Veterans General Hospital, Taipei. After pre- processing procedure, tumor lesion data was encoded as input vector and the treatment result as the output vector of the artificial neural network. The program was constructed with an object-oriented programming concept that runs on a PC platform. Partial successes have been obtained for simple-shaped tumors, however, for complex-shaped and/or large tumors, further endeavors are required. Discussions on this are included.",
author = "Tseng, {Y. J.} and Chu, {W. C.} and Pau-Choo Chung and Chung, {W. Y.} and Pan, {D. H C}",
year = "1998",
language = "English",
volume = "18",
pages = "97--105",
journal = "Journal of Medical and Biological Engineering",
issn = "1609-0985",
publisher = "Biomedical Engineering Society",
number = "2",

}

Neural network assisted Gamma knife radiosurgery treatment planning : Basic studies. / Tseng, Y. J.; Chu, W. C.; Chung, Pau-Choo; Chung, W. Y.; Pan, D. H C.

In: Chinese Journal of Medical and Biological Engineering, Vol. 18, No. 2, 1998, p. 97-105.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Neural network assisted Gamma knife radiosurgery treatment planning

T2 - Basic studies

AU - Tseng, Y. J.

AU - Chu, W. C.

AU - Chung, Pau-Choo

AU - Chung, W. Y.

AU - Pan, D. H C

PY - 1998

Y1 - 1998

N2 - Due to the extreme accuracy requirement of Gamma knife stereotactic radiosurgery, the treatment planning procedure has been a time consuming and enduring process for neurosurgeons to uphold. For this reason, we propose using artificial neural network to integrate traditional intricate diagnosing procedures to determine multi-focal shots, focal positions and weightings in an automatic or semi-automatic way. We use error-back-propagation neural network algorithm to train 32 phantom cases and 74 real cases acquired from the Neurological Institute of Veterans General Hospital, Taipei. After pre- processing procedure, tumor lesion data was encoded as input vector and the treatment result as the output vector of the artificial neural network. The program was constructed with an object-oriented programming concept that runs on a PC platform. Partial successes have been obtained for simple-shaped tumors, however, for complex-shaped and/or large tumors, further endeavors are required. Discussions on this are included.

AB - Due to the extreme accuracy requirement of Gamma knife stereotactic radiosurgery, the treatment planning procedure has been a time consuming and enduring process for neurosurgeons to uphold. For this reason, we propose using artificial neural network to integrate traditional intricate diagnosing procedures to determine multi-focal shots, focal positions and weightings in an automatic or semi-automatic way. We use error-back-propagation neural network algorithm to train 32 phantom cases and 74 real cases acquired from the Neurological Institute of Veterans General Hospital, Taipei. After pre- processing procedure, tumor lesion data was encoded as input vector and the treatment result as the output vector of the artificial neural network. The program was constructed with an object-oriented programming concept that runs on a PC platform. Partial successes have been obtained for simple-shaped tumors, however, for complex-shaped and/or large tumors, further endeavors are required. Discussions on this are included.

UR - http://www.scopus.com/inward/record.url?scp=0031732598&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0031732598&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:0031732598

VL - 18

SP - 97

EP - 105

JO - Journal of Medical and Biological Engineering

JF - Journal of Medical and Biological Engineering

SN - 1609-0985

IS - 2

ER -