A deep learning model integrating FCNNs and CRFs for brain tumor segmentation

By Xiaomei Zhao, Yihong Wu, Guidong Song, Zhenye Li, Yazhuo Zhang, Yong Fan. Medical Image Anal., 2017

724 citations recorded by the source corpus.

HighlightsA deep learning model integrating FCNNs and CRFs for brain tumor segmentation.The integration of FCNNs and CRF‐RNN improves the segmentation robustness.A segmentation model with Flair, T1c, and T2 scans achieves competitive performance. Abstract Accurate and reliable brain tumor segmentation is a critical component in cancer diagnosis, treatment planning, and treatment outcome evaluation. Build upon successful deep learning techniques, a novel brain tumor segmentation method is developed by integrating fully convolutional neural networks (FCNNs) and Conditional Random Fields (CRFs) in a unified framework to obtain segmentation results with appearance and spatial consistency. We train a deep learning based segmentation model using 2D image patches and image slices in following steps: 1) training FCNNs using image patches; 2) training CRFs as Recurrent Neural Networks (CRF‐RNN) using image slices with parameters of FCNNs fixed; and 3) fine‐tuning the FCNNs and the CRF‐RNN using image slices. Particularly, we train 3 segmentation models using 2D image patches and slices obtained in axial, coronal and sagittal views respectively, and combine them to segment brain tumors using a voting based fusion strategy. Our method could segment brain images slice‐by‐slice, much faster than those based on image patches. We have evaluated our method based on imaging data provided by the Multimodal Brain Tumor Image Segmentation Challenge (BRATS) 2013, BRATS 2015 and BRATS 2016. The experimental results have demonstrated that our method could build a segmentation model with Flair, T1c, and T2 scans and achieve competitive performance as those built with Flair, T1, T1c, and T2 scans. Graphical abstract Figure. No Caption available.

Subfields: Computer Vision and Pattern Recognition, Neurology

View Paper: https://www.semanticscholar.org/paper/c01f6960618c9b357832d6d654c6bc2af4c90b84

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Caifeng Shan
2. Zheheng Jiang
3. Hassan Elahi
4. Zhihua Liu
5. Huiyu Zhou
6. Antonello Rizzi
7. Su Ruan
8. Jing Qin

In Neurology

1. Su Ruan
2. Stéphane Canu
3. Tongxue Zhou
4. Yin Dai
5. Yifan Gao

Citations in the corpus

• Application of Deep Learning in Automated Analysis of Molecular Images in Cancer: A Survey (2017, methodology): “[36] BRATS 2013 3D fully CNN + CRF Dice = 0.”
• Deep learning based brain tumor segmentation: a survey (2020, methodology): “Large parameter size by introducing the recurrent level sets to increase the dimension [67] 2D FCNN with CRFRNN CRF as RNN to refine the results.”
• Cancer Diagnosis Using Deep Learning: A Bibliographic Review (2019, methodology): “…removed by using the 3D fully connected random field, after the 3D segmentation of the images using modality of CNN. Zhao et al. combined the multi-modality information from T1, T1C, T2, and fluid-attenuated inversion recovery (FLAIR) images and trained the proposed CNN from this information [82].”
• A review: Deep learning for medical image segmentation using multi-modality fusion (2019, methodology): “Most of the existing multi-modal medical image segmentation networks adopt the input-level fusion strategy, which directly integrates the multi-modal images in the original input space [54] [29] [30] [13] [71] [36] [77] [51] [12].”