Corpus ID: 231639069

A survey on shape-constraint deep learning for medical image segmentation

  title={A survey on shape-constraint deep learning for medical image segmentation},
  author={Simon Bohlender and Ilkay {\"O}ks{\"u}z and A. Mukhopadhyay},
Since the advent of U-Net, fully convolutional deep neural networks and its many variants have completely changed the modern landscape of deep learning based medical image segmentation. However, the over dependence of these methods on pixel level classification and regression has been identified early on as a problem. Especially when trained on medical databases with sparse available annotation, these methods are prone to generate segmentation artifacts such as fragmented structures… Expand

Figures and Tables from this paper

A Surprisingly Effective Perimeter-based Loss for Medical Image Segmentation
A novel loss constraint is proposed that optimizes the perimeter length of the segmented object relative to the ground-truth segmentation and outperforms state-of-the-art boundary losses for both single and multi-organ segmentation. Expand
Anatomy-aided deep learning for medical image segmentation: a review
A review of anatomy-aided DL for medical image segmentation which covers systematically summarized anatomical information categories and corresponding representation methods and presents a categorized methodology overview on using anatomical information with DL from over 70 papers. Expand


Accurate and robust deep learning-based segmentation of the prostate clinical target volume in ultrasound images
This study demonstrates that estimation of model uncertainty and use of prior shape information can significantly improve the performance of CNN-based medical image segmentation methods, especially on difficult images. Expand
A Novel Bayesian Model Incorporating Deep Neural Network and Statistical Shape Model for Pancreas Segmentation
This work proposes a novel Bayesian model incorporating the segmentation results from both deep neural network and statistical shape model for segmentation and reports 85.32 % of the mean DSC that outperforms the state-of-the-art and approximately 12 % improvement from the predicted segment ofDeep neural network. Expand
Superpixel-based deep convolutional neural networks and active contour model for automatic prostate segmentation on 3D MRI scans
An automatic and novel coarse-to-fine segmentation method for prostate 3D MRI scans that combines local texture and spatial information using the Intrinsic Manifold Simple Linear Iterative Clustering algorithm and probabilistic atlas in a deep convolutional neural networks model jointly with the particle swarm optimization algorithm to classify prostate and non-prostate tissues is proposed. Expand
Conditional Random Fields as Recurrent Neural Networks for 3D Medical Imaging Segmentation
This paper developed an implementation of the Conditional Random Field as a Recurrent Neural Network layer which works for any number of spatial dimensions, input/output image channels, and reference image channels and concluded that the performance differences observed were not statistically significant. Expand
Deep Active Contour Network for Medical Image Segmentation
The proposed DACN leverages the advantage of ACM to detect object boundaries accurately, which can be trained in an end-to-end differential manner, and the experimental results on two public datasets demonstrate the effectiveness of DACN. Expand
Automatic Liver Segmentation by Integrating Fully Convolutional Networks into Active Contour Models.
Experimental results for segmenting livers have revealed that the proposed model improves segmentation results in comparison with FCN alone, and is capable of handling image variations from different datasets due to its inherent deformable nature. Expand
Shape Constrained CNN for Cardiac MR Segmentation with Simultaneous Prediction of Shape and Pose Parameters
This paper performs LV and myocardial segmentation by regression of pose and shape parameters derived from a statistical shape model and enforce robustness of shape and pose prediction by simultaneously constructing a segmentation distance map during training. Expand
Study on MRI Medical Image Segmentation Technology Based on CNN-CRF Model
A cascading structure is added under the deep convolutional neural networks (DCNN) framework to more effectively simulate the direct dependencies between spatial closure tags and the conditional random field (CRF) is used for post-segmentation processing, which effectively solves the contradiction between the segmentation accuracy and the network depth and the number of pooling times in the traditional convolutionals. Expand
Deep learning approaches to biomedical image segmentation
In this review, the basics of deep learning methods are discussed along with an overview of successful implementations involving image segmentation for different medical applications and the future need for further improvements is pointed out. Expand
Incorporating prior knowledge in medical image segmentation: a survey
This survey focuses on optimization-based methods that incorporate prior information into their frameworks and reviews and compares these methods in terms of the types of prior employed, the domain of formulation, and the optimization techniques. Expand