151
|
Karimaghaloo Z, Arnold DL, Arbel T. Adaptive multi-level conditional random fields for detection and segmentation of small enhanced pathology in medical images. Med Image Anal 2015. [PMID: 26211811 DOI: 10.1016/j.media.2015.06.004] [Citation(s) in RCA: 9] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/28/2022]
Abstract
Detection and segmentation of large structures in an image or within a region of interest have received great attention in the medical image processing domains. However, the problem of small pathology detection and segmentation still remains an unresolved challenge due to the small size of these pathologies, their low contrast and variable position, shape and texture. In many contexts, early detection of these pathologies is critical in diagnosis and assessing the outcome of treatment. In this paper, we propose a probabilistic Adaptive Multi-level Conditional Random Fields (AMCRF) with the incorporation of higher order cliques for detecting and segmenting such pathologies. In the first level of our graphical model, a voxel-based CRF is used to identify candidate lesions. In the second level, in order to further remove falsely detected regions, a new CRF is developed that incorporates higher order textural features, which are invariant to rotation and local intensity distortions. At this level, higher order textures are considered together with the voxel-wise cliques to refine boundaries and is therefore adaptive. The proposed algorithm is tested in the context of detecting enhancing Multiple Sclerosis (MS) lesions in brain MRI, where the problem is further complicated as many of the enhancing voxels are associated with normal structures (i.e. blood vessels) or noise in the MRI. The algorithm is trained and tested on large multi-center clinical trials from Relapsing-Remitting MS patients. The effect of several different parameter learning and inference techniques is further investigated. When tested on 120 cases, the proposed method reaches a lesion detection rate of 90%, with very few false positive lesion counts on average, ranging from 0.17 for very small (3-5 voxels) to 0 for very large (50+ voxels) regions. The proposed model is further tested on a very large clinical trial containing 2770 scans where a high sensitivity of 91% with an average false positive count of 0.5 is achieved. Incorporation of contextual information at different scales is also explored. Finally, superior performance is shown upon comparing with Support Vector Machine (SVM), Random Forest and variant of an MRF.
Collapse
Affiliation(s)
| | | | - Tal Arbel
- Centre for Intelligent Machines, McGill University, Montreal, Canada
| |
Collapse
|
152
|
Tomas-Fernandez X, Warfield SK. A Model of Population and Subject (MOPS) Intensities With Application to Multiple Sclerosis Lesion Segmentation. IEEE TRANSACTIONS ON MEDICAL IMAGING 2015; 34:1349-61. [PMID: 25616008 PMCID: PMC4506921 DOI: 10.1109/tmi.2015.2393853] [Citation(s) in RCA: 33] [Impact Index Per Article: 3.7] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/15/2023]
Abstract
White matter (WM) lesions are thought to play an important role in multiple sclerosis (MS) disease burden. Recent work in the automated segmentation of white matter lesions from magnetic resonance imaging has utilized a model in which lesions are outliers in the distribution of tissue signal intensities across the entire brain of each patient. However, the sensitivity and specificity of lesion detection and segmentation with these approaches have been inadequate. In our analysis, we determined this is due to the substantial overlap between the whole brain signal intensity distribution of lesions and normal tissue. Inspired by the ability of experts to detect lesions based on their local signal intensity characteristics, we propose a new algorithm that achieves lesion and brain tissue segmentation through simultaneous estimation of a spatially global within-the-subject intensity distribution and a spatially local intensity distribution derived from a healthy reference population. We demonstrate that MS lesions can be segmented as outliers from this intensity model of population and subject. We carried out extensive experiments with both synthetic and clinical data, and compared the performance of our new algorithm to those of state-of-the art techniques. We found this new approach leads to a substantial improvement in the sensitivity and specificity of lesion detection and segmentation.
Collapse
|
153
|
Karimaghaloo Z, Rivaz H, Arnold DL, Collins DL, Arbel T. Temporal Hierarchical Adaptive Texture CRF for Automatic Detection of Gadolinium-Enhancing Multiple Sclerosis Lesions in Brain MRI. IEEE TRANSACTIONS ON MEDICAL IMAGING 2015; 34:1227-1241. [PMID: 25532171 DOI: 10.1109/tmi.2014.2382561] [Citation(s) in RCA: 8] [Impact Index Per Article: 0.9] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/04/2023]
Abstract
We propose a conditional random field (CRF) based classifier for segmentation of small enhanced pathologies. Specifically, we develop a temporal hierarchical adaptive texture CRF (THAT-CRF) and apply it to the challenging problem of gad enhancing lesion segmentation in brain MRI of patients with multiple sclerosis. In this context, the presence of many nonlesion enhancements (such as blood vessels) renders the problem more difficult. In addition to voxel-wise features, the framework exploits multiple higher order textures to discriminate the true lesional enhancements from the pool of other enhancements. Since lesional enhancements show more variation over time as compared to the nonlesional ones, we incorporate temporal texture analysis in order to study the textures of enhanced candidates over time. The parameters of the THAT-CRF model are learned based on 2380 scans from a multi-center clinical trial. The effect of different components of the model is extensively evaluated on 120 scans from a separate multi-center clinical trial. The incorporation of the temporal textures results in a general decrease of the false discovery rate. Specifically, THAT-CRF achieves overall sensitivity of 95% along with false discovery rate of 20% and average false positive count of 0.5 lesions per scan. The sensitivity of the temporal method to the trained time interval is further investigated on five different intervals of 69 patients. Moreover, superior performance is achieved by the reviewed labelings of our model compared to the fully manual labeling when applied to the context of separating different treatment arms in a real clinical trial.
Collapse
|
154
|
Lindemer ER, Salat DH, Smith EE, Nguyen K, Fischl B, Greve DN. White matter signal abnormality quality differentiates mild cognitive impairment that converts to Alzheimer's disease from nonconverters. Neurobiol Aging 2015; 36:2447-57. [PMID: 26095760 DOI: 10.1016/j.neurobiolaging.2015.05.011] [Citation(s) in RCA: 36] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/03/2015] [Revised: 05/15/2015] [Accepted: 05/19/2015] [Indexed: 01/18/2023]
Abstract
The objective of this study was to assess how longitudinal change in the quantity and quality of white matter signal abnormalities (WMSAs) contributes to the progression from mild cognitive impairment (MCI) to Alzheimer's disease (AD). The Mahalanobis distance of WMSA from normal-appearing white matter using T1-, T2-, and proton density-weighted MRI was defined as a quality measure for WMSA. Cross-sectional analysis of WMSA volume in 104 cognitively healthy older adults, 116 individuals with MCI who converted to AD within 3 years (mild cognitive impairment converter [MCI-C]), 115 individuals with MCI that did not convert in that time (mild cognitive impairment nonconverter [MCI-NC]), and 124 individuals with AD from the Alzheimer's Disease Neuroimaging Initiative revealed that WMSA volume was substantially greater in AD relative to the other groups but did not differ between MCI-NC and MCI-C. Longitudinally, MCI-C exhibited faster WMSA quality progression but not volume compared with matched MCI-NC beginning 18 months before MCI-C conversion to AD. The strongest difference in rate of change was seen in the time period starting 6 months before MCI-C conversion to AD and ending 6 months after conversion (p < 0.001). The relatively strong effect in this time period relative to AD conversion in the MCI-C was similar to the relative rate of change in hippocampal volume, a traditional imaging marker of AD pathology. These data demonstrate changes in white matter tissue properties that occur within WMSA in individuals with MCI that will subsequently obtain a clinical diagnosis of AD within 18 months. Individuals with AD have substantially greater WMSA volume than all MCI suggesting that there is a progressive accumulation of WMSA with progressive disease severity, and that quality change predates changes in this total volume. Given the timing of the changes in WMSA tissue quality relative to the clinical diagnosis of AD, these findings suggest that WMSAs are a critical component for this conversion and are a critical component of this clinical syndrome.
