Metastatic liver tumour segmentation with a neural network-guided 3D deformable model
dc.contributor.author | Vorontsov, Eugene | |
dc.contributor.author | Tang, An | |
dc.contributor.author | Roy, David | |
dc.contributor.author | Pal, Christopher | |
dc.contributor.author | Kadoury, Samuel | |
dc.date.accessioned | 2023-10-04T13:18:27Z | |
dc.date.available | NO_RESTRICTION | fr |
dc.date.available | 2023-10-04T13:18:27Z | |
dc.date.issued | 2016-04-22 | |
dc.identifier.uri | http://hdl.handle.net/1866/31894 | |
dc.publisher | Springer | fr |
dc.subject | Liver cancer | fr |
dc.subject | Tumour segmentation | fr |
dc.subject | CT imaging | fr |
dc.subject | Multilayer perceptron | fr |
dc.subject | Deformable surface model | fr |
dc.title | Metastatic liver tumour segmentation with a neural network-guided 3D deformable model | fr |
dc.type | Article | fr |
dc.contributor.affiliation | Université de Montréal. Faculté de médecine. Département de radiologie, radio-oncologie et médecine nucléaire | fr |
dc.identifier.doi | 10.1007/s11517-016-1495-8 | |
dcterms.abstract | The segmentation of liver tumours in CT images is useful for the diagnosis and treatment of liver cancer. Furthermore, an accurate assessment of tumour volume aids in the diagnosis and evaluation of treatment response. Currently, segmentation is performed manually by an expert, and because of the time required, a rough estimate of tumour volume is often done instead. We propose a semi-automatic segmentation method that makes use of machine learning within a deformable surface model. Specifically, we propose a deformable model that uses a voxel classifier based on a multilayer perceptron (MLP) to interpret the CT image. The new deformable model considers vertex displacement towards apparent tumour boundaries and regularization that promotes surface smoothness. During operation, a user identifies the target tumour and the mesh then automatically delineates the tumour from the MLP processed image. The method was tested on a dataset of 40 abdominal CT scans with a total of 95 colorectal metastases collected from a variety of scanners with variable spatial resolution. The segmentation results are encouraging with a Dice similarity metric of 0.80±0.11 and demonstrates that the proposed method can deal with highly variable data. This work motivates further research into tumour segmentation using machine learning with more data and deeper neural networks. | fr |
dcterms.isPartOf | urn:ISSN:0140-0118 | fr |
dcterms.isPartOf | urn:ISSN:1741-0444 | fr |
dcterms.language | eng | fr |
UdeM.ReferenceFournieParDeposant | "Vorontsov, E., Tang, A., Roy, D., Pal, C. J., & Kadoury, S. (2017). Metastatic liver tumour segmentation with a neural network-guided 3D deformable model. Medical & biological engineering & computing, 55(1), 127–139. https://doi.org/10.1007/s11517-016-1495-8 " | fr |
UdeM.VersionRioxx | Version acceptée / Accepted Manuscript | fr |
oaire.citationTitle | Medical and biological engineering and computing | fr |
oaire.citationVolume | 55 | fr |
oaire.citationIssue | 1 | fr |
oaire.citationStartPage | 127 | fr |
oaire.citationEndPage | 139 | fr |
Files in this item
This item appears in the following Collection(s)
This document disseminated on Papyrus is the exclusive property of the copyright holders and is protected by the Copyright Act (R.S.C. 1985, c. C-42). It may be used for fair dealing and non-commercial purposes, for private study or research, criticism and review as provided by law. For any other use, written authorization from the copyright holders is required.