nanoll
extt
Contact admin for Full-Text
Please use this identifier to cite or link to this item:
http://lrcdrs.bennett.edu.in:80/handle/123456789/1434| Title: | Advanced Computing |
| Authors: | Garg, Deepak Kumar Gupta, Suneet |
| Keywords: | Computed Tomography (CT) images Convolutional Neural Networks ResU-Net Organ segmentation |
| Issue Date: | Feb-2021 |
| Publisher: | Springer Science and Business Media Deutschland GmbH |
| Citation: | In Deepak Garg et.al (Eds) Advanced Computing: 10th International Conference, IACC 2020, Panaji, Goa, India, December 5–6, 2020, Communications in Computer and Information Science |
| Abstract: | The recent advances in the field of computer vision have led to the wide use of Convolutional Neural Networks (CNNs) in organ segmentation of computed tomography (CT) images. Image-guided radiation therapy requires the accurate segmentation of organs at risk (OARs). In this paper, the proposed model is a 2D ResU-Net network to automatically segment thoracic organs at risk in computed tomography (CT) images. The architecture consists of a downsampling path for capturing features and a symmetric upsampling path for obtaining precise localization. The proposed approach achieves a 0.93 dice metric (DSC) and 0.26 hausdorff distance (HD) after using ImageNet stats for normalizing and using pre-trained weights. © 2021, Springer Nature Singapore Pte Ltd. |
| URI: | https://doi.org/10.1007/978-981-16-0401-0 http://lrcdrs.bennett.edu.in:80/handle/123456789/1434 |
| ISSN: | 1865-0929 |
| Appears in Collections: | Conference Proceedings_ SCSET |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| Advanced Computing.pdf Restricted Access | 81.22 MB | Adobe PDF | View/Open Request a copy |
Contact admin for Full-Text
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.