Knowledge-based enhancement of megavoltage images in radiation therapy using a hybrid neuro-fuzzy system

H. R. Tizhoosh; G. Krell; B. Michaelis

doi:10.1016/S0262-8856(00)00070-6

Knowledge-based enhancement of megavoltage images in radiation therapy using a hybrid neuro-fuzzy system

H. R. Tizhoosh, G. Krell, B. Michaelis

Artificial Intelligence and Informatics

Research output: Contribution to journal › Article › peer-review

Abstract

Megavoltage images (MVIs) are used in radiation therapy for verification of the patient's position during cancer treatment. Due to the physics of imaging devices, the quality of MVI is very poor. In this work, we propose a hybrid neuro-fuzzy system consisting of fuzzy techniques and neural nets for knowledge-based enhancement of MVIs. The fuzzy enhancement includes different contrast adaptation techniques and also soft filtering, respectively. A modified associative memory is trained using a priori knowledge for image restoration. In order to consider the subjective demands of physicians, an observer-dependent overall system for contrast adaptation is also proposed.

Original language	English (US)
Pages (from-to)	217-233
Number of pages	17
Journal	Image and Vision Computing
Volume	19
Issue number	4
DOIs	https://doi.org/10.1016/S0262-8856(00)00070-6
State	Published - Mar 2001

ASJC Scopus subject areas

Signal Processing
Computer Vision and Pattern Recognition

Access to Document

10.1016/S0262-8856(00)00070-6

Cite this

@article{6ed98b68fb6f454383bb455e43415875,

title = "Knowledge-based enhancement of megavoltage images in radiation therapy using a hybrid neuro-fuzzy system",

abstract = "Megavoltage images (MVIs) are used in radiation therapy for verification of the patient's position during cancer treatment. Due to the physics of imaging devices, the quality of MVI is very poor. In this work, we propose a hybrid neuro-fuzzy system consisting of fuzzy techniques and neural nets for knowledge-based enhancement of MVIs. The fuzzy enhancement includes different contrast adaptation techniques and also soft filtering, respectively. A modified associative memory is trained using a priori knowledge for image restoration. In order to consider the subjective demands of physicians, an observer-dependent overall system for contrast adaptation is also proposed.",

author = "Tizhoosh, {H. R.} and G. Krell and B. Michaelis",

note = "Funding Information: This work was supported by EU grant (Contract No. BMH4-CT95-0567), grant FKZ 002 KE 1996, Land Sachsen-Anhalt, and FKZ 0002KE009, Land Sachsen-Anhalt. We also gratefully thank Prof. G. Gademann (Clinic for Radiation Therapy, Magdeburg, Germany) and Dr C. Moore (Christie Hospital, Manchester, UK) for providing us with image data. ",

year = "2001",

month = mar,

doi = "10.1016/S0262-8856(00)00070-6",

language = "English (US)",

volume = "19",

pages = "217--233",

journal = "Image and Vision Computing",

issn = "0262-8856",

publisher = "Elsevier Limited",

number = "4",

}

TY - JOUR

T1 - Knowledge-based enhancement of megavoltage images in radiation therapy using a hybrid neuro-fuzzy system

AU - Tizhoosh, H. R.

AU - Krell, G.

AU - Michaelis, B.

N1 - Funding Information: This work was supported by EU grant (Contract No. BMH4-CT95-0567), grant FKZ 002 KE 1996, Land Sachsen-Anhalt, and FKZ 0002KE009, Land Sachsen-Anhalt. We also gratefully thank Prof. G. Gademann (Clinic for Radiation Therapy, Magdeburg, Germany) and Dr C. Moore (Christie Hospital, Manchester, UK) for providing us with image data.

PY - 2001/3

Y1 - 2001/3

N2 - Megavoltage images (MVIs) are used in radiation therapy for verification of the patient's position during cancer treatment. Due to the physics of imaging devices, the quality of MVI is very poor. In this work, we propose a hybrid neuro-fuzzy system consisting of fuzzy techniques and neural nets for knowledge-based enhancement of MVIs. The fuzzy enhancement includes different contrast adaptation techniques and also soft filtering, respectively. A modified associative memory is trained using a priori knowledge for image restoration. In order to consider the subjective demands of physicians, an observer-dependent overall system for contrast adaptation is also proposed.

AB - Megavoltage images (MVIs) are used in radiation therapy for verification of the patient's position during cancer treatment. Due to the physics of imaging devices, the quality of MVI is very poor. In this work, we propose a hybrid neuro-fuzzy system consisting of fuzzy techniques and neural nets for knowledge-based enhancement of MVIs. The fuzzy enhancement includes different contrast adaptation techniques and also soft filtering, respectively. A modified associative memory is trained using a priori knowledge for image restoration. In order to consider the subjective demands of physicians, an observer-dependent overall system for contrast adaptation is also proposed.

UR - http://www.scopus.com/inward/record.url?scp=0035283255&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0035283255&partnerID=8YFLogxK

U2 - 10.1016/S0262-8856(00)00070-6

DO - 10.1016/S0262-8856(00)00070-6

M3 - Article

AN - SCOPUS:0035283255

SN - 0262-8856

VL - 19

SP - 217

EP - 233

JO - Image and Vision Computing

JF - Image and Vision Computing

IS - 4

ER -

Knowledge-based enhancement of megavoltage images in radiation therapy using a hybrid neuro-fuzzy system

Abstract

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this