Title :
Lung nodules identification rules extraction with neural fuzzy network
Author :
Lin, Daw-Tung ; Yan, Chong-Ren
Author_Institution :
Dept. of Comput. Sci. & Inf. Eng., Chung-Hua Univ., Hsinchu, Taiwan
Abstract :
In this paper, a neural fuzzy model is proposed to extract the diagnosis rules for detecting the pulmonary nodules. First, series of image processing techniques including thresholding, morphology closing, and labeling to segment the lung area and obtain the ROIs are employed. Then, three main features, circularity, size of area, and mean brightness are extracted from ROIs and the nodules are identified with diagnosis rules that are obtained by the neural fuzzy model. Twenty-nine clinical cases including 583 CT slice images (512 × 512 × 8 bits) are tested in our study. The detection rate of the proposed method is 89.3%, and the false positive is approximately 0.3 per image. This result demonstrates that our method improves the detection rate and reduces false positive compared to other approaches. This also implies potential of this system in clinical practice.
Keywords :
feature extraction; fuzzy neural nets; lung; medical image processing; clinical cases; diagnosis rules; feature extraction; image processing; morphology; neural fuzzy model; pulmonary nodules; Biomedical imaging; Cancer detection; Computed tomography; Data mining; Feature extraction; Flowcharts; Fuzzy neural networks; Image segmentation; Lungs; Neural networks;
Conference_Titel :
Neural Information Processing, 2002. ICONIP '02. Proceedings of the 9th International Conference on
Print_ISBN :
981-04-7524-1
DOI :
10.1109/ICONIP.2002.1199035