Automatic Vertebra Labeling in Large-Scale 3D CT using Deep Image-to-Image Network with Message Passing and Sparsity Regularization

  title={Automatic Vertebra Labeling in Large-Scale 3D CT using Deep Image-to-Image Network with Message Passing and Sparsity Regularization},
  author={Dong Yang and Tao Xiong and Daguang Xu and Qiangui Huang and David Liu and Shaohua Kevin Zhou and Zhoubing Xu and Jin Hyeong Park and Mingqing Chen and Trac D. Tran and Sang Peter Chin and Dimitris N. Metaxas and Dorin Comaniciu},
Automatic localization and labeling of vertebra in 3D medical images plays an important role in many clinical tasks, including pathological diagnosis, surgical planning and postoperative assessment. However, the unusual conditions of pathological cases, such as the abnormal spine curvature, bright visual imaging artifacts caused by metal implants, and the limited field of view, increase the difficulties of accurate localization. In this paper, we propose an automatic and fast algorithm to… 

Automatic Localization and Segmentation of Vertebral Bodies in 3D CT Volumes with Deep Learning

A two-step algorithm to localize and segment just vertebral bodies by taking the advantage of the intensity pattern along the front spinal region, as well as GPU accelerations using convolutional neural networks is developed.

Automatic Segmentation, Localization, and Identification of Vertebrae in 3D CT Images Using Cascaded Convolutional Neural Networks

The proposed method for automatic segmentation, localization, and identification of vertebrae in arbitrary 3D CT images achieved better performance than all existing works in all the three metrics.

Automatic L3 slice detection in 3D CT images using fully-convolutional networks

This paper proposes an efficient method to automatically detect the L3 slice in 3D CT images, and proposes a variant architecture with less parameters allowing 1D confidence map prediction and slightly faster prediction time without loss of accuracy.

Coarse to Fine Vertebrae Localization and Segmentation with SpatialConfiguration-Net and U-Net

A fully automatic coarse to coarse approach for vertebrae localization and segmentation based on fully convolutional CNNs is proposed, ranking first place and winning the MICCAI 2019 Large Scale Vertebrae Segmentation Challenge (VerSe 2019).

Automatic vertebrae localization and segmentation in CT with a two-stage Dense-U-Net

This paper proposed a deep-learning approach for automatic CT vertebrae localization and segmentation with a two-stage Dense-U-Net and implemented instance segmentation of vertebraes in the whole spine.

Automatic Vertebra Localization and Identification in CT by Spine Rectification and Anatomically-constrained Optimization

A robust and accurate method that effectively exploits the anatomical knowledge of the spine to facilitate vertebra localization and identification and outperforms the best competing method on a major public benchmark of 302 highly pathological CT images.

Vertebrae localization, segmentation and identification using a graph optimization and an anatomic consistency cycle

This work introduces an iterative cycle in which individual vertebrae are recursively localized, segmented and identified using deep-nets, while anatomic consistency is enforced using statistical priors, and achieves state-of-the-art results on the VerSe20 challenge benchmark.

Iterative convolutional neural networks for automatic vertebra identification and segmentation in CT images

An automatic method based on iterative convolutional neural networks that utilizes the inherent order of the vertebral column to simplify the detection problem, so that the network can be trained with as little as ten manual reference segmentations.



Vertebrae Localization in Pathological Spine CT via Dense Classification from Sparse Annotations

A robust localization and identification algorithm which builds upon supervised classification forests and avoids an explicit parametric model of appearance is proposed which outperforms state-of-the-art on pathological cases and overcome the tedious requirement for dense annotations by a semi-automatic labeling strategy.

Automatic Localization and Identification of Vertebrae in Spine CT via a Joint Learning Model with Deep Neural Networks

A novel joint learning model with CNN J-CNN that can effectively identify the type of vertebra and eliminate false detections based on a set of coarse vertebral centroids generated from a random forest classifier.

Fast Automatic Vertebrae Detection and Localization in Pathological CT Scans - A Deep Learning Approach

An efficient approach based on deep feed-forward neural networks is used to predict the location of each vertebra using its contextual information in the image and can perform vertebrae detection at a rate of 96% with an overall run time of less than 3 seconds.

3D Deeply Supervised Network for Automatic Liver Segmentation from CT Volumes

A novel 3D deeply supervised network (3D DSN) is presented which takes advantage of a fully convolutional architecture which performs efficient end-to-end learning and inference and introduces a deep supervision mechanism during the learning process to combat potential optimization difficulties.

V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation

This work proposes an approach to 3D image segmentation based on a volumetric, fully convolutional, neural network, trained end-to-end on MRI volumes depicting prostate, and learns to predict segmentation for the whole volume at once.

Dense Volume-to-Volume Vascular Boundary Detection

This work introduces HED-3D, a 3D extension of the state-of-the-art 2D edge detector (HED), and develops a novel 3D-Convolutional Neural Network (CNN) architecture, I2I- 3D, that predicts boundary location in volumetric data.

Automatic Localization and Identification of Vertebrae in Arbitrary Field-of-View CT Scans

A new method for automatic localization and identification of vertebrae in arbitrary field-of-view CT scans based on regression forests and probabilistic graphical models, which is more general than previous work while being computationally efficient.

U-Net: Convolutional Networks for Biomedical Image Segmentation

It is shown that such a network can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks.