AnatomyNet: Deep Learning for Fast and Fully Automated Whole-volume
Segmentation of Head and Neck Anatomy
release_y3tzjc6t2rglnlr7lrodfwggqm
by
Wentao Zhu, Yufang Huang, Liang Zeng, Xuming Chen, Yong Liu, Zhen
Qian, Nan Du, Wei Fan, Xiaohui Xie
2018
Abstract
Methods: Our deep learning model, called AnatomyNet, segments OARs from head
and neck CT images in an end-to-end fashion, receiving whole-volume HaN CT
images as input and generating masks of all OARs of interest in one shot.
AnatomyNet is built upon the popular 3D U-net architecture, but extends it in
three important ways: 1) a new encoding scheme to allow auto-segmentation on
whole-volume CT images instead of local patches or subsets of slices, 2)
incorporating 3D squeeze-and-excitation residual blocks in encoding layers for
better feature representation, and 3) a new loss function combining Dice scores
and focal loss to facilitate the training of the neural model. These features
are designed to address two main challenges in deep-learning-based HaN
segmentation: a) segmenting small anatomies (i.e., optic chiasm and optic
nerves) occupying only a few slices, and b) training with inconsistent data
annotations with missing ground truth for some anatomical structures.
Results: We collected 261 HaN CT images to train AnatomyNet, and used MICCAI
Head and Neck Auto Segmentation Challenge 2015 as a benchmark dataset to
evaluate the performance of AnatomyNet. The objective is to segment nine
anatomies: brain stem, chiasm, mandible, optic nerve left, optic nerve right,
parotid gland left, parotid gland right, submandibular gland left, and
submandibular gland right. Compared to previous state-of-the-art results from
the MICCAI 2015 competition, AnatomyNet increases Dice similarity coefficient
by 3.3% on average. AnatomyNet takes about 0.12 seconds to fully segment a head
and neck CT image of dimension 178 x 302 x 225, significantly faster than
previous methods. In addition, the model is able to process whole-volume CT
images and delineate all OARs in one pass, requiring little pre- or
post-processing.
https://github.com/wentaozhu/AnatomyNet-for-anatomical-segmentation.git.
In text/plain
format
Archived Files and Locations
application/pdf 1.6 MB
file_gmk2wzxmo5bnxa3ihbmpfh3kxu
|
arxiv.org (repository) web.archive.org (webarchive) |
1808.05238v2
access all versions, variants, and formats of this works (eg, pre-prints)