TY - JOUR
T1 - Artificial neural networks for single photon emission computed tomography
T2 - A study of cold lesion detection and localization
AU - Tourassi, Georgia D.
AU - Floyd, Carey E.
PY - 1993/8
Y1 - 1993/8
N2 - RATIONALE AND OBJECTIVES. An artificial neural network was developed for cold lesion detection and localization in single photon emission computed tomography (SPECT) images. METHODS. The network was trained for several noise levels and lesion sizes to identify lesions located in the center of small image neighborhoods. When scrolled across an image the trained network was able to identify cold abnormalities. The diagnostic performance of the technique was evaluated at two noise levels (50,000 and 100,000 counts/slice) and for two lesion sizes (radius: 1.0 cm and 1.5 cm) using the free-response operating characteristic (FROC) analysis. Furthermore, the same network was tested on a situation it was not trained on (80,000 counts/slice and a different reconstruction filter). RESULTS. The neural network showed high sensitivity and small false-positive rates per image for all test situations. These results suggest that neural networks are promising tools for computer-aided clinical diagnosis in SPECT.
AB - RATIONALE AND OBJECTIVES. An artificial neural network was developed for cold lesion detection and localization in single photon emission computed tomography (SPECT) images. METHODS. The network was trained for several noise levels and lesion sizes to identify lesions located in the center of small image neighborhoods. When scrolled across an image the trained network was able to identify cold abnormalities. The diagnostic performance of the technique was evaluated at two noise levels (50,000 and 100,000 counts/slice) and for two lesion sizes (radius: 1.0 cm and 1.5 cm) using the free-response operating characteristic (FROC) analysis. Furthermore, the same network was tested on a situation it was not trained on (80,000 counts/slice and a different reconstruction filter). RESULTS. The neural network showed high sensitivity and small false-positive rates per image for all test situations. These results suggest that neural networks are promising tools for computer-aided clinical diagnosis in SPECT.
KW - Artificial neural networks
KW - Computer-aided diagnosis
KW - Lesion detection
KW - Single photon emission computed tomography
UR - http://www.scopus.com/inward/record.url?scp=0027889353&partnerID=8YFLogxK
U2 - 10.1097/00004424-199308000-00002
DO - 10.1097/00004424-199308000-00002
M3 - Article
C2 - 8375998
AN - SCOPUS:0027889353
SN - 0020-9996
VL - 28
SP - 671
EP - 677
JO - Investigative Radiology
JF - Investigative Radiology
IS - 8
ER -