Computer-Aided Diagnosis for the Differentiation of Malignant from Benign Thyroid Nodules on Ultrasonography1
Received 3 August 2007; accepted 25 December 2008.
Rationale and Objectives
We sought to evaluate the diagnostic performance of an artificial neural network (ANN) and binary logistic regression (BLR) in differentiating malignant from benign thyroid nodules on ultrasonography.
Materials and Methods
Two experienced radiologists, who were unaware of the histopathological diagnosis, analyzed ultrasonographic (US) features of 109 pathologically proven thyroid lesions (49 malignant and 60 benign) in 96 patients. Each radiologist was asked to evaluate US findings and categorize nodules into one of the two groups (malignant vs. benign) in each case. The following 8 US parameters were assessed for each nodule: size, shape, margin, echogenicity, cystic change, microcalcification, macrocalcification, and halo sign. Statistically significant US findings were obtained with backward stepwise logistic regression and were used for training and testing of the ANN and the BLR. The performance of the ANN and BLR was compared to that of the radiologists using receiver-operating characteristic (ROC) analysis.
Results
Statistically significant US findings were size, margin, echogenicity, cystic change, and macrocalcification of the nodules. The area under the ROC curve (Az) values of ANN and BLR were 0.9492 ± 0.0195 and 0.9046 ± 0.0289, respectively. The Az value was 0.8300 ± 0.0359 for reader 1 and 0.7600 ± 0.0409 for reader 2. The Az values for ANN and BLR were significantly higher than those for both radiologists (all p < .05).
Conclusion
The performance of the ANN and the BLR was better than that of the radiologists in the distinction of benign and malignant thyroid nodules.
aDepartment of Radiology, College of Medicine, Hallym University, Kangdong Sacred Heart Hospital, Kil-1 dong, Kangdong-gu, Seoul 134-701, Korea
bDepartment of Biomedical Engineering Branch, Division of Basic and Applied Science, National Cancer Center, Geongi-do, Korea
cDepartment of Radiology, Kangwon National University College of Medicine, Kangwon-do, Korea
dDepartment of Radiology, College of Medicine, University of Ulsan, Asan Medical Center, Seoul, Korea.
Address correspondence to: C.S.C.
1 Dr. Lim's current address is Department of Radiology, University of Ulsan College of Medicine, Asan Medical Center, 388-1 Pungnap-2 dong, Songpa-gu, Seoul 138-736, Korea.
ABSTRACT