An Automated Detection and Segmentation of Thyroid Nodules using Res-UNet

Recently, some countries have been distressing with the increasing number of thyroid cancer cases. The number of cases is increased every year. Practically, one of the causes of the increase in the number of patients was due to manual examination. Recently, some researchers have involved in the development of CAD to solve this problem. However, CAD itself still has some limitations. One of the major limitations is that the nodules segmentation process was not well-conducted. Thus, to overcome that problem, we proposed a scheme for detecting and segmenting the thyroid nodules. Our scheme consisted of four major steps which were data augmentation process, normalization process, segmentation and evaluation process. The proposed scheme was tested in 480 thyroid ultrasound images. The proposed scheme successfully achieved more than 90% in all evaluation metrics in both detection and segmentation process. According to this achievement, we concluded that our proposed method had potential to be integrated as part of the intelligent system for detecting and segmenting thyroid cancer.

Automated summary

Researchers proposed a new scheme for detecting and segmenting thyroid nodules, which achieved over 90% success rate in testing. The proposed scheme has the potential to be integrated as part of an intelligent system for detecting and segmenting thyroid cancer.