Paper Info
Title
Esophageal Gross Tumor Volume Segmentation Using a 3D Convolutional Neural Network.
Abstract
Accurate gross tumor volume (GTV) segmentation in esophagus CT images is a critical task in computer aided diagnosis (CAD) systems. However, because of the difficulties raised by the contrast similarity between esophageal GTV and its neighboring tissues in CT scans, this problem has been addressed weakly. In this paper, we present a 3D end-to-end method based on a convolutional neural network (CNN) for this purpose. We leverage design elements from DenseNet in a typical U-shape. The proposed architecture consists of a contractile path and an extending path that includes dense blocks for extracting contextual features and retrieves the lost resolution respectively. Using dense blocks leads to deep supervision, feature re-usability, and parameter reduction while aiding the network to be more accurate. The proposed architecture was trained and tested on a dataset containing 553 scans from 49 distinct patients. The proposed network achieved a Dice value of 0.73 +/- 0.20, and a 95% mean surface distance of 3.07 +/- 1.86 mm for 85 test scans. The experimental results indicate the effectiveness of the proposed method for clinical diagnosis and treatment systems.
Year
DOI
Venue
2018
10.1007/978-3-030-00937-3_40
Lecture Notes in Computer Science
Keywords
Field
DocType
Convolutional Neural Network,Gross tumor volume,Esophagus,CT segmentation
Design elements and principles,CAD,Computer vision,Pattern recognition,Computer science,Convolutional neural network,Segmentation,Computer-aided diagnosis,Artificial intelligence,Clinical diagnosis,Gross tumor volume,Parameter reduction
Conference
Volume
ISSN
Citations 
11073
0302-9743
0
PageRank 
References 
Authors
0.34
4
7
Name
Order
Citations
PageRank
Sahar Yousefi1193.11
Hessam Sokooti2613.74
Mohamed S. Elmahdy311.03
Femke P. Peters400.34
Mohammad T. Manzuri Shalmani516518.97
Roel T. Zinkstok600.34
Marius Staring797159.25