Computer Aided Diagnosis System of Thyroid Nodules from Scintigraphic Images

Authors : Aysun SEZER, Emre ALPTEKİN

Pages : 559-567

Doi:10.21205/deufmd.2023257504

View : 48 | Download : 40

Publication Date : 2023-09-27

Article Type : Research Paper

Abstract :In modern medicine, image recognition via segmentation of anatomical regions and automatic classification of diseases using medical images has a growing potential role in diagnosis of various diseases. Scintigraphy of thyroid is one of the established imaging modalities for diagnosis of thyroid gland disorders. In our study, the speckle noise was reduced in the scintigraphy images with the optimized Bayesian nonlocal mean filter. The thyroid gland was automatically segmented by local based active contour method and the thyroid gland pathologies were classified with convolutional neural networks insert ignore into journalissuearticles values(CNN);. The proposed computer aided diagnosis insert ignore into journalissuearticles values(CAD); system was compared with Pyramid of Histograms of Orientation Gradients insert ignore into journalissuearticles values(PHOG);, Gray Level Co occurrence Matrix insert ignore into journalissuearticles values(GLCM);, Local Configuration Pattern insert ignore into journalissuearticles values(LCP); and Bag of Feature insert ignore into journalissuearticles values(BoF); methods. The common pathological patterns of scintigraphic images of the thyroid gland were successfully classified by CNN with an overall success rate of 91.19%. The comparative methods were PHOG, GLCM, LCP and BoF methods which provided overall success rates of 7.61%, 86.04%, 88.91% and 85.72% respectively. The proposed CNN based automatic diagnosis system provided promising results compared to handcrafted methods.
Keywords : Derin öğrenme, görüntü sınıflama, Aktif kontur, gürültü giderme, tiroid nodül, sintigrafi