3D multi‐scale FCN with random modality voxel dropout learning for Intervertebral Disc Localization and Segmentation from Multi‐modality MR Images
By Xiaomeng Li, Qi-Yan Dou, Hao Chen, Chi-Wing Fu, Xiaojuan Qi, D. Belavy, G. Armbrecht, D. Felsenberg, Guoyan Zheng, P. Heng. 2018
138 citations recorded by the source corpus.
&NA; Intervertebral discs (IVDs) are small joints that lie between adjacent vertebrae. The localization and segmentation of IVDs are important for spine disease diagnosis and measurement quantification. However, manual annotation is time‐consuming and error‐prone with limited reproducibility, particularly for volumetric data. In this work, our goal is to develop an automatic and accurate method based on fully convolutional networks (FCN) for the localization and segmentation of IVDs from multi‐modality 3D MR data. Compared with single modality data, multi‐modality MR images provide complementary contextual information, which contributes to better recognition performance. However, how to effectively integrate such multi‐modality information to generate accurate segmentation results remains to be further explored. In this paper, we present a novel multi‐scale and modality dropout learning framework to locate and segment IVDs from four‐modality MR images. First, we design a 3D multi‐scale context fully convolutional network, which processes the input data in multiple scales of context and then merges the high‐level features to enhance the representation capability of the network for handling the scale variation of anatomical structures. Second, to harness the complementary information from different modalities, we present a random modality voxel dropout strategy which alleviates the co‐adaption issue and increases the discriminative capability of the network. Our method achieved the 1st place in the MICCAI challenge on automatic localization and segmentation of IVDs from multi‐modality MR images, with a mean segmentation Dice coefficient of 91.2% and a mean localization error of 0.62 mm. We further conduct extensive experiments on the extended dataset to validate our method. We demonstrate that the proposed modality dropout strategy with multi‐modality images as contextual information improved the segmentation accuracy significantly. Furthermore, experiments conducted on extended data collected from two different time points demonstrate the efficacy of our method on tracking the morphological changes in a longitudinal study.
Subfields: Biomedical Engineering, Pathology and Forensic Medicine, Surgery
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Biomedical Engineering
In Pathology and Forensic Medicine
In Surgery
Citations in the corpus
- An overview of deep learning in medical imaging focusing on MRI (2018, background): “17 Lately, so-called fully-convolution CNNs have become popular, in which average pooling across the whole input after the final activation layer replaces the fully-connected layers, significantly reducing the total number of weights in the network.”
- H-DenseUNet: Hybrid Densely Connected UNet for Liver and Tumor Segmentation From CT Volumes (2018, unknown): “array of recognition problems [4]–[14].”
- Unpaired Multi-Modal Segmentation via Knowledge Distillation (2020, background): “It has been widely applied for analyzing brain imaging [9], spinal structures [10], prostate cancer [11], and others.”
- 3D Deep Learning on Medical Images: A Review (2020, unknown): “[101] presented fully connected, accurate and automatic 3D deep architecture for the localization and segmentation of IVDs using multimodal MR images.”