Artificial neural network-statistical approach for PET volume analysis and classification

Mhd. Saeed Sharif, Maysam Abbod, Abbes Amira, Habib Zaidi

Research output: Contribution to journalArticle

Abstract

The increasing number of imaging studies and the prevailing application of positron emission tomography (PET) in clinical oncology have led to a real need for efficient PET volume handling and the development of new volume analysis approaches to aid the clinicians in the clinical diagnosis, planning of treatment, and assessment of response to therapy. A novel automated system for oncological PET volume analysis is proposed in this work. The proposed intelligent system deploys two types of artificial neural networks (ANNs) for classifying PET volumes. The first methodology is a competitive neural network (CNN), whereas the second one is based on learning vector quantisation neural network (LVQNN). Furthermore, Bayesian information criterion (BIC) is used in this system to assess the optimal number of classes for each PET data set and assist the ANN blocks to achieve accurate analysis by providing the best number of classes. The system evaluation was carried out using experimental phantom studies (NEMA IEC image quality body phantom), simulated PET studies using the Zubal phantom, and clinical studies representative of nonsmall cell lung cancer and pharyngolaryngeal squamous cell carcinoma. The proposed analysis methodology of clinical oncological PET data has shown promising results and can successfully classify and quantify malignant lesions.
Original languageEnglish
Article number327861,
JournalAdvances in Fuzzy Systems
Volume2012
DOIs
Publication statusPublished - 2012
Externally publishedYes

Fingerprint

Positron Emission Tomography
Positron emission tomography
Artificial Neural Network
Neural networks
Phantom
Neural Networks
Learning Vector Quantization
Oncology
Bayesian Information Criterion
Methodology
Lung Cancer
Cell
Vector quantization
Intelligent systems
Intelligent Systems
Image Quality
Image quality
Therapy
Quantify
Classify

Cite this

Sharif, Mhd. Saeed ; Abbod, Maysam ; Amira, Abbes ; Zaidi, Habib. / Artificial neural network-statistical approach for PET volume analysis and classification. In: Advances in Fuzzy Systems. 2012 ; Vol. 2012.
@article{bafdb4f584f1433cb7cca16985ccdc8f,
title = "Artificial neural network-statistical approach for PET volume analysis and classification",
abstract = "The increasing number of imaging studies and the prevailing application of positron emission tomography (PET) in clinical oncology have led to a real need for efficient PET volume handling and the development of new volume analysis approaches to aid the clinicians in the clinical diagnosis, planning of treatment, and assessment of response to therapy. A novel automated system for oncological PET volume analysis is proposed in this work. The proposed intelligent system deploys two types of artificial neural networks (ANNs) for classifying PET volumes. The first methodology is a competitive neural network (CNN), whereas the second one is based on learning vector quantisation neural network (LVQNN). Furthermore, Bayesian information criterion (BIC) is used in this system to assess the optimal number of classes for each PET data set and assist the ANN blocks to achieve accurate analysis by providing the best number of classes. The system evaluation was carried out using experimental phantom studies (NEMA IEC image quality body phantom), simulated PET studies using the Zubal phantom, and clinical studies representative of nonsmall cell lung cancer and pharyngolaryngeal squamous cell carcinoma. The proposed analysis methodology of clinical oncological PET data has shown promising results and can successfully classify and quantify malignant lesions.",
author = "Sharif, {Mhd. Saeed} and Maysam Abbod and Abbes Amira and Habib Zaidi",
year = "2012",
doi = "10.1155/2012/327861",
language = "English",
volume = "2012",
journal = "Advances in Fuzzy Systems",
issn = "1687-7101",
publisher = "Hindawi Publishing Corporation",

}

Artificial neural network-statistical approach for PET volume analysis and classification. / Sharif, Mhd. Saeed; Abbod, Maysam; Amira, Abbes; Zaidi, Habib.

In: Advances in Fuzzy Systems, Vol. 2012, 327861, 2012.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Artificial neural network-statistical approach for PET volume analysis and classification

AU - Sharif, Mhd. Saeed

AU - Abbod, Maysam

AU - Amira, Abbes

AU - Zaidi, Habib

PY - 2012

Y1 - 2012

N2 - The increasing number of imaging studies and the prevailing application of positron emission tomography (PET) in clinical oncology have led to a real need for efficient PET volume handling and the development of new volume analysis approaches to aid the clinicians in the clinical diagnosis, planning of treatment, and assessment of response to therapy. A novel automated system for oncological PET volume analysis is proposed in this work. The proposed intelligent system deploys two types of artificial neural networks (ANNs) for classifying PET volumes. The first methodology is a competitive neural network (CNN), whereas the second one is based on learning vector quantisation neural network (LVQNN). Furthermore, Bayesian information criterion (BIC) is used in this system to assess the optimal number of classes for each PET data set and assist the ANN blocks to achieve accurate analysis by providing the best number of classes. The system evaluation was carried out using experimental phantom studies (NEMA IEC image quality body phantom), simulated PET studies using the Zubal phantom, and clinical studies representative of nonsmall cell lung cancer and pharyngolaryngeal squamous cell carcinoma. The proposed analysis methodology of clinical oncological PET data has shown promising results and can successfully classify and quantify malignant lesions.

AB - The increasing number of imaging studies and the prevailing application of positron emission tomography (PET) in clinical oncology have led to a real need for efficient PET volume handling and the development of new volume analysis approaches to aid the clinicians in the clinical diagnosis, planning of treatment, and assessment of response to therapy. A novel automated system for oncological PET volume analysis is proposed in this work. The proposed intelligent system deploys two types of artificial neural networks (ANNs) for classifying PET volumes. The first methodology is a competitive neural network (CNN), whereas the second one is based on learning vector quantisation neural network (LVQNN). Furthermore, Bayesian information criterion (BIC) is used in this system to assess the optimal number of classes for each PET data set and assist the ANN blocks to achieve accurate analysis by providing the best number of classes. The system evaluation was carried out using experimental phantom studies (NEMA IEC image quality body phantom), simulated PET studies using the Zubal phantom, and clinical studies representative of nonsmall cell lung cancer and pharyngolaryngeal squamous cell carcinoma. The proposed analysis methodology of clinical oncological PET data has shown promising results and can successfully classify and quantify malignant lesions.

U2 - 10.1155/2012/327861

DO - 10.1155/2012/327861

M3 - Article

VL - 2012

JO - Advances in Fuzzy Systems

JF - Advances in Fuzzy Systems

SN - 1687-7101

M1 - 327861,

ER -