Deep Learning Based Classification of Ultrasound Images for Thyroid Nodules: A Large Scale of Pilot Study
Thyroid World Congress ePoster Library. Guan Q. 06/21/19; 272111; 64
Qing Guan
Qing Guan
Login now to access Regular content available to all registered users.

You may also access this content "anytime, anywhere" with the Free MULTILEARNING App for iOS and Android
Abstract
Rate & Comment (0)

Purpose To explore the ability of the deep learning network Inception-v3 to differentiate between papillary thyroid carcinomas (PTCs) and benign nodules in ultrasound images.

Materials and Methods A total of 2836 thyroid ultrasound images from 2235 patients were divided into a training dataset and a test dataset. Inception-v3 was trained and tested to crop the margin of the images of nodules and provide a differential diagnosis. The sizes and sonographic features of nodules were further analysed to identify the factors that may influence diagnostic efficiency. Statistical analyses included χ2 and Fisher’s exact tests and univariate and multivariate analyses.

Results There were 1275 PTCs and 1162 benign nodules in the training group and 209 PTCs and 190 benign nodules in the test group. A margin size of 50 pixels and an input size of 384×384 showed the best outcome after training, and these parameters were selected for the test group. In the test group, the sensitivity and specificity for Inception-v3 were 93.3% (195/209) and 87.4% (166/190), respectively. Inception-v3 displayed the highest accuracy for 0.5-1.0 cm nodules. The accuracy differed according to the margin description (P=.024). Taller nodules were more accurately diagnosed than were wider nodules (P=.015). Microcalcification (odds ratio (OR)=0.254, 95% confidence interval (CI) 0.076-0.847, P=.026) and taller shape (OR=0.243, 95% CI 0.073-0.810, P=.021) were negatively associated with misdiagnosis rate.

Conclusion Inception-v3 can achieve an excellent diagnostic efficiency. Nodules that are 0.5-1.0 cm in size and have microcalcification and a taller shape can be more accurately diagnosed by Inception-v3.

 


Purpose To explore the ability of the deep learning network Inception-v3 to differentiate between papillary thyroid carcinomas (PTCs) and benign nodules in ultrasound images.

Materials and Methods A total of 2836 thyroid ultrasound images from 2235 patients were divided into a training dataset and a test dataset. Inception-v3 was trained and tested to crop the margin of the images of nodules and provide a differential diagnosis. The sizes and sonographic features of nodules were further analysed to identify the factors that may influence diagnostic efficiency. Statistical analyses included χ2 and Fisher’s exact tests and univariate and multivariate analyses.

Results There were 1275 PTCs and 1162 benign nodules in the training group and 209 PTCs and 190 benign nodules in the test group. A margin size of 50 pixels and an input size of 384×384 showed the best outcome after training, and these parameters were selected for the test group. In the test group, the sensitivity and specificity for Inception-v3 were 93.3% (195/209) and 87.4% (166/190), respectively. Inception-v3 displayed the highest accuracy for 0.5-1.0 cm nodules. The accuracy differed according to the margin description (P=.024). Taller nodules were more accurately diagnosed than were wider nodules (P=.015). Microcalcification (odds ratio (OR)=0.254, 95% confidence interval (CI) 0.076-0.847, P=.026) and taller shape (OR=0.243, 95% CI 0.073-0.810, P=.021) were negatively associated with misdiagnosis rate.

Conclusion Inception-v3 can achieve an excellent diagnostic efficiency. Nodules that are 0.5-1.0 cm in size and have microcalcification and a taller shape can be more accurately diagnosed by Inception-v3.

 


    This eLearning portal is powered by:
    This eLearning portal is powered by MULTIEPORTAL
Anonymous User Privacy Preferences

Strictly Necessary Cookies (Always Active)

MULTILEARNING platforms and tools hereinafter referred as “MLG SOFTWARE” are provided to you as pure educational platforms/services requiring cookies to operate. In the case of the MLG SOFTWARE, cookies are essential for the Platform to function properly for the provision of education. If these cookies are disabled, a large subset of the functionality provided by the Platform will either be unavailable or cease to work as expected. The MLG SOFTWARE do not capture non-essential activities such as menu items and listings you click on or pages viewed.


Performance Cookies

Performance cookies are used to analyse how visitors use a website in order to provide a better user experience.


Save Settings