A New Graph-Based Method for Automatic Segmentation

Gemme, Laura; Dellepiane, S.

doi:10.1007/978-3-319-23231-7_54

Cited by 6 publications

(11 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In fact, since the proposed method is able to work on singular object volumes, a segmentation [8] process is necessary. Despite the low quality of the images and the presence of noise, this kind of segmentation achieves satisfactory results, with a precise extraction of regions of interest (ROI) from the given volumes.…”

Section: Registration Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Multi-temporal MRI carpal bone volumes analysis by principal axes registration

Ferretti

Dellepiane

2016

SPIE Proceedings

Self Cite

View full text Add to dashboard Cite

In this paper, a principal axes registration technique is presented, with the relevant application to segmented volumes. The purpose of the proposed registration is to compare multi-temporal volumes of carpal bones from Magnetic Resonance Imaging (MRI) acquisitions. Starting from the study of the second-order moment matrix, the eigenvectors are calculated to allow the rotation of volumes with respect to reference axes. Then the volumes are spatially translated to become perfectly overlapped. A quantitative evaluation of the results obtained is carried out by computing classical indices from the confusion matrix, which depict similarity measures between the volumes of the same organ as extracted from MRI acquisitions executed at different moments. Within the medical field, the way a registration can be used to compare multi-temporal images is of great interest, since it provides the physician with a tool which allows a visual monitoring of a disease evolution. The segmentation method used herein is based on the graph theory and is a robust, unsupervised and parameters independent method. Patients affected by rheumatic diseases have been considered

show abstract

Section: Registration Methodsmentioning

confidence: 99%

“…The considered volumes have been acquired with MRI. For the processing of individual bones, a segmentation [8] has been used, followed by the registration of each bone. This method has been tested on various patients with the objective of studying the related follow-up and measuring the progression of the disease.…”

Section: Introductionmentioning

confidence: 99%

Multi-temporal MRI carpal bone volumes analysis by principal axes registration

Ferretti

Dellepiane

2016

SPIE Proceedings

Self Cite

View full text Add to dashboard Cite

show abstract

“…This work, referring to the 3D-segmentation method described in [2], focuses on automatizing and optimizing the graph cut phase. The volume is mapped into a graph, where each voxel corresponds to a vertex and pairs of neighboring vertices represent the edges.…”

Section: Proposed Methodsmentioning

confidence: 99%

“…In order to obtain a precise and accurate segmentation, the cut should occur at the boundary between object and background. Within this context, the energy function is defined as follows [4]: (2) where A is the vector that defines the segmentation, R is the regional term; B is the boundary term and is the relative importance factor between the two previous terms.…”

Section: Graph Cut In Image Segmentationmentioning

confidence: 99%

See 1 more Smart Citation

An Optimal and Automatic Graph Cut Method for Biomedical Images Using Compactness Measure

Nardotto¹,

Gemme²,

Dellepiane³

2017

IJCTE

Self Cite

View full text Add to dashboard Cite

This work aims to achieve an automatic and optimal graph cut phase based on a segmentation method presented in a previous paper. A graph-based segmentation algorithm, starting from a seed point belonging to the region of interest (ROI), is able to find the Minimum Path Spanning Tree (MPST) by using a new cost function and an optimal aggregation criterion. In order to extract the ROI, a graph-cut of the obtained tree is absolutely necessary.By definition, the main drawback of the graph-based segmentation methods is the loss of spatial and contextual information. To overcome this problem, a new method based on compactness measure is here proposedThe present approach is applied to the biomedical field, considering Magnetic Resonance Imaging (MRI) volumes of the hand and neurological districts.

show abstract

Optimizing and Evaluating a Graph-Based Segmentation of MRI Wrist Bones

Nardotto

Ferretti

Gemme

et al. 2015

New Trends in Image Analysis and Processing -- ICIAP 2015 Workshops

View full text Add to dashboard Cite

In this paper, a quantitative evaluation of the graph-based segmentation method presented in a previous work is performed. The algorithm, starting from a single source element belonging to a region of interest, aims at finding the optimal path minimizing a new cost function for all elements of a digital volume. The method is an adaptive, unsupervised, and semi-automatic approach.For the assessment, a training phase and a testing phase are considered. The system is able to learn and adapt to the ground truth. The performance of the method is estimated by computing classical indices from the confusion matrix, similarity measures, and distance measures.Our work is based on the segmentation and 3D reconstructions of carpal bones derived from Magnetic Resonance Imaging (MRI) volumetric data of patients affected by rheumatic diseases.

show abstract

A New Graph-Based Method for Automatic Segmentation

Cited by 6 publications

References 10 publications

Multi-temporal MRI carpal bone volumes analysis by principal axes registration

Multi-temporal MRI carpal bone volumes analysis by principal axes registration

An Optimal and Automatic Graph Cut Method for Biomedical Images Using Compactness Measure

Optimizing and Evaluating a Graph-Based Segmentation of MRI Wrist Bones

Contact Info

Product

Resources

About