PURPOSE: To evaluate how much the experience of radiologists affects the performance of an artificial neural network (ANN) trained by two highly experienced radiologists. MATERIALS AND METHODS: Before biopsy two experienced radiologists reviewed the MR images of 100 adult patients with suspicious breast lesions and evaluated their findings based on six features. This database was then used to train a three-layered feed-forward neural network. The network's generalizing ability was then tested to predict the outcome of biopsy in 56 new patients' records which were extracted by 10 participating radiologists. The MRI findings of each reader were presented to the ANN to evaluate the effect of various levels of experience on the output of the ANN. The performance of the ANN was then compared with that of attendant physicians in terms of sensitivity, specificity, and accuracy as well as ROC analysis. RESULTS: The best ANN outcome offered a correct diagnosis in 40 of 41 of the patients with malignant breast cancer and 10 of 15 with benign entity presented in the testing set. The output of the trained ANN outperformed the attendant radiologists with low levels of experience and showed comparable performance with radiologists with higher levels of experience. CONCLUSIONS: The ANN is able to work as a backup system to assist radiologists in the diagnosis of breast cancer.
PURPOSE: To evaluate how much the experience of radiologists affects the performance of an artificial neural network (ANN) trained by two highly experienced radiologists. MATERIALS AND METHODS: Before biopsy two experienced radiologists reviewed the MR images of 100 adult patients with suspicious breast lesions and evaluated their findings based on six features. This database was then used to train a three-layered feed-forward neural network. The network's generalizing ability was then tested to predict the outcome of biopsy in 56 new patients' records which were extracted by 10 participating radiologists. The MRI findings of each reader were presented to the ANN to evaluate the effect of various levels of experience on the output of the ANN. The performance of the ANN was then compared with that of attendant physicians in terms of sensitivity, specificity, and accuracy as well as ROC analysis. RESULTS: The best ANN outcome offered a correct diagnosis in 40 of 41 of the patients with malignant breast cancer and 10 of 15 with benign entity presented in the testing set. The output of the trained ANN outperformed the attendant radiologists with low levels of experience and showed comparable performance with radiologists with higher levels of experience. CONCLUSIONS: The ANN is able to work as a backup system to assist radiologists in the diagnosis of breast cancer.
Authors: J Khan; J S Wei; M Ringnér; L H Saal; M Ladanyi; F Westermann; F Berthold; M Schwab; C R Antonescu; C Peterson; P S Meltzer Journal: Nat Med Date: 2001-06 Impact factor: 53.440
Authors: Roberta Fusco; Mario Sansone; Salvatore Filice; Guglielmo Carone; Daniela Maria Amato; Carlo Sansone; Antonella Petrillo Journal: J Med Biol Eng Date: 2016-08-31 Impact factor: 1.553