Improving automated multiple sclerosis lesion segmentation with a cascaded 3D convolutional neural network approach
In this paper, we present a novel automated method for White Matter (WM) lesion segmentation of Multiple Sclerosis (MS) patient images. Our approach is based on a cascade of two 3D patch-wise convolutional neural networks (CNN). The first network is trained to be more sensitive revealing possible ca...
| Autores: | ; ; ; ; ; ; ; ; ; |
|---|---|
| Tipo de documento: | Artículo |
| Estado: | Published version |
| Fecha de publicación: | 2017 |
| País: | España |
| Institución: | Varias* (Consorci de Biblioteques Universitáries de Catalunya, Centre de Serveis Científics i Acadèmics de Catalunya) |
| Repositorio: | Recercat. Dipósit de la Recerca de Catalunya |
| OAI Identifier: | oai:recercat.cat:10256/14477 |
| Acceso en línea: | http://hdl.handle.net/10256/14477 |
| Nivel de acceso: | Acceso con embargo |
| Palabra clave: | Esclerosi múltiple Multiple sclerosis Imatge -- Segmentació Imaging segmentation Imatges -- Processament -- Tècniques digitals Image processing -- Digital techniques Imatges -- Processament Image processing Imatgeria tridimensional Three-dimensional imaging |
| _version_ | 1878735559898169344 |
|---|---|
| author | Valverde Valverde, Sergi |
| author2 | Cabezas Grebol, Mariano Roura Perez, Eloy González Villà, Sandra Pareto, Deborah Vilanova, Joan Carles Ramió i Torrentà, Lluís Rovira, Àlex Oliver i Malagelada, Arnau Lladó Bardera, Xavier |
| author2_role | author author author author author author author author author |
| author_browse | Cabezas Grebol, Mariano González Villà, Sandra Lladó Bardera, Xavier Oliver i Malagelada, Arnau Pareto, Deborah Ramió i Torrentà, Lluís Roura Perez, Eloy Rovira, Àlex Valverde Valverde, Sergi Vilanova, Joan Carles |
| author_facet | Valverde Valverde, Sergi Cabezas Grebol, Mariano Roura Perez, Eloy González Villà, Sandra Pareto, Deborah Vilanova, Joan Carles Ramió i Torrentà, Lluís Rovira, Àlex Oliver i Malagelada, Arnau Lladó Bardera, Xavier |
| author_role | author |
| collection | Recercat. Dipósit de la Recerca de Catalunya |
| description | In this paper, we present a novel automated method for White Matter (WM) lesion segmentation of Multiple Sclerosis (MS) patient images. Our approach is based on a cascade of two 3D patch-wise convolutional neural networks (CNN). The first network is trained to be more sensitive revealing possible candidate lesion voxels while the second network is trained to reduce the number of misclassified voxels coming from the first network. This cascaded CNN architecture tends to learn well from a small (n≤35) set of labeled data of the same MRI contrast, which can be very interesting in practice, given the difficulty to obtain manual label annotations and the large amount of available unlabeled Magnetic Resonance Imaging (MRI) data. We evaluate the accuracy of the proposed method on the public MS lesion segmentation challenge MICCAI2008 dataset, comparing it with respect to other state-of-the-art MS lesion segmentation tools. Furthermore, the proposed method is also evaluated on two private MS clinical datasets, where the performance of our method is also compared with different recent public available state-of-the-art MS lesion segmentation methods. At the time of writing this paper, our method is the best ranked approach on the MICCAI2008 challenge, outperforming the rest of 60 participant methods when using all the available input modalities (T1-w, T2-w and FLAIR), while still in the top-rank (3rd position) when using only T1-w and FLAIR modalities. On clinical MS data, our approach exhibits a significant increase in the accuracy segmenting of WM lesions when compared with the rest of evaluated methods, highly correlating (r≥0.97) also with the expected lesion volume |
| eu_rights_str_mv | embargoedAccess |
| format | article |
| id | ES_7f2235aebc72cc0e5b794b66b7ab7004 |
| institution | Varias* (Consorci de Biblioteques Universitáries de Catalunya, Centre de Serveis Científics i Acadèmics de Catalunya) |
| instname_str | Varias* (Consorci de Biblioteques Universitáries de Catalunya, Centre de Serveis Científics i Acadèmics de Catalunya) |
| network_acronym_str | ES |
| network_name_str | España |
| oai_identifier_str | oai:recercat.cat:10256/14477 |
| publishDate | 2017 |
| publishDateSort | 2017 |
| publisher | Elsevier |
