Open AccessAutomatic detection of thyroid nodules with ultrasound images: Basing on semi-supervised learning
Author(s) -
Qingsong Wang,
Jie Zheng,
Hui Jing Yu,
Jingqi Zhang,
Jie Zhang
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1976/1/012012
Subject(s) - thyroid nodules , artificial intelligence , segmentation , ultrasound , computer science , pattern recognition (psychology) , nodule (geology) , sørensen–dice coefficient , thyroid , radiology , image segmentation , computer vision , medicine , paleontology , biology
Ultrasonography is one of the most common method for the diagnosis of thyroid nodules clinically. But the lack of experienced radiologists has become the biggest problem which reduce the accuracy and effectiveness of thyroid nodules’ detection. What’s more, although artificial intelligence (AI) has been widely used to solve the problem, the performance is limited by the size of the database. In this paper, an improved U-Net is designed for the segmentation of thyroid nodules, following a fully convolution network for the classification of thyroid nodules. During the training, pseudo-label is used for semi-supervised learning. The whole work is trained in 2032 ultrasound images (1000 nodules) and tested in 400 ultrasound images (200 nodules). The average dice coefficient is 89.7% in the test set for segmentation, while the precision and recall is 93.2% and 96% separately for classification. These results are higher than the method which only use the images with true labels, proving the effectiveness of pseudo-label.