Paper Info
Title
Dense volumetric detection and segmentation of mediastinal lymph nodes in chest CT images.
Abstract
We propose a novel mediastinal lymph node detection and segmentation method from chest CT volumes based on fully convolutional networks (FCNs). Most lymph node detection methods are based on filters for blob-like structures, which are not specific for lymph nodes. The 3D U-Net is a recent example of the state-of-the-art 3D FCNs. The 3D U-Net can be trained to learn appearances of lymph nodes in order to output lymph node likelihood maps on input CT volumes. However, it is prone to oversegmentation of each lymph node due to the strong data imbalance between lymph nodes and the remaining part of the CT volumes. To moderate the balance of sizes between the target classes, we train the 3D U-Net using not only lymph node annotations but also other anatomical structures (lungs, airways, aortic arches, and pulmonary arteries) that can be extracted robustly in an automated fashion. We applied the proposed method to 45 cases of contrast-enhanced chest CT volumes. Experimental results showed that 95.5% of lymph nodes were detected with 16.3 false positives per CT volume. The segmentation results showed that the proposed method can prevent oversegmentation, achieving an average Dice score of 52.3% +/- 23.1, compared to the baseline method with 49.2% +/- 23.8, respectively.
Year
DOI
Venue
2018
10.1117/12.2287066
Proceedings of SPIE
Keywords
DocType
Volume
Computer-Aided Diagnosis,Fully convolutional network,Imbalance weighting
Conference
10575
ISSN
Citations 
PageRank 
0277-786X
0
0.34
References 
Authors
0
12
Name
Order
Citations
PageRank
Hirohisa Oda1458.30
Holger R. Roth234.87
Kanwal K. Bhatia3344.13
Masahiro Oda418240.81
Takayuki Kitasaka552067.91
Shingo Iwano6577.54
Hirotoshi Honma7309.77
Hirotsugu Takabatake823529.60
Masaki Mori914417.48
Hiroshi Natori1022028.49
Julia A Schnabel111978151.49
Kensaku Mori121125160.28