Intelligent Diagnosis of Thyroid Ultrasound Imaging Using an Ensemble of Deep Learning Methods

Medicina

AliceElena Ghenea¹  AncaMarilena Ungureanu¹  Mihaela Popescu²  DragoşOvidiu Alexandru³  Gabriel Gruionu⁴  Cristian Gheonea⁵  CarmenElena Niculescu⁵  AndreiIoan Drocaş⁶  AndreeaValentina Iacob⁷  Ștefan Udriștoiu⁷  AncaLoredana Udriștoiu⁷  LucianGheorghe Gruionu⁸  CorinaMaria Vasile⁹ 

[1] Department of Bacteriology-Virology-Parasitology, University of Medicine and Pharmacy of Craiova, 200349 Craiova, Romania;Department of Endocrinology, University of Medicine and Pharmacy of Craiova, 200349 Craiova, Romania;Department of Medical Informatics and Biostatistics, University of Medicine and Pharmacy of Craiova, 200349 Craiova, Romania;Department of Medicine, Indiana University School of Medicine, Indianapolis, IN 46202, USA;Department of Pediatrics, University of Medicine and Pharmacy of Craiova, 200349 Craiova, Romania;Department of Urology, University of Medicine and Pharmacy of Craiova, 200349 Craiova, Romania;Faculty of Automation, Computers and Electronics, University of Craiova, 200776 Craiova, Romania;Faculty of Mechanics, University of Craiova, 200512 Craiova, Romania;PhD School Department, University of Medicine and Pharmacy of Craiova, 200349 Craiova, Romania;

关键词: thyroid disorders;    ultrasound image;    deep learning;    neural networks;   

DOI  :  10.3390/medicina57040395

来源: DOAJ

【 摘 要 】

Background and Objectives: At present, thyroid disorders have a great incidence in the worldwide population, so the development of alternative methods for improving the diagnosis process is necessary. Materials and Methods: For this purpose, we developed an ensemble method that fused two deep learning models, one based on convolutional neural network and the other based on transfer learning. For the first model, called 5-CNN, we developed an efficient end-to-end trained model with five convolutional layers, while for the second model, the pre-trained VGG-19 architecture was repurposed, optimized and trained. We trained and validated our models using a dataset of ultrasound images consisting of four types of thyroidal images: autoimmune, nodular, micro-nodular, and normal. Results: Excellent results were obtained by the ensemble CNN-VGG method, which outperformed the 5-CNN and VGG-19 models: 97.35% for the overall test accuracy with an overall specificity of 98.43%, sensitivity of 95.75%, positive and negative predictive value of 95.41%, and 98.05%. The micro average areas under each receiver operating characteristic curves was 0.96. The results were also validated by two physicians: an endocrinologist and a pediatrician. Conclusions: We proposed a new deep learning study for classifying ultrasound thyroidal images to assist physicians in the diagnosis process.

【 授权许可】

Unknown