Unsupervised Medical Image Segmentation Based on the Local Center of Mass

@article{Aganj2018UnsupervisedMI,
  title={Unsupervised Medical Image Segmentation Based on the Local Center of Mass},
  author={Iman Aganj and Mukesh G. Harisinghani and Ralph Weissleder and Bruce R. Fischl},
  journal={Scientific Reports},
  year={2018},
  volume={8}
}
Image segmentation is a critical step in numerous medical imaging studies, which can be facilitated by automatic computational techniques. Supervised methods, although highly effective, require large training datasets of manually labeled images that are labor-intensive to produce. Unsupervised methods, on the contrary, can be used in the absence of training data to segment new images. We introduce a new approach to unsupervised image segmentation that is based on the computation of the local… 

Figures and Tables from this paper

Automatic segmentation of medical images using a novel Harris Hawk optimization method and an active contour model.
TLDR
A new fully automated method for medical image segmentation is proposed, which utilizes the advantages of thresholding and an active contour model, and can effectively segment the region of interest and produce superior segmentation results for skin and cardiac dataset, as compared to other state-of-the-art algorithms.
Medical Image Segmentation A Review of Recent Techniques, Advancements and a Comprehensive Comparison
TLDR
The important place of image segmentation in decision-making information extraction is projected and deliberating upon current techniques which are used in medical imaging and discussing about various advancements in this research field are discussed.
Multi-Atlas Image Soft Segmentation via Computation of the Expected Label Value
TLDR
This work proposes to consider the probability of all possible atlas-to-image transformations and compute the expected label value (ELV), thereby not relying merely on the transformation deemed “optimal” by the registration method and avoiding the associated computational costs.
Multi-Atlas Image Soft-Segmentation via Computation of the Expected Label Value
TLDR
This work proposes to consider the probability of all possible atlas-to-image transformations and compute the expected label value (ELV), thereby not relying merely on the transformation deemed “optimal” by the registration method and avoiding the associated computational costs.
FOR ATLAS-BASED IMAGE SEGMENTATION
TLDR
This work proposes to consider the probability of all possible transformations and compute the expected label value (ELV), thereby not relying merely on the transformation resulting from the registration, thus avoiding the associated computational costs.
Expected Label Value Computation for Atlas-Based Image Segmentation
  • I. Aganj, B. Fischl
  • Computer Science
    2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019)
  • 2019
TLDR
This work proposes to consider the probability of all possible transformations and compute the expected label value (ELV), thereby not relying merely on the transformation resulting from the registration, thus avoiding the associated computational costs.
TricycleGAN: Unsupervised Image Synthesis and Segmentation Based on Shape Priors
TLDR
A novel network architecture for capable of unsupervised and semi-supervised image segmentation called TricycleGAN is introduced, which uses three generative models to learn translations between medical images and segmentation maps using edge maps as an intermediate step.
Superpixel/voxel medical image segmentation algorithm based on the regional interlinked value
TLDR
This paper proposes a superpixel/voxel medical image segmentation algorithm based on regional interlinked value and block (region) merging, which can segment the two-dimensional bone image and three-dimensional brain image.
Lung Tumor Segmentation by Fusing 2D and 3D Models
TLDR
An automatic lung tumor segmentation model is proposed that is a fusion model from 2D and 3D model with very positive results compared to other methods.
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 15 REFERENCES
Medical Image Segmentation: A Brief Survey
TLDR
Most popular medical image segmentation techniques are overviews and their capabilities, and basic advantages and limitations are discussed.
Multi Modality State-of-the-Art Medical Image Segmentation and Registration Methodologies: Volume II
TLDR
Most popular medical image segmentation techniques are overviews and their capabilities, and basic advantages and limitations are discussed.
Advanced algorithmic approaches to medical image segmentation: state-of-the-art application in cardiology, neurology, mammography and pathology
Medical imaging is generally recognised as key to the success of better diagnosis and patient care and this book, describing state-of-the-art techniques, is a valuable contribution to the literature.
Hybrid image segmentation using watersheds and fast region merging
TLDR
A hybrid multidimensional image segmentation algorithm is proposed, which combines edge and region-based techniques through the morphological algorithm of watersheds and additionally maintains the so-called nearest neighbor graph, due to which the priority queue size and processing time are drastically reduced.
A survey on deep learning in medical image analysis
Interactive Whole-Heart Segmentation in Congenital Heart Disease
TLDR
This work presents an interactive algorithm to segment the heart chambers and epicardial surfaces, including the great vessel walls, in pediatric cardiac MRI of congenital heart disease, and shows that strategies asking the user to manually segment regions of interest within short-axis slices yield higher accuracy with less user input than those querying entire short- axis slices.
Normalized Cuts and Image Segmentation
TLDR
This work treats image segmentation as a graph partitioning problem and proposes a novel global criterion, the normalized cut, for segmenting the graph, which measures both the total dissimilarity between the different groups as well as the total similarity within the groups.
Normalized cuts and image segmentation
  • Jianbo Shi, J. Malik
  • Computer Science
    Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition
  • 1997
TLDR
This work treats image segmentation as a graph partitioning problem and proposes a novel global criterion, the normalized cut, for segmenting the graph, which measures both the total dissimilarity between the different groups as well as the total similarity within the groups.
SLIC Superpixels Compared to State-of-the-Art Superpixel Methods
TLDR
A new superpixel algorithm is introduced, simple linear iterative clustering (SLIC), which adapts a k-means clustering approach to efficiently generate superpixels and is faster and more memory efficient, improves segmentation performance, and is straightforward to extend to supervoxel generation.
...
1
2
...