DeepCenterline: a Multi-task Fully Convolutional Network for Centerline Extraction

  title={DeepCenterline: a Multi-task Fully Convolutional Network for Centerline Extraction},
  author={Zhihui Guo and Junjie Bai and Yi Lu and Xin Wang and Kunlin Cao and Qi Song and Milan Sonka and Youbing Yin},
A novel centerline extraction framework is reported which combines an end-to-end trainable multi-task fully convolutional network (FCN) with a minimal path extractor. [] Key Method The method generates single-pixel-wide centerlines with no spurious branches. It handles arbitrary tree-structured object with no prior assumption regarding depth of the tree or its bifurcation pattern. It is also robust to substantial scale changes across different parts of the target object and minor imperfections of the object…

Learning tree-structured representation for 3D coronary artery segmentation

Coronary Centerline Extraction from CCTA Using 3D-UNet

This paper has obtained promising results for accuracy and overlap with various network training configurations on the data from the Rotterdam Coronary Artery Centerline Extraction benchmark and demonstrated the ability of the proposed network to learn despite the huge class imbalance and sparse annotation present in the training data.

Ordered multi-path propagation for vessel centerline extraction

An iterative multi-path search framework for automatic vessel centerline extraction is proposed that has a high F1 score of 87.8% ± 2.7% for the angiography images and achieves accurate and continuous results of vesselcenterline extraction.

CenterlineNet: Automatic Coronary Artery Centerline Extraction for Computed Tomographic Angiographic Images Using Convolutional Neural Network Architectures

A novel method for the automatic extraction of coronary artery centerlines in Computed Tomography Angiography (CTA) data based on a 3D convolutional neural network used as a local vessel centerline detector to extract the main and side branches of the coronary artery tree.

Enforcing connectivity of 3D linear structures using their 2D projections

This paper proposes to improve the 3D connectivity of their results by minimizing a sum of topology-aware losses on their 2D projections to increase the accuracy and to reduce the annotation required to provide the required annotated training data.

Deep Learning for Cardiac Image Segmentation: A Review

A review of over 100 cardiac image segmentation papers using deep learning, which covers common imaging modalities including magnetic resonance imaging, computed tomography, and ultrasound and major anatomical structures of interest.

Automatic Cerebral Artery System Labeling Using Registration and Key Points Tracking

An automatic pipeline that can identify the main arteries, dissect them into segments, and generate their straightened lumen is proposed that is robust to all kinds of brain/neck scanning protocols and most topological variations of the artery system.

A Review of Deep Learning in Medical Imaging: Imaging Traits, Technology Trends, Case Studies With Progress Highlights, and Future Promises

This survey article presents traits of medical imaging, highlights both clinical needs and technical challenges in medical Imaging, and describes how emerging trends in DL are addressing these issues, including the topics of network architecture, sparse and noisy labels, federating learning, interpretability, uncertainty quantification, and so on.

Calcium Scoring at Coronary CT Angiography Using Deep Learning.

A deep learning automatic calcium scoring method accurately quantified coronary artery calcium from CT angiography images and categorized risk.



Coronary Centerline Extraction via Optimal Flow Paths and CNN Path Pruning

The robustness and stability of the method are enhanced by using a model-based detection of coronary specific territories and main branches to constrain the search space and a convolutional neural network classifier for removing extraneous paths in the detected centerlines.

Progressive Attention Guided Recurrent Network for Salient Object Detection

A novel attention guided network which selectively integrates multi-level contextual information in a progressive manner and introduces multi-path recurrent feedback to enhance this proposed progressive attention driven framework.

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.

Robust and Accurate Coronary Artery Centerline Extraction in CTA by Combining Model-Driven and Data-Driven Approaches

The automatically segmented chambers are exploited to predict the initial position of the major coronary centerlines and define a vessel-specific region-of-interest (ROI) to constrain the following centerline refinement.

Globally-Optimal Anatomical Tree Extraction from 3D Medical Images Using Pictorial Structures and Minimal Paths

This work proposes an automatic tree extraction method that leverages prior knowledge of tree topology and geometry and ensures globally-optimal solutions and demonstrates the advantages of incorporating tree statistics and global optimization for this task.

Coronary centerline extraction from CT coronary angiography images using a minimum cost path approach.

The presented results show that minimum cost path approaches can effectively be applied as a preprocessing step for subsequent analysis in clinical practice and biomedical research.

Comprehensive Modeling and Visualization of Cardiac Anatomy and Physiology from CT Imaging and Computer Simulations

  • G. XiongPeng Sun J. Min
  • Medicine, Biology
    IEEE Transactions on Visualization and Computer Graphics
  • 2017
A new computer-aided diagnosis framework is introduced, which allows for comprehensive modeling and visualization of cardiac anatomy and physiology from CT imaging data and computer simulations, with a primary focus on ischemic heart disease.