Title:	Coordinate-Unet 3D for segmentation of lung parenchyma
Authors:	Van Linh, Le Saut, Olivier
Citation:	WSCG 2023: full papers proceedings: 1. International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision, p. 36-42.
Issue Date:	2023
Publisher:	Václav Skala - UNION Agency
Document type:	konferenční příspěvek conferenceObject
URI:	http://hdl.handle.net/11025/54397
ISBN:	978-80-86943-32-9
ISSN:	2464–4617 (print) 2464–4625 (CD/DVD)
Keywords:	segmentace plic;NSCLC;nemalobuněčný karcinom plic;koordinace;hluboké učení
Keywords in different language:	lung segmentation;NSCLC;Non-Small Cell Lung Cancer;coordinate convolutional;deep learning
Abstract in different language:	Lung segmentation is an initial step to provide accurate lung parenchyma in many studies on lung diseases based on analyzing the Computed Tomography (CT) scan, especially in Non-Small Cell Lung Cancer (NSCLC) detec tion. In this work, Coordinate-UNet 3D, a model inspired by UNet, is proposed to improve the accuracy of lung segmentation in the CT scan. Like UNet, the proposed model consists of a contracting/encoder path to extract the high-level information and an expansive/decoder path to recover the features to provide the segmentation. However, we have considered modifying the structure inside each level of the model and using the Coordinate Convolutional layer as the final layer to provide the segmentation. This network was trained end-to-end by using a small set of CT scans of NSCLC patients. The experimental results show the proposed network can provide a highly accurate segmentation for the validation set with a Dice Coefficient index of 0.991, an F1 score of 0.976, and a Jaccard index (IOU) of 0.9535.
Rights:	© Václav Skala - UNION Agency
Appears in Collections:	WSCG 2023: Full Papers Proceedings

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.