Literature DB >> 31686380

Incorporating prior shape knowledge via data-driven loss model to improve 3D liver segmentation in deep CNNs.

Saeed Mohagheghi1, Amir Hossein Foruzan2.   

Abstract

PURPOSE: Convolutional neural networks (CNNs) have obtained enormous success in liver segmentation. However, there are several challenges, including low-contrast images, and large variations in the shape, and appearance of the liver. Incorporating prior knowledge in deep CNN models improves their performance and generalization.
METHODS: A convolutional denoising auto-encoder is utilized to learn global information about 3D liver shapes in a low-dimensional latent space. Then, the deep data-driven knowledge is used to define a loss function and combine it with the Dice loss in the main segmentation model. The resultant hybrid model would be forced to learn the global shape information as prior knowledge, while it tries to produce accurate results and increase the Dice score.
RESULTS: The proposed training strategy improved the performance of the 3D U-Net model and reached the Dice score of 97.62% on the Sliver07-I liver dataset, which is competitive to the state-of-the-art automatic segmentation methods. The proposed algorithm enhanced the generalization and robustness of the hybrid model and outperformed the 3D U-Net model in the prediction of unseen images.
CONCLUSIONS: The results indicate that the incorporation of prior shape knowledge enhances liver segmentation tasks in deep CNN models. The proposed method improves the generalization and robustness of the hybrid model due to the abstract features provided by the data-driven loss model.

Keywords:  3D liver segmentation; Convolutional neural network; Deep learning; Prior knowledge

Mesh:

Year:  2019        PMID: 31686380     DOI: 10.1007/s11548-019-02085-y

Source DB:  PubMed          Journal:  Int J Comput Assist Radiol Surg        ISSN: 1861-6410            Impact factor:   2.924


  12 in total

1.  Automatic liver segmentation based on appearance and context information.

Authors:  Yongchang Zheng; Danni Ai; Jinrong Mu; Weijian Cong; Xuan Wang; Haitao Zhao; Jian Yang
Journal:  Biomed Eng Online       Date:  2017-01-14       Impact factor: 2.819

2.  Liver segmentation from computed tomography scans: a survey and a new algorithm.

Authors:  Paola Campadelli; Elena Casiraghi; Andrea Esposito
Journal:  Artif Intell Med       Date:  2008-12-06       Impact factor: 5.326

3.  DCAN: Deep contour-aware networks for object instance segmentation from histology images.

Authors:  Hao Chen; Xiaojuan Qi; Lequan Yu; Qi Dou; Jing Qin; Pheng-Ann Heng
Journal:  Med Image Anal       Date:  2016-11-16       Impact factor: 8.545

4.  Automatic 3D liver location and segmentation via convolutional neural network and graph cut.

Authors:  Fang Lu; Fa Wu; Peijun Hu; Zhiyi Peng; Dexing Kong
Journal:  Int J Comput Assist Radiol Surg       Date:  2016-09-07       Impact factor: 2.924

5.  SegAN: Adversarial Network with Multi-scale L1 Loss for Medical Image Segmentation.

Authors:  Yuan Xue; Tao Xu; Han Zhang; L Rodney Long; Xiaolei Huang
Journal:  Neuroinformatics       Date:  2018-10

6.  Comparison and evaluation of methods for liver segmentation from CT datasets.

Authors:  Tobias Heimann; Bram van Ginneken; Martin A Styner; Yulia Arzhaeva; Volker Aurich; Christian Bauer; Andreas Beck; Christoph Becker; Reinhard Beichel; György Bekes; Fernando Bello; Gerd Binnig; Horst Bischof; Alexander Bornik; Peter M M Cashman; Ying Chi; Andrés Cordova; Benoit M Dawant; Márta Fidrich; Jacob D Furst; Daisuke Furukawa; Lars Grenacher; Joachim Hornegger; Dagmar Kainmüller; Richard I Kitney; Hidefumi Kobatake; Hans Lamecker; Thomas Lange; Jeongjin Lee; Brian Lennon; Rui Li; Senhu Li; Hans-Peter Meinzer; Gábor Nemeth; Daniela S Raicu; Anne-Mareike Rau; Eva M van Rikxoort; Mikaël Rousson; László Rusko; Kinda A Saddi; Günter Schmidt; Dieter Seghers; Akinobu Shimizu; Pieter Slagmolen; Erich Sorantin; Grzegorz Soza; Ruchaneewan Susomboon; Jonathan M Waite; Andreas Wimmer; Ivo Wolf
Journal:  IEEE Trans Med Imaging       Date:  2009-02-10       Impact factor: 10.048

7.  Segmentation of liver and spleen based on computational anatomy models.

Authors:  Chunhua Dong; Yen-Wei Chen; Amir Hossein Foruzan; Lanfen Lin; Xian-Hua Han; Tomoko Tateyama; Xing Wu; Gang Xu; Huiyan Jiang
Journal:  Comput Biol Med       Date:  2015-10-28       Impact factor: 4.589

8.  Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation.

Authors:  Konstantinos Kamnitsas; Christian Ledig; Virginia F J Newcombe; Joanna P Simpson; Andrew D Kane; David K Menon; Daniel Rueckert; Ben Glocker
Journal:  Med Image Anal       Date:  2016-10-29       Impact factor: 8.545

9.  Metrics for evaluating 3D medical image segmentation: analysis, selection, and tool.

Authors:  Abdel Aziz Taha; Allan Hanbury
Journal:  BMC Med Imaging       Date:  2015-08-12       Impact factor: 1.930

10.  Fully automatic liver segmentation combining multi-dimensional graph cut with shape information in 3D CT images.

Authors:  Xuesong Lu; Qinlan Xie; Yunfei Zha; Defeng Wang
Journal:  Sci Rep       Date:  2018-07-16       Impact factor: 4.379

View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.