TY - JOUR
T1 - Computer-Aided Diagnosis (CAD) to Detect Brain Abnormality from PET Image using Artificial Neural Network (ANN)
AU - Kusumawardani, Y.
AU - Ratianto,
AU - Prajitno, P.
AU - Soejoko, D. S.
N1 - Publisher Copyright:
© Published under licence by IOP Publishing Ltd.
PY - 2020/6/15
Y1 - 2020/6/15
N2 - PET imaging is powerful to diagnose the presence of abnormalities, staging cancer, and evaluating radiotherapy treatment results. Sometimes, small uptake is not easily visual recognized, hence an additional supporting method for its detection is needed. In this study, Computer-Aided Diagnosis (CAD) of brain abnormalities from PET images using segmentation and classification methods based on a feature in the form of Gray Level CoOccurrence Matrix (GLCM) was developed Artificial Neural Network (ANN) is used to deal with the classification problems arising in this application. We develop CAD in this study using MATLAB. A total number of samples were 360 images with 180 abnormal (14 patient) and 180 normal (20 patient) images were used as training and testing data. The result based on Receiver Operating Characteristic (ROC) illustrated that the training error was 4.22 ± 2.37 % and the test error was 12.30 ± 3.47%. These results mean that this developed CAD system can recognize normal and abnormal brain images.
AB - PET imaging is powerful to diagnose the presence of abnormalities, staging cancer, and evaluating radiotherapy treatment results. Sometimes, small uptake is not easily visual recognized, hence an additional supporting method for its detection is needed. In this study, Computer-Aided Diagnosis (CAD) of brain abnormalities from PET images using segmentation and classification methods based on a feature in the form of Gray Level CoOccurrence Matrix (GLCM) was developed Artificial Neural Network (ANN) is used to deal with the classification problems arising in this application. We develop CAD in this study using MATLAB. A total number of samples were 360 images with 180 abnormal (14 patient) and 180 normal (20 patient) images were used as training and testing data. The result based on Receiver Operating Characteristic (ROC) illustrated that the training error was 4.22 ± 2.37 % and the test error was 12.30 ± 3.47%. These results mean that this developed CAD system can recognize normal and abnormal brain images.
UR - http://www.scopus.com/inward/record.url?scp=85086801745&partnerID=8YFLogxK
U2 - 10.1088/1742-6596/1505/1/012002
DO - 10.1088/1742-6596/1505/1/012002
M3 - Conference article
AN - SCOPUS:85086801745
SN - 1742-6588
VL - 1505
JO - Journal of Physics: Conference Series
JF - Journal of Physics: Conference Series
IS - 1
M1 - 012002
T2 - 3rd Annual Scientific Meeting on Medical Physics and Biophysics, PIT-FMB in conjunction with the 17th South-East Asia Congress of Medical Physics, SEACOMP 2019
Y2 - 8 August 2019 through 10 August 2019
ER -