| publisherStr | Elsevier |
| reponame_str | Recercat. Dipósit de la Recerca de Catalunya |
| spelling | Improving automated multiple sclerosis lesion segmentation with a cascaded 3D convolutional neural network approach Valverde Valverde, Sergi Cabezas Grebol, Mariano Roura Perez, Eloy González Villà, Sandra Pareto, Deborah Vilanova, Joan Carles Ramió i Torrentà, Lluís Rovira, Àlex Oliver i Malagelada, Arnau Lladó Bardera, Xavier Esclerosi múltiple Multiple sclerosis Imatge -- Segmentació Imaging segmentation Imatges -- Processament -- Tècniques digitals Image processing -- Digital techniques Imatges -- Processament Image processing Imatgeria tridimensional Three-dimensional imaging In this paper, we present a novel automated method for White Matter (WM) lesion segmentation of Multiple Sclerosis (MS) patient images. Our approach is based on a cascade of two 3D patch-wise convolutional neural networks (CNN). The first network is trained to be more sensitive revealing possible candidate lesion voxels while the second network is trained to reduce the number of misclassified voxels coming from the first network. This cascaded CNN architecture tends to learn well from a small (n≤35) set of labeled data of the same MRI contrast, which can be very interesting in practice, given the difficulty to obtain manual label annotations and the large amount of available unlabeled Magnetic Resonance Imaging (MRI) data. We evaluate the accuracy of the proposed method on the public MS lesion segmentation challenge MICCAI2008 dataset, comparing it with respect to other state-of-the-art MS lesion segmentation tools. Furthermore, the proposed method is also evaluated on two private MS clinical datasets, where the performance of our method is also compared with different recent public available state-of-the-art MS lesion segmentation methods. At the time of writing this paper, our method is the best ranked approach on the MICCAI2008 challenge, outperforming the rest of 60 participant methods when using all the available input modalities (T1-w, T2-w and FLAIR), while still in the top-rank (3rd position) when using only T1-w and FLAIR modalities. On clinical MS data, our approach exhibits a significant increase in the accuracy segmenting of WM lesions when compared with the rest of evaluated methods, highly correlating (r≥0.97) also with the expected lesion volume This work has been partially supported by “La Fundació la Marató de TV3”, by Retos de InvestigaciónTIN2014-55710-R, and by the MPC UdG 2016/022 grant Elsevier http://hdl.handle.net/10256/14477 |
| spellingShingle | Improving automated multiple sclerosis lesion segmentation with a cascaded 3D convolutional neural network approach Valverde Valverde, Sergi Esclerosi múltiple Multiple sclerosis Imatge -- Segmentació Imaging segmentation Imatges -- Processament -- Tècniques digitals Image processing -- Digital techniques Imatges -- Processament Image processing Imatgeria tridimensional Three-dimensional imaging |
| status_str | publishedVersion |
| title | Improving automated multiple sclerosis lesion segmentation with a cascaded 3D convolutional neural network approach |
| title_full | Improving automated multiple sclerosis lesion segmentation with a cascaded 3D convolutional neural network approach |
| title_fullStr | Improving automated multiple sclerosis lesion segmentation with a cascaded 3D convolutional neural network approach |
| title_full_unstemmed | Improving automated multiple sclerosis lesion segmentation with a cascaded 3D convolutional neural network approach |
| title_short | Improving automated multiple sclerosis lesion segmentation with a cascaded 3D convolutional neural network approach |
| title_sort | Improving automated multiple sclerosis lesion segmentation with a cascaded 3D convolutional neural network approach |
| topic | Esclerosi múltiple Multiple sclerosis Imatge -- Segmentació Imaging segmentation Imatges -- Processament -- Tècniques digitals Image processing -- Digital techniques Imatges -- Processament Image processing Imatgeria tridimensional Three-dimensional imaging |
| topic_facet | Esclerosi múltiple Multiple sclerosis Imatge -- Segmentació Imaging segmentation Imatges -- Processament -- Tècniques digitals Image processing -- Digital techniques Imatges -- Processament Image processing Imatgeria tridimensional Three-dimensional imaging |
| url | http://hdl.handle.net/10256/14477 |