Collapse
Affiliation(s)
- Emily R Lindemer
- Harvard-MIT Division of Health Sciences and Technology, Cambridge, MA, USA; Athinoula A. Martinos Center for Biomedical Imaging, Charlestown, MA, USA; Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, MA, USA.
| | - David H Salat
- Athinoula A. Martinos Center for Biomedical Imaging, Charlestown, MA, USA; Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, MA, USA; VA Boston Healthcare System, Boston, MA, USA
| | - Eric E Smith
- Department of Clinical Neurosciences and Hotchkiss Brain Institute, University of Calgary, Calgary, Alberta, Canada
| | - Khoa Nguyen
- Athinoula A. Martinos Center for Biomedical Imaging, Charlestown, MA, USA; Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, MA, USA
| | - Bruce Fischl
- Harvard-MIT Division of Health Sciences and Technology, Cambridge, MA, USA; Athinoula A. Martinos Center for Biomedical Imaging, Charlestown, MA, USA; Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, MA, USA; Computer Science and Artificial Intelligence Laboratory (CSAIL), Massachusetts Institute of Technology (MIT), Cambridge, MA, USA
| | - Douglas N Greve
- Athinoula A. Martinos Center for Biomedical Imaging, Charlestown, MA, USA; Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, MA, USA
| | | |
Collapse
|
155
|
Jain S, Sima DM, Ribbens A, Cambron M, Maertens A, Van Hecke W, De Mey J, Barkhof F, Steenwijk MD, Daams M, Maes F, Van Huffel S, Vrenken H, Smeets D. Automatic segmentation and volumetry of multiple sclerosis brain lesions from MR images. NEUROIMAGE-CLINICAL 2015; 8:367-75. [PMID: 26106562 PMCID: PMC4474324 DOI: 10.1016/j.nicl.2015.05.003] [Citation(s) in RCA: 143] [Impact Index Per Article: 15.9] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 03/16/2015] [Revised: 05/11/2015] [Accepted: 05/13/2015] [Indexed: 11/29/2022]
Abstract
The location and extent of white matter lesions on magnetic resonance imaging (MRI) are important criteria for diagnosis, follow-up and prognosis of multiple sclerosis (MS). Clinical trials have shown that quantitative values, such as lesion volumes, are meaningful in MS prognosis. Manual lesion delineation for the segmentation of lesions is, however, time-consuming and suffers from observer variability. In this paper, we propose MSmetrix, an accurate and reliable automatic method for lesion segmentation based on MRI, independent of scanner or acquisition protocol and without requiring any training data. In MSmetrix, 3D T1-weighted and FLAIR MR images are used in a probabilistic model to detect white matter (WM) lesions as an outlier to normal brain while segmenting the brain tissue into grey matter, WM and cerebrospinal fluid. The actual lesion segmentation is performed based on prior knowledge about the location (within WM) and the appearance (hyperintense on FLAIR) of lesions. The accuracy of MSmetrix is evaluated by comparing its output with expert reference segmentations of 20 MRI datasets of MS patients. Spatial overlap (Dice) between the MSmetrix and the expert lesion segmentation is 0.67 ± 0.11. The intraclass correlation coefficient (ICC) equals 0.8 indicating a good volumetric agreement between the MSmetrix and expert labelling. The reproducibility of MSmetrix' lesion volumes is evaluated based on 10 MS patients, scanned twice with a short interval on three different scanners. The agreement between the first and the second scan on each scanner is evaluated through the spatial overlap and absolute lesion volume difference between them. The spatial overlap was 0.69 ± 0.14 and absolute total lesion volume difference between the two scans was 0.54 ± 0.58 ml. Finally, the accuracy and reproducibility of MSmetrix compare favourably with other publicly available MS lesion segmentation algorithms, applied on the same data using default parameter settings.
