An Overview of Deep Learning Methods for Segmenting Thyroid Ultrasound Images
Jatinder Kumar1, Surya Narayan Panda2, Devi Dayal3
1Jatinder Kumar, Institute of Engineering and Technology, Chitkara University, Punjab, India.
2Surya Narayan Panda, Institute of Engineering and Technology, Chitkara University, Punjab, India.
3Devi Dayal, Department of Paediatrics, Endocrinology and Diabetes Unit, PGIMER, Chandigarh, India.
Manuscript received on 04 November 2023 | Revised Manuscript received on 12 December 2023 | Manuscript Accepted on 15 December 2023 | Manuscript published on 30 December 2023 | PP: 1-7 | Volume-10 Issue-12, December 2023 | Retrieval Number: 100.1/ijaent.A97591213123 | DOI: 10.35940/ijaent.A9759.12101223
Open Access | Editorial and Publishing Policies | Cite | Zenodo | Indexing and Abstracting
© The Authors. Published By: Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: One of the various imaging modalities that is most frequently utilized in clinical practice is ultrasound (US). It is an emerging technology that has certain advantages along with disadvantages such as poor imaging quality and a lot of fluctuation. To aid in US diagnosis and/or to increase the objectivity and accuracy of such evaluation, effective automatic US image assessment techniques must be created from the perspective of image analysis. The most effective machine learning technology, notably in computer vision and general evaluation of images, has since been proven to belong to deep learning. Deep learning also has a huge potential for using US images for many automated activities. This paper quickly presents many well-known deep learning architectures before summarizing and delving into their applications in a number of distinct.
Keywords: Deep Learning, Ultrasound Image, Segmentation, Thyroid Nodule, Deep Learning, Machine Learning
Scope of the Article: Deep Learning