YOLO-TN: ultrasound diagnosis of thyroid nodules based on transfer learning and convolutional neural networks. (13th July 2022)

• Record Type: Journal Article
• Authors: Wang, Xun; Zhang, Ning; Ding, Mao; Xu, Nuo
• Is Part Of: International journal of adaptive and innovative systems. Volume 3:Number 2(2022)
• Page Start: 87
• Page End: 99
• Publication Date: 2022-07-13
• Subjects: ultrasound images -- thyroid nodules -- benign and malignant diagnosis -- transfer learning -- convolutional neural network; Adaptive computing systems -- Periodicals; Computer systems -- Technological innovations -- Periodicals; Systems software -- Periodicals; 004
• Languages: English
• ISSNs: 1740-2107

Abstract

Thyroid nodules are a common clinical condition. Currently, radiologists commonly use ultrasound as a method of diagnosing them. However, the varying experience of radiologists leads them to describe the features of nodules in the same ultrasound image differently. Incorrect descriptions will lead to misdiagnosis for the patient. To address the problem of difficult diagnosis of benign and malignant thyroid nodules in ultrasound images, we proposed a model for the diagnosis of thyroid nodules, which is named YOLO-TN (thyroid nodules). In this work, we used transfer learning and data augmentation to alleviate the data dependency of the model and designed CSPSE-DarkNet to simulate clinical diagnosis. In addition, we enhanced the detection of small objects and proposed soft ROI selection to enrich the contextual information of thyroid nodules. The model achieved a mAP value of 91.3% on our dataset, providing better performance than some of the popular networks currently available.