Collapse
Affiliation(s)
| | - Diana M Sima
- icometrix, R&D, Leuven, Belgium ; Department of Electrical Engineering-ESAT, STADIUS Center for Dynamical Systems, Signal Processing and Data Analytics, KU Leuven, Leuven, Belgium
| | | | - Melissa Cambron
- Department of Neurology, Center for Neurosciences, Universitair Ziekenhuis Brussel, Vrije Universiteit Brussel (VUB), Brussel, Belgium
| | | | | | - Johan De Mey
- Department of Neurology, Center for Neurosciences, Universitair Ziekenhuis Brussel, Vrije Universiteit Brussel (VUB), Brussel, Belgium
| | - Frederik Barkhof
- Department of Radiology and Nuclear Medicine, Neuroscience Campus Amsterdam, VU University Medical Center, Amsterdam, The Netherlands
| | - Martijn D Steenwijk
- Department of Radiology and Nuclear Medicine, Neuroscience Campus Amsterdam, VU University Medical Center, Amsterdam, The Netherlands
| | - Marita Daams
- Department of Radiology and Nuclear Medicine, Neuroscience Campus Amsterdam, VU University Medical Center, Amsterdam, The Netherlands ; Department of Anatomy and Neurosciences, Neuroscience Campus Amsterdam, VU University Medical Center, Amsterdam, The Netherlands
| | - Frederik Maes
- Department of Electrical Engineering-ESAT, PSI Medical Image Computing, KU Leuven, Leuven, Belgium ; Medical IT, iMinds, Leuven, Belgium
| | - Sabine Van Huffel
- Department of Electrical Engineering-ESAT, STADIUS Center for Dynamical Systems, Signal Processing and Data Analytics, KU Leuven, Leuven, Belgium ; Medical IT, iMinds, Leuven, Belgium
| | - Hugo Vrenken
- Department of Radiology and Nuclear Medicine, Neuroscience Campus Amsterdam, VU University Medical Center, Amsterdam, The Netherlands ; Department of Physics and Medical Technology, Neuroscience Campus Amsterdam, VU University Medical Center, Amsterdam, The Netherlands
| | | |
Collapse
|
156
|
Guizard N, Coupé P, Fonov VS, Manjón JV, Arnold DL, Collins DL. Rotation-invariant multi-contrast non-local means for MS lesion segmentation. NEUROIMAGE-CLINICAL 2015; 8:376-89. [PMID: 26106563 PMCID: PMC4474283 DOI: 10.1016/j.nicl.2015.05.001] [Citation(s) in RCA: 51] [Impact Index Per Article: 5.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 12/24/2014] [Revised: 05/02/2015] [Accepted: 05/03/2015] [Indexed: 01/18/2023]
Abstract
Multiple sclerosis (MS) lesion segmentation is crucial for evaluating disease burden, determining disease progression and measuring the impact of new clinical treatments. MS lesions can vary in size, location and intensity, making automatic segmentation challenging. In this paper, we propose a new supervised method to segment MS lesions from 3D magnetic resonance (MR) images using non-local means (NLM). The method uses a multi-channel and rotation-invariant distance measure to account for the diversity of MS lesions. The proposed segmentation method, rotation-invariant multi-contrast non-local means segmentation (RMNMS), captures the MS lesion spatial distribution and can accurately and robustly identify lesions regardless of their orientation, shape or size. An internal validation on a large clinical magnetic resonance imaging (MRI) dataset of MS patients demonstrated a good similarity measure result (Dice similarity = 60.1% and sensitivity = 75.4%), a strong correlation between expert and automatic lesion load volumes (R2 = 0.91), and a strong ability to detect lesions of different sizes and in varying spatial locations (lesion detection rate = 79.8%). On the independent MS Grand Challenge (MSGC) dataset validation, our method provided competitive results with state-of-the-art supervised and unsupervised methods. Qualitative visual and quantitative voxel- and lesion-wise evaluations demonstrated the accuracy of RMNMS method. We propose a new multi-channel MS lesion segmentation technique. We adapt for lesion segmentation the non-local means operator to account for multi-contrast and rotation-invariant distance. The proposed method presents highly competitive results compared to state-of-the-art methods. The proposed method provides segmentation quality near inter-rater variability for MS lesion segmentation. Our non-local approach is able to detect structures that vary in size, shape and location such as MS lesions.
Collapse
Affiliation(s)
| | - Pierrick Coupé
- Laboratoire Bordelais de Recherche en Informatique, Unité Mixte de Recherche CNRS (UMR 5800), PICTURA Research Group, 351, Talence, France
| | | | - Jose V Manjón
- IBIME Research Group, ITACA Institute, Universidad Politécnica de Valencia, Medical Imaging Area, Valencia, Spain
| | | | | |
Collapse
|
157
|
Harmouche R, Subbanna NK, Collins DL, Arnold DL, Arbel T. Probabilistic Multiple Sclerosis Lesion Classification Based on Modeling Regional Intensity Variability and Local Neighborhood Information. IEEE Trans Biomed Eng 2015; 62:1281-92. [DOI: 10.1109/tbme.2014.2385635] [Citation(s) in RCA: 21] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/07/2022]
|
158
|
Diez Y, Oliver A, Cabezas M, Valverde S, Martí R, Vilanova JC, Ramió-Torrentà L, Rovira A, Lladó X. Intensity based methods for brain MRI longitudinal registration. A study on multiple sclerosis patients. Neuroinformatics 2015; 12:365-79. [PMID: 24338728 DOI: 10.1007/s12021-013-9216-z] [Citation(s) in RCA: 13] [Impact Index Per Article: 1.4] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/17/2022]
Abstract
Registration is a key step in many automatic brain Magnetic Resonance Imaging (MRI) applications. In this work we focus on longitudinal registration of brain MRI for Multiple Sclerosis (MS) patients. First of all, we analyze the effect that MS lesions have on registration by synthetically eliminating some of the lesions. Our results show how a widely used method for longitudinal registration such as rigid registration is practically unconcerned by the presence of MS lesions while several non-rigid registration methods produce outputs that are significantly different. We then focus on assessing which is the best registration method for longitudinal MRI images of MS patients. In order to analyze the results obtained for all studied criteria, we use both descriptive statistics and statistical inference: one way ANOVA, pairwise t-tests and permutation tests.
Collapse
Affiliation(s)
- Yago Diez
- Computer Vision and Robotics Group, University of Girona, Campus Montilivi, Ed. P-IV, 17071, Girona, Spain,
| | | | | | | | | | | | | | | | | |
Collapse
|
159
|
Wang R, Li C, Wang J, Wei X, Li Y, Zhu Y, Zhang S. Threshold segmentation algorithm for automatic extraction of cerebral vessels from brain magnetic resonance angiography images. J Neurosci Methods 2015; 241:30-6. [DOI: 10.1016/j.jneumeth.2014.12.003] [Citation(s) in RCA: 44] [Impact Index Per Article: 4.9] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/14/2014] [Revised: 11/14/2014] [Accepted: 12/03/2014] [Indexed: 11/25/2022]
|
160
|
Subbanna N, Precup D, Arnold D, Arbel T. IMaGe: Iterative Multilevel Probabilistic Graphical Model for Detection and Segmentation of Multiple Sclerosis Lesions in Brain MRI. LECTURE NOTES IN COMPUTER SCIENCE 2015. [DOI: 10.1007/978-3-319-19992-4_40] [Citation(s) in RCA: 13] [Impact Index Per Article: 1.4] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 12/12/2022]
|
161
|
Abramson RG, Burton KR, Yu JPJ, Scalzetti EM, Yankeelov TE, Rosenkrantz AB, Mendiratta-Lala M, Bartholmai BJ, Ganeshan D, Lenchik L, Subramaniam RM. Methods and challenges in quantitative imaging biomarker development. Acad Radiol 2015; 22:25-32. [PMID: 25481515 PMCID: PMC4258641 DOI: 10.1016/j.acra.2014.09.001] [Citation(s) in RCA: 67] [Impact Index Per Article: 7.4] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/17/2014] [Revised: 09/03/2014] [Accepted: 09/03/2014] [Indexed: 12/18/2022]
Abstract
Academic radiology is poised to play an important role in the development and implementation of quantitative imaging (QI) tools. This article, drafted by the Association of University Radiologists Radiology Research Alliance Quantitative Imaging Task Force, reviews current issues in QI biomarker research. We discuss motivations for advancing QI, define key terms, present a framework for QI biomarker research, and outline challenges in QI biomarker development. We conclude by describing where QI research and development is currently taking place and discussing the paramount role of academic radiology in this rapidly evolving field.
Collapse
Affiliation(s)
- Richard G. Abramson
- Department of Radiology and Radiological Sciences Vanderbilt University 1161 21 Ave. S, CCC-1121 MCN Nashville, TN 37232-2675 (615)322-6759 Fax (615) 322-3764
| | - Kirsteen R. Burton
- Dept. of Medical Imaging and Institute of Health Policy, Management and Evaluation University of Toronto 263 McCaul Street, 4th Floor Toronto, ON M5T1W7 (416) 978-6801
| | - John-Paul J. Yu
- Department of Radiology and Biomedical Imaging University of California, San Francisco 505 Parnassus Ave., M-391 Box 0628 San Francisco, CA 94143-0628
| | - Ernest M. Scalzetti
- Department of Radiology SUNY Upstate Medical University 750 E. Adams St. Syracuse NY 13210
| | - Thomas E. Yankeelov
- Institute of Imaging Science Vanderbilt University 1161 21 Ave. S, AA-1105 MCN Nashville, TN 37232-2310
| | - Andrew B. Rosenkrantz
- Department of Radiology NYU Langone Medical Center 550 First Avenue New York, NY 10016 (212) 263-0232 fax: (212) 263-6634
| | - Mishal Mendiratta-Lala
- Abdominal and Cross-sectional Interventional Radiology Henry Ford Hospital 2799 West Grand Blvd. Detroit, MI 48202 (313) 461-1648
| | - Brian J. Bartholmai
- Chair, Division of Radiology Informatics Mayo Clinic Rochester, MN Phone 507-284-4292 FAX: 507-284-8996
| | - Dhakshinamoorthy Ganeshan
- Department of Abdominal Imaging University of Texas MD Anderson Cancer Center Houston, TX 77030 713-792-2486 Fax: 713-745-1151
| | - Leon Lenchik
- Department of Radiology Wake Forest School of Medicine Medical Center Boulevard Winston-Salem, NC 27157 Phone: 336-716-4316 Fax: 336-716-1278
| | - Rathan M. Subramaniam
- Russell H Morgan Department of Radiology and Radiological Sciences Johns Hopkins School of Medicine Department of Health Policy and Management Johns Hopkins Bloomberg School of Public Health Johns Hopkins University Baltimore, MD
| |
Collapse
|
162
|
Wang R, Li C, Wang J, Wei X, Li Y, Hui C, Zhu Y, Zhang S. Automatic segmentation of white matter lesions on magnetic resonance images of the brain by using an outlier detection strategy. Magn Reson Imaging 2014; 32:1321-9. [DOI: 10.1016/j.mri.2014.08.010] [Citation(s) in RCA: 5] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/08/2014] [Revised: 06/23/2014] [Accepted: 08/08/2014] [Indexed: 11/17/2022]
|
163
|
Automatic segmentation and quantitative analysis of white matter hyperintensities on FLAIR images using trimmed-likelihood estimator. Acad Radiol 2014; 21:1512-23. [PMID: 25176451 DOI: 10.1016/j.acra.2014.07.001] [Citation(s) in RCA: 4] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/28/2014] [Revised: 07/04/2014] [Accepted: 07/07/2014] [Indexed: 11/23/2022]
Abstract
RATIONALE AND OBJECTIVES Quantitative analysis of white matter hyperintensities (WMHs) on fluid-attenuated inversion recovery (FLAIR) images provides information for disease tracking, therapeutic efficacy assessment, and cognitive science research. This study developed an automatic segmentation method to detect and quantify WMHs on FLAIR images. This study aims to assess the accuracy and reproducibility of the proposed method. MATERIALS AND METHODS The FLAIR images of 82 patients (58-84 years) with different WMH burdens were acquired with the same 3T scanner (Intera-achieva SMI-2.1; Philip Medical System, Sixth Affiliated People's Hospital, Shanghai, China). The FLAIR images were preprocessed through brain extraction and intensity inhomogeneity correction. An anatomy atlas built from a set of 20 patients with different WMH burdens (mild, 11 patients; moderate, 6 patients; and severe, 3 patients) was used to estimate a control parameter in the framework of segmentation. The general flow for WMH segmentation included classification of foreground and background regions, detection of abnormally high signals, and WMH refinement. The performance of automatic segmentation was evaluated by a volumetric comparison with manual segmentation on patients with different WMH burdens. RESULTS Similarity index values for the accuracy of automatic segmentation compared to manual segmentation were consistently high for patients with different WMH burdens (mild, 0.78 ± 0.08; moderate, 0.83 ± 0.06; severe, 0.84 ± 0.08; and total, 0.80 ± 0.08). Linear regression demonstrated a strong correlation between the WMH volumes measured by the two methods in all patients (r = 0.98, P = .006). Small average differences were detected between the WMH volumes obtained through manual and automatic segmentations (mild, 4.76%; moderate, 6.84%; and severe, 7.59%). The results of Bland-Altman analysis show a system bias of 0.68 cm(3) and a standard deviation of 2.10 cm(3) over the range of 2.58-53.9 cm(3). CONCLUSIONS The developed method is accurate and efficient in detecting and quantifying differently sized WMHs on FLAIR images. Automatic segmentation is a promising computer-aided diagnostic tool to study WMHs in aging and dementia in basic research and even in clinical trials.
Collapse
|
164
|
Automatic segmentation and volumetric quantification of white matter hyperintensities on fluid-attenuated inversion recovery images using the extreme value distribution. Neuroradiology 2014; 57:307-20. [PMID: 25407717 DOI: 10.1007/s00234-014-1466-4] [Citation(s) in RCA: 7] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/18/2014] [Accepted: 11/10/2014] [Indexed: 10/24/2022]
Abstract
INTRODUCTION This study aims to develop an automatic segmentation framework on the basis of extreme value distribution (EVD) for the detection and volumetric quantification of white matter hyperintensities (WMHs) on fluid-attenuated inversion recovery (FLAIR) images. METHODS Two EVD-based segmentation methods, namely the Gumbel and Fréchet segmentation, were developed to detect WMHs on FLAIR (slice thickness = 5 mm; TR/TE/TI = 11,000/120/2,800 ms; flip angle = 90°) images. Another automatic segmentation method using a trimmed likelihood estimator (TLE) was implemented for comparison with our proposed segmentation framework. The performances of the three automatic segmentation methods were evaluated by comparing with the manual segmentation method. RESULTS The Dice similarity coefficients (DSCs) of the two EVD-based segmentation methods were larger than those of the TLE-based segmentation method (Gumbel, 0.823 ± 0.063; Fréchet, 0.843 ± 0.057; TLE, 0.817 ± 0.068), demonstrating that the EVD-based segmentation outperformed the TLE-based segmentation. The Fréchet segmentation obtained larger DSCs on patients with moderate to severe lesion loads and a comparable performance on patients with mild lesion loads, indicating that the Fréchet segmentation was superior to the Gumbel segmentation. The Gumbel segmentation underestimated the lesion volumes of all patients, whereas the Fréchet and TLE-based segmentation methods obtained overestimated lesion volumes (Manual, 13.71 ± 14.02 cc; Gumbel, 12.73 ± 13.21 cc; Fréchet, 13.88 ± 13.96 cc; TLE, 13.54 ± 12.27 cc). Moreover, the EVD-based segmentation was demonstrated to be comparable to other state-of-the-art methods on a publicly available dataset. CONCLUSION The proposed EVD-based segmentation framework is a promising, effective, and convenient tool for volumetric quantification and further study of WMHs in aging and dementia.
Collapse
|
165
|
Abstract
The detection of abnormal intensities in brain images caused by the presence of pathologies is currently under great scrutiny. Selecting appropriate models for pathological data is of critical importance for an unbiased and biologically plausible model fit, which in itself enables a better understanding of the underlying data and biological processes. Besides, it impacts on one's ability to extract pathologically meaningful imaging biomarkers. With this aim in mind, this work proposes a fully unsupervised hierarchical model selection framework for neuroimaging data which permits the stratification of different types of abnormal image atterns without prior knowledge about the subject's pathological status.
Collapse
|
166
|
BOOST: a supervised approach for multiple sclerosis lesion segmentation. J Neurosci Methods 2014; 237:108-17. [PMID: 25194638 DOI: 10.1016/j.jneumeth.2014.08.024] [Citation(s) in RCA: 25] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/20/2013] [Revised: 08/19/2014] [Accepted: 08/25/2014] [Indexed: 11/23/2022]
Abstract
BACKGROUND Automatic multiple sclerosis lesion segmentation is a challenging task. An extensive analysis of the most recent techniques indicates an improvement of the results obtained when using prior knowledge and contextual information. NEW METHOD We present BOOST, a knowledge-based approach to automatically segment multiple sclerosis lesions through a voxel by voxel classification. We used the Gentleboost classifier and a set of features, including contextual features, registered atlas probability maps and an outlier map. RESULTS Results are computed on a set of 45 cases from three different hospitals (15 of each), obtaining a moderate agreement between the manual annotations and the automatically segmented results. COMPARISON WITH EXISTING METHOD(S) We quantitatively compared our results with three public state-of-the-art approaches obtaining competitive results and a better overlap with manual annotations. Our approach tends to better segment those cases with high lesion load, while cases with small lesion load are more difficult to accurately segment. CONCLUSIONS We believe BOOST has potential applicability in the clinical practice, although it should be improved in those cases with small lesion load.
Collapse
|
167
|
Ferreira D, Voevodskaya O, Imrell K, Stawiarz L, Spulber G, Wahlund LO, Hillert J, Westman E, Karrenbauer VD. Multiple sclerosis patients lacking oligoclonal bands in the cerebrospinal fluid have less global and regional brain atrophy. J Neuroimmunol 2014; 274:149-54. [DOI: 10.1016/j.jneuroim.2014.06.010] [Citation(s) in RCA: 39] [Impact Index Per Article: 3.9] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/09/2014] [Accepted: 06/17/2014] [Indexed: 01/26/2023]
|
168
|
Automated White Matter Hyperintensity Detection in Multiple Sclerosis Using 3D T2 FLAIR. Int J Biomed Imaging 2014; 2014:239123. [PMID: 25136355 PMCID: PMC4130152 DOI: 10.1155/2014/239123] [Citation(s) in RCA: 9] [Impact Index Per Article: 0.9] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/11/2014] [Revised: 07/09/2014] [Accepted: 07/10/2014] [Indexed: 02/06/2023] Open
Abstract
White matter hyperintensities (WMH) seen on T2WI are a hallmark of multiple sclerosis (MS) as it indicates inflammation associated with the disease. Automatic detection of the WMH can be valuable in diagnosing and monitoring of treatment effectiveness. T2 fluid attenuated inversion recovery (FLAIR) MR images provided good contrast between the lesions and other tissue; however the signal intensity of gray matter tissue was close to the lesions in FLAIR images that may cause more false positives in the segment result. We developed and evaluated a tool for automated WMH detection only using high resolution 3D T2 fluid attenuated inversion recovery (FLAIR) MR images. We use a high spatial frequency suppression method to reduce the gray matter area signal intensity. We evaluate our method in 26 MS patients and 26 age matched health controls. The data from the automated algorithm showed good agreement with that from the manual segmentation. The linear correlation between these two approaches in comparing WMH volumes was found to be Y = 1.04X + 1.74 (R (2) = 0.96). The automated algorithm estimates the number, volume, and category of WMH.
Collapse
|
169
|
Cabezas M, Oliver A, Roura E, Freixenet J, Vilanova JC, Ramió-Torrentà L, Rovira A, Lladó X. Automatic multiple sclerosis lesion detection in brain MRI by FLAIR thresholding. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2014; 115:147-161. [PMID: 24813718 DOI: 10.1016/j.cmpb.2014.04.006] [Citation(s) in RCA: 25] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 09/17/2013] [Revised: 03/25/2014] [Accepted: 04/06/2014] [Indexed: 06/03/2023]
Abstract
Magnetic resonance imaging (MRI) is frequently used to detect and segment multiple sclerosis lesions due to the detailed and rich information provided. We present a modified expectation-maximisation algorithm to segment brain tissues (white matter, grey matter, and cerebro-spinal fluid) as well as a partial volume class containing fluid and grey matter. This algorithm provides an initial segmentation in which lesions are not separated from tissue, thus a second step is needed to find them. This second step involves the thresholding of the FLAIR image, followed by a regionwise refinement to discard false detections. To evaluate the proposal, we used a database with 45 cases comprising 1.5T imaging data from three different hospitals with different scanner machines and with a variable lesion load per case. The results for our database point out to a higher accuracy when compared to two of the best state-of-the-art approaches.
Collapse
Affiliation(s)
- Mariano Cabezas
- Department of Computer Architecture and Technology, University of Girona, Spain
| | - Arnau Oliver
- Department of Computer Architecture and Technology, University of Girona, Spain
| | - Eloy Roura
- Department of Computer Architecture and Technology, University of Girona, Spain
| | - Jordi Freixenet
- Department of Computer Architecture and Technology, University of Girona, Spain
| | | | - Lluís Ramió-Torrentà
- Multiple Sclerosis and Neuroimmunology Unit, Dr. Josep Trueta University Hospital, Spain
| | - Alex Rovira
- Magnetic Resonance Unit, Department of Radiology, Vall d'Hebron University Hospital, Spain
| | - Xavier Lladó
- Department of Computer Architecture and Technology, University of Girona, Spain.
| |
Collapse
|
170
|
Sweeney EM, Vogelstein JT, Cuzzocreo JL, Calabresi PA, Reich DS, Crainiceanu CM, Shinohara RT. A comparison of supervised machine learning algorithms and feature vectors for MS lesion segmentation using multimodal structural MRI. PLoS One 2014; 9:e95753. [PMID: 24781953 PMCID: PMC4004572 DOI: 10.1371/journal.pone.0095753] [Citation(s) in RCA: 33] [Impact Index Per Article: 3.3] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/03/2014] [Accepted: 03/28/2014] [Indexed: 11/18/2022] Open
Abstract
Machine learning is a popular method for mining and analyzing large collections of medical data. We focus on a particular problem from medical research, supervised multiple sclerosis (MS) lesion segmentation in structural magnetic resonance imaging (MRI). We examine the extent to which the choice of machine learning or classification algorithm and feature extraction function impacts the performance of lesion segmentation methods. As quantitative measures derived from structural MRI are important clinical tools for research into the pathophysiology and natural history of MS, the development of automated lesion segmentation methods is an active research field. Yet, little is known about what drives performance of these methods. We evaluate the performance of automated MS lesion segmentation methods, which consist of a supervised classification algorithm composed with a feature extraction function. These feature extraction functions act on the observed T1-weighted (T1-w), T2-weighted (T2-w) and fluid-attenuated inversion recovery (FLAIR) MRI voxel intensities. Each MRI study has a manual lesion segmentation that we use to train and validate the supervised classification algorithms. Our main finding is that the differences in predictive performance are due more to differences in the feature vectors, rather than the machine learning or classification algorithms. Features that incorporate information from neighboring voxels in the brain were found to increase performance substantially. For lesion segmentation, we conclude that it is better to use simple, interpretable, and fast algorithms, such as logistic regression, linear discriminant analysis, and quadratic discriminant analysis, and to develop the features to improve performance.
Collapse
Affiliation(s)
- Elizabeth M. Sweeney
- Department of Biostatistics, The Johns Hopkins University, Baltimore, Maryland, United States of America
- Translational Neuroradiology Unit, Neuroimmunology Branch, National Institute of Neurological Disease and Stroke, National Institute of Health, Bethesda, Maryland, United States of America
- * E-mail:
| | - Joshua T. Vogelstein
- Department of Statistical Science, Duke University, Durham, North Carolina, United States of America
- Center for the Developing Brain, Child Mind Institute, New York, New York, United States of America
| | - Jennifer L. Cuzzocreo
- Department of Radiology, The Johns Hopkins University School of Medicine, Baltimore, Maryland, United States of America
| | - Peter A. Calabresi
- Department of Neurology, The Johns Hopkins University School of Medicine, Baltimore, Maryland, United States of America
| | - Daniel S. Reich
- Department of Biostatistics, The Johns Hopkins University, Baltimore, Maryland, United States of America
- Translational Neuroradiology Unit, Neuroimmunology Branch, National Institute of Neurological Disease and Stroke, National Institute of Health, Bethesda, Maryland, United States of America
- Department of Radiology, The Johns Hopkins University School of Medicine, Baltimore, Maryland, United States of America
- Department of Neurology, The Johns Hopkins University School of Medicine, Baltimore, Maryland, United States of America
| | - Ciprian M. Crainiceanu
- Department of Biostatistics, The Johns Hopkins University, Baltimore, Maryland, United States of America
| | - Russell T. Shinohara
- Department of Biostatistics and Epidemiology, Center for Clinical Epidemiology and Biostatistics, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, United States of America
| |
Collapse
|
171
|
Gao J, Li C, Feng C, Xie M, Yin Y, Davatzikos C. Non-locally regularized segmentation of multiple sclerosis lesion from multi-channel MRI data. Magn Reson Imaging 2014; 32:1058-66. [PMID: 24948583 DOI: 10.1016/j.mri.2014.03.006] [Citation(s) in RCA: 19] [Impact Index Per Article: 1.9] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/26/2013] [Revised: 01/20/2014] [Accepted: 03/07/2014] [Indexed: 11/28/2022]
Abstract
Segmentation of multiple sclerosis (MS) lesion is important for many neuroimaging studies. In this paper, we propose a novel algorithm for automatic segmentation of MS lesions from multi-channel MR images (T1W, T2W and FLAIR images). The proposed method is an extension of Li et al.'s algorithm in [1], which only segments the normal tissues from T1W images. The proposed method is aimed to segment MS lesions, while normal tissues are also segmented and bias field is estimated to handle intensity inhomogeneities in the images. Another contribution of this paper is the introduction of a nonlocal means technique to achieve spatially regularized segmentation, which overcomes the influence of noise. Experimental results have demonstrated the effectiveness and advantages of the proposed algorithm.
Collapse
Affiliation(s)
- Jingjing Gao
- School of Electronic Engineering, University of Electronic Science and Technology of China, Chengdu, Sichuan 611731, China; Center of Biomedical Image Computing and Analytics, University of PA, Philadelphia 19104, USA
| | - Chunming Li
- Center of Biomedical Image Computing and Analytics, University of PA, Philadelphia 19104, USA; Department of Radiology, University of Pennsylvania, Philadelphia, PA 19104, USA.
| | - Chaolu Feng
- Key Laboratory of Medical Image Computing of Ministry of Education, Northeastern University, Shenyang, Liaoning 110819, China
| | - Mei Xie
- School of Electronic Engineering, University of Electronic Science and Technology of China, Chengdu, Sichuan 611731, China
| | - Yilong Yin
- School of Computer Science and Technology, Shandong University, Jinan, Shandong 250100, China
| | - Christos Davatzikos
- Center of Biomedical Image Computing and Analytics, University of PA, Philadelphia 19104, USA; Department of Radiology, University of Pennsylvania, Philadelphia, PA 19104, USA
| |
Collapse
|
172
|
Iannitti T, Kerr BJ, Taylor BK. Mechanisms and pharmacology of neuropathic pain in multiple sclerosis. Curr Top Behav Neurosci 2014; 20:75-97. [PMID: 24590824 PMCID: PMC4464806 DOI: 10.1007/7854_2014_288] [Citation(s) in RCA: 16] [Impact Index Per Article: 1.6] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/06/2023]
Abstract
The neuropathic pain of multiple sclerosis is quite prevalent and severely impacts quality of life. A few randomized, placebo-controlled, blinded clinical trials suggest that cannabis- and anticonvulsant-based treatments provide partial pain relief, but at the expense of adverse events. An even smaller, but emerging, number of translational studies are using rodent models of experimental autoimmune encephalomyelitis (EAE), which exhibit pain-like behaviors resembling those of Multiple sclerosis (MS) patients. These studies not only support the possible effectiveness of anticonvulsants, but also compel further clinical trials with serotonin-norepinephrine reuptake inhibitors, the immunosuppressant drug rapamycin, or drugs which interfere with glutamatergic neurotransmission. Future behavioral studies in EAE models are essential toward a new pharmacotherapy of multiple sclerosis pain.
Collapse
Affiliation(s)
- T Iannitti
- Department of Physiology, School of Medicine, University of Kentucky Medical Center, Lexington, KY, 40536-0298, USA
| | | | | |
Collapse
|
173
|
Ganiler O, Oliver A, Diez Y, Freixenet J, Vilanova JC, Beltran B, Ramió-Torrentà L, Rovira A, Lladó X. A subtraction pipeline for automatic detection of new appearing multiple sclerosis lesions in longitudinal studies. Neuroradiology 2014; 56:363-74. [PMID: 24590302 DOI: 10.1007/s00234-014-1343-1] [Citation(s) in RCA: 39] [Impact Index Per Article: 3.9] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/20/2013] [Accepted: 02/13/2014] [Indexed: 11/30/2022]
Abstract
INTRODUCTION Time-series analysis of magnetic resonance images (MRI) is of great value for multiple sclerosis (MS) diagnosis and follow-up. In this paper, we present an unsupervised subtraction approach which incorporates multisequence information to deal with the detection of new MS lesions in longitudinal studies. METHODS The proposed pipeline for detecting new lesions consists of the following steps: skull stripping, bias field correction, histogram matching, registration, white matter masking, image subtraction, automated thresholding, and postprocessing. We also combine the results of PD-w and T2-w images to reduce false positive detections. RESULTS Experimental tests are performed in 20 MS patients with two temporal studies separated 12 (12M) or 48 (48M) months in time. The pipeline achieves very good performance obtaining an overall sensitivity of 0.83 and 0.77 with a false discovery rate (FDR) of 0.14 and 0.18 for the 12M and 48M datasets, respectively. The most difficult situation for the pipeline is the detection of very small lesions where the obtained sensitivity is lower and the FDR higher. CONCLUSION Our fully automated approach is robust and accurate, allowing detection of new appearing MS lesions. We believe that the pipeline can be applied to large collections of images and also be easily adapted to monitor other brain pathologies.
Collapse
Affiliation(s)
- Onur Ganiler
- VICOROB Computer Vision and Robotics Group, University of Girona, Edifici P-IV. Campus de Montilivi s/n, 17071, Girona, Spain,
| | | | | | | | | | | | | | | | | |
Collapse
|
174
|
|
175
|
Popescu V, Ran NCG, Barkhof F, Chard DT, Wheeler-Kingshott CA, Vrenken H. Accurate GM atrophy quantification in MS using lesion-filling with co-registered 2D lesion masks. NEUROIMAGE-CLINICAL 2014; 4:366-73. [PMID: 24567908 PMCID: PMC3930097 DOI: 10.1016/j.nicl.2014.01.004] [Citation(s) in RCA: 34] [Impact Index Per Article: 3.4] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 10/29/2013] [Revised: 12/18/2013] [Accepted: 01/10/2014] [Indexed: 11/28/2022]
Abstract
Background In multiple sclerosis (MS), brain atrophy quantification is affected by white matter lesions. LEAP and FSL-lesion_filling, replace lesion voxels with white matter intensities; however, they require precise lesion identification on 3DT1-images. Aim To determine whether 2DT2 lesion masks co-registered to 3DT1 images, yield grey and white matter volumes comparable to precise lesion masks. Methods 2DT2 lesion masks were linearly co-registered to 20 3DT1-images of MS patients, with nearest-neighbor (NNI), and tri-linear interpolation. As gold-standard, lesion masks were manually outlined on 3DT1-images. LEAP and FSL-lesion_filling were applied with each lesion mask. Grey (GM) and white matter (WM) volumes were quantified with FSL-FAST, and deep gray matter (DGM) volumes using FSL-FIRST. Volumes were compared between lesion mask types using paired Wilcoxon tests. Results Lesion-filling with gold-standard lesion masks compared to native images reduced GM overestimation by 1.93 mL (p < .001) for LEAP, and 1.21 mL (p = .002) for FSL-lesion_filling. Similar effects were achieved with NNI lesion masks from 2DT2. Global WM underestimation was not significantly influenced. GM and WM volumes from NNI, did not differ significantly from gold-standard. GM segmentation differed between lesion masks in the lesion area, and also elsewhere. Using the gold-standard, FSL-FAST quantified as GM on average 0.4% of the lesion area with LEAP and 24.5% with FSL-lesion_filling. Lesion-filling did not influence DGM volumes from FSL-FIRST. Discussion These results demonstrate that for global GM volumetry, precise lesion masks on 3DT1 images can be replaced by co-registered 2DT2 lesion masks. This makes lesion-filling a feasible method for GM atrophy measurements in MS. In multiple sclerosis brain atrophy measurement is affected by white matter lesions. LEAP and FSL-lesion_filling replace lesion voxels with white matter intensities. The two lesion-filling methods show differences. 2D lesion masks can be registered and used for lesion-filling on 3DT1 images. This makes lesion-filling a feasible method for atrophy measurements in MS.
Collapse
Affiliation(s)
- V Popescu
- Department of Radiology and Nuclear Medicine, VU University Medical Center, Amsterdam, The Netherlands
| | - N C G Ran
- Department of Radiology and Nuclear Medicine, VU University Medical Center, Amsterdam, The Netherlands
| | - F Barkhof
- Department of Radiology and Nuclear Medicine, VU University Medical Center, Amsterdam, The Netherlands
| | - D T Chard
- NMR Research Unit, Queen Square Multiple Sclerosis Centre, University College London (UCL) Institute of Neurology, London, UK ; National Institute for Health Research (NIHR), University College London Hospitals (UCLH), Biomedical Research Centre, London, UK
| | - C A Wheeler-Kingshott
- NMR Research Unit, Queen Square Multiple Sclerosis Centre, University College London (UCL) Institute of Neurology, London, UK
| | - H Vrenken
- Department of Radiology and Nuclear Medicine, VU University Medical Center, Amsterdam, The Netherlands ; Department of Physics and Medical Technology, VU University Medical Center, Amsterdam, The Netherlands
| |
Collapse
|
176
|
Deep Learning of Image Features from Unlabeled Data for Multiple Sclerosis Lesion Segmentation. MACHINE LEARNING IN MEDICAL IMAGING 2014. [DOI: 10.1007/978-3-319-10581-9_15] [Citation(s) in RCA: 21] [Impact Index Per Article: 2.1] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 12/03/2022]
|
177
|
İçer S. Automatic segmentation of corpus callosum using Gaussian mixture modeling and Fuzzy C means methods. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2013; 112:38-46. [PMID: 23871683 DOI: 10.1016/j.cmpb.2013.06.006] [Citation(s) in RCA: 6] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 05/02/2013] [Revised: 06/05/2013] [Accepted: 06/14/2013] [Indexed: 06/02/2023]
Abstract
This paper presents a comparative study of the success and performance of the Gaussian mixture modeling and Fuzzy C means methods to determine the volume and cross-sectionals areas of the corpus callosum (CC) using simulated and real MR brain images. The Gaussian mixture model (GMM) utilizes weighted sum of Gaussian distributions by applying statistical decision procedures to define image classes. In the Fuzzy C means (FCM), the image classes are represented by certain membership function according to fuzziness information expressing the distance from the cluster centers. In this study, automatic segmentation for midsagittal section of the CC was achieved from simulated and real brain images. The volume of CC was obtained using sagittal sections areas. To compare the success of the methods, segmentation accuracy, Jaccard similarity and time consuming for segmentation were calculated. The results show that the GMM method resulted by a small margin in more accurate segmentation (midsagittal section segmentation accuracy 98.3% and 97.01% for GMM and FCM); however the FCM method resulted in faster segmentation than GMM. With this study, an accurate and automatic segmentation system that allows opportunity for quantitative comparison to doctors in the planning of treatment and the diagnosis of diseases affecting the size of the CC was developed. This study can be adapted to perform segmentation on other regions of the brain, thus, it can be operated as practical use in the clinic.
Collapse
Affiliation(s)
- Semra İçer
- Erciyes University, Engineering Faculty, Biomedical Engineering Department, Kayseri, Turkey.
| |
Collapse
|
178
|
Bauer S, Wiest R, Nolte LP, Reyes M. A survey of MRI-based medical image analysis for brain tumor studies. Phys Med Biol 2013; 58:R97-129. [PMID: 23743802 DOI: 10.1088/0031-9155/58/13/r97] [Citation(s) in RCA: 301] [Impact Index Per Article: 27.4] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/18/2022]
Abstract
MRI-based medical image analysis for brain tumor studies is gaining attention in recent times due to an increased need for efficient and objective evaluation of large amounts of data. While the pioneering approaches applying automated methods for the analysis of brain tumor images date back almost two decades, the current methods are becoming more mature and coming closer to routine clinical application. This review aims to provide a comprehensive overview by giving a brief introduction to brain tumors and imaging of brain tumors first. Then, we review the state of the art in segmentation, registration and modeling related to tumor-bearing brain images with a focus on gliomas. The objective in the segmentation is outlining the tumor including its sub-compartments and surrounding tissues, while the main challenge in registration and modeling is the handling of morphological changes caused by the tumor. The qualities of different approaches are discussed with a focus on methods that can be applied on standard clinical imaging protocols. Finally, a critical assessment of the current state is performed and future developments and trends are addressed, giving special attention to recent developments in radiological tumor assessment guidelines.
Collapse
Affiliation(s)
- Stefan Bauer
- Institute for Surgical Technology and Biomechanics, University of Bern, Switzerland.
| | | | | | | |
Collapse
|
179
|
Sweeney EM, Shinohara RT, Shiee N, Mateen FJ, Chudgar AA, Cuzzocreo JL, Calabresi PA, Pham DL, Reich DS, Crainiceanu CM. OASIS is Automated Statistical Inference for Segmentation, with applications to multiple sclerosis lesion segmentation in MRI. Neuroimage Clin 2013; 2:402-13. [PMID: 24179794 PMCID: PMC3777691 DOI: 10.1016/j.nicl.2013.03.002] [Citation(s) in RCA: 48] [Impact Index Per Article: 4.4] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/18/2013] [Revised: 02/23/2013] [Accepted: 03/05/2013] [Indexed: 10/31/2022]
Abstract
Magnetic resonance imaging (MRI) can be used to detect lesions in the brains of multiple sclerosis (MS) patients and is essential for diagnosing the disease and monitoring its progression. In practice, lesion load is often quantified by either manual or semi-automated segmentation of MRI, which is time-consuming, costly, and associated with large inter- and intra-observer variability. We propose OASIS is Automated Statistical Inference for Segmentation (OASIS), an automated statistical method for segmenting MS lesions in MRI studies. We use logistic regression models incorporating multiple MRI modalities to estimate voxel-level probabilities of lesion presence. Intensity-normalized T1-weighted, T2-weighted, fluid-attenuated inversion recovery and proton density volumes from 131 MRI studies (98 MS subjects, 33 healthy subjects) with manual lesion segmentations were used to train and validate our model. Within this set, OASIS detected lesions with a partial area under the receiver operating characteristic curve for clinically relevant false positive rates of 1% and below of 0.59% (95% CI; [0.50%, 0.67%]) at the voxel level. An experienced MS neuroradiologist compared these segmentations to those produced by LesionTOADS, an image segmentation software that provides segmentation of both lesions and normal brain structures. For lesions, OASIS out-performed LesionTOADS in 74% (95% CI: [65%, 82%]) of cases for the 98 MS subjects. To further validate the method, we applied OASIS to 169 MRI studies acquired at a separate center. The neuroradiologist again compared the OASIS segmentations to those from LesionTOADS. For lesions, OASIS ranked higher than LesionTOADS in 77% (95% CI: [71%, 83%]) of cases. For a randomly selected subset of 50 of these studies, one additional radiologist and one neurologist also scored the images. Within this set, the neuroradiologist ranked OASIS higher than LesionTOADS in 76% (95% CI: [64%, 88%]) of cases, the neurologist 66% (95% CI: [52%, 78%]) and the radiologist 52% (95% CI: [38%, 66%]). OASIS obtains the estimated probability for each voxel to be part of a lesion by weighting each imaging modality with coefficient weights. These coefficients are explicit, obtained using standard model fitting techniques, and can be reused in other imaging studies. This fully automated method allows sensitive and specific detection of lesion presence and may be rapidly applied to large collections of images.
Collapse
Affiliation(s)
- Elizabeth M. Sweeney
- Department of Biostatistics, The Johns Hopkins University, Baltimore, MD 21205, USA
- Translational Neuroradiology Unit, Neuroimmunology Branch, National Institute of Neurological Disease and Stroke, National Institute of Health, Bethesda, MD 20892, USA
| | - Russell T. Shinohara
- Translational Neuroradiology Unit, Neuroimmunology Branch, National Institute of Neurological Disease and Stroke, National Institute of Health, Bethesda, MD 20892, USA
- Department of Biostatistics and Epidemiology, Center for Clinical Epidemiology and Biostatistics, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA 19104, USA
| | - Navid Shiee
- Center for Neuroscience and Regenerative Medicine, Henry M. Jackson Foundation, Bethesda, MD 20892, USA
| | - Farrah J. Mateen
- Department of International Health, The Johns Hopkins University, Baltimore, MD 21205, USA
| | - Avni A. Chudgar
- Department of Radiology, Division of Emergency Radiology, Brigham and Women's Hospital and Harvard Medical School, Boston, MA 02115, USA
| | - Jennifer L. Cuzzocreo
- Department of Radiology, The Johns Hopkins University School of Medicine, Baltimore