1
|
Zhu H, Tang Z, Cheng H, Wu Y, Fan Y. Multi-atlas label fusion with random local binary pattern features: Application to hippocampus segmentation. Sci Rep 2019; 9:16839. [PMID: 31727982 PMCID: PMC6856174 DOI: 10.1038/s41598-019-53387-9] [Citation(s) in RCA: 9] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/18/2018] [Accepted: 10/30/2019] [Indexed: 01/15/2023] Open
Abstract
Automatic and reliable segmentation of the hippocampus from magnetic resonance (MR) brain images is extremely important in a variety of neuroimage studies. To improve the hippocampus segmentation performance, a local binary pattern based feature extraction method is developed for machine learning based multi-atlas hippocampus segmentation. Under the framework of multi-atlas image segmentation (MAIS), a set of selected atlases are registered to images to be segmented using a non-linear image registration algorithm. The registered atlases are then used as training data to build linear regression models for segmenting the images based on the image features, referred to as random local binary pattern (RLBP), extracted using a novel image feature extraction method. The RLBP based MAIS algorithm has been validated for segmenting hippocampus based on a data set of 135 T1 MR images which are from the Alzheimer’s Disease Neuroimaging Initiative database (adni.loni.usc.edu). By using manual segmentation labels produced by experienced tracers as the standard of truth, six segmentation evaluation metrics were used to evaluate the image segmentation results by comparing automatic segmentation results with the manual segmentation labels. We further computed Cohen’s d effect size to investigate the sensitivity of each segmenting method in detecting volumetric differences of the hippocampus between different groups of subjects. The evaluation results showed that our method was competitive to state-of-the-art label fusion methods in terms of accuracy. Hippocampal volumetric analysis showed that the proposed RLBP method performed well in detecting the volumetric differences of the hippocampus between groups of Alzheimer’s disease patients, mild cognitive impairment subjects, and normal controls. These results have demonstrated that the RLBP based multi-atlas image segmentation method could facilitate efficient and accurate extraction of the hippocampus and may help predict Alzheimer’s disease. The codes of the proposed method is available (https://www.nitrc.org/frs/?group_id=1242).
Collapse
Affiliation(s)
- Hancan Zhu
- School of Mathematics Physics and Information, Shaoxing University, Shaoxing, Zhejiang, 312000, China
| | - Zhenyu Tang
- Beijing Advanced Innovation Center for Big Data and Brain Computing, Beihang University, Beijing, 100191, China
| | - Hewei Cheng
- Department of Biomedical Engineering, School of Bioinformatics, Chongqing University of Posts and Telecommunications, Chongqing, 400065, China
| | - Yihong Wu
- National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China
| | - Yong Fan
- Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, 19104, USA.
| |
Collapse
|
2
|
Sanroma G, Benkarim OM, Piella G, Camara O, Wu G, Shen D, Gispert JD, Molinuevo JL, González Ballester MA. Learning non-linear patch embeddings with neural networks for label fusion. Med Image Anal 2018; 44:143-155. [PMID: 29247877 PMCID: PMC5896774 DOI: 10.1016/j.media.2017.11.013] [Citation(s) in RCA: 14] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/21/2017] [Revised: 10/05/2017] [Accepted: 11/27/2017] [Indexed: 12/29/2022]
Abstract
In brain structural segmentation, multi-atlas strategies are increasingly being used over single-atlas strategies because of their ability to fit a wider anatomical variability. Patch-based label fusion (PBLF) is a type of such multi-atlas approaches that labels each target point as a weighted combination of neighboring atlas labels, where atlas points with higher local similarity to the target contribute more strongly to label fusion. PBLF can be potentially improved by increasing the discriminative capabilities of the local image similarity measurements. We propose a framework to compute patch embeddings using neural networks so as to increase discriminative abilities of similarity-based weighted voting in PBLF. As particular cases, our framework includes embeddings with different complexities, namely, a simple scaling, an affine transformation, and non-linear transformations. We compare our method with state-of-the-art alternatives in whole hippocampus and hippocampal subfields segmentation experiments using publicly available datasets. Results show that even the simplest versions of our method outperform standard PBLF, thus evidencing the benefits of discriminative learning. More complex transformation models tended to achieve better results than simpler ones, obtaining a considerable increase in average Dice score compared to standard PBLF.
Collapse
Affiliation(s)
- Gerard Sanroma
- Department of Information and Communication Technologies, Universitat Pompeu Fabra, Tànger 122-140, Barcelona 08018, Spain
| | - Oualid M. Benkarim
- Department of Information and Communication Technologies, Universitat Pompeu Fabra, Tànger 122-140, Barcelona 08018, Spain
| | - Gemma Piella
- Department of Information and Communication Technologies, Universitat Pompeu Fabra, Tànger 122-140, Barcelona 08018, Spain
| | - Oscar Camara
- Department of Information and Communication Technologies, Universitat Pompeu Fabra, Tànger 122-140, Barcelona 08018, Spain
| | - Guorong Wu
- Department of Radiology and BRIC, University of North Carolina at Chapel Hill, 102 Mason Farm Rd., NC 27599, USA
| | - Dinggang Shen
- Department of Radiology and BRIC, University of North Carolina at Chapel Hill, 102 Mason Farm Rd., NC 27599, USA
- Department of Brain and Cognitive Engineering, Korea University, Seoul, Republic of Korea
| | - Juan D. Gispert
- Barcelonaβeta Brain Research Center, Pasqual Maragall Foundation, Wellington 30, Barcelona 08005 Spain
| | - José Luis Molinuevo
- Barcelonaβeta Brain Research Center, Pasqual Maragall Foundation, Wellington 30, Barcelona 08005 Spain
| | - Miguel A. González Ballester
- Department of Information and Communication Technologies, Universitat Pompeu Fabra, Tànger 122-140, Barcelona 08018, Spain
- ICREA, Pg. Lluis Companys 23, Barcelona 08010 Spain
| |
Collapse
|
3
|
Discriminative confidence estimation for probabilistic multi-atlas label fusion. Med Image Anal 2017; 42:274-287. [PMID: 28888171 DOI: 10.1016/j.media.2017.08.008] [Citation(s) in RCA: 6] [Impact Index Per Article: 0.9] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/31/2017] [Revised: 06/26/2017] [Accepted: 08/29/2017] [Indexed: 12/31/2022]
Abstract
Quantitative neuroimaging analyses often rely on the accurate segmentation of anatomical brain structures. In contrast to manual segmentation, automatic methods offer reproducible outputs and provide scalability to study large databases. Among existing approaches, multi-atlas segmentation has recently shown to yield state-of-the-art performance in automatic segmentation of brain images. It consists in propagating the labelmaps from a set of atlases to the anatomy of a target image using image registration, and then fusing these multiple warped labelmaps into a consensus segmentation on the target image. Accurately estimating the contribution of each atlas labelmap to the final segmentation is a critical step for the success of multi-atlas segmentation. Common approaches to label fusion either rely on local patch similarity, probabilistic statistical frameworks or a combination of both. In this work, we propose a probabilistic label fusion framework based on atlas label confidences computed at each voxel of the structure of interest. Maximum likelihood atlas confidences are estimated using a supervised approach, explicitly modeling the relationship between local image appearances and segmentation errors produced by each of the atlases. We evaluate different spatial pooling strategies for modeling local segmentation errors. We also present a novel type of label-dependent appearance features based on atlas labelmaps that are used during confidence estimation to increase the accuracy of our label fusion. Our approach is evaluated on the segmentation of seven subcortical brain structures from the MICCAI 2013 SATA Challenge dataset and the hippocampi from the ADNI dataset. Overall, our results indicate that the proposed label fusion framework achieves superior performance to state-of-the-art approaches in the majority of the evaluated brain structures and shows more robustness to registration errors.
Collapse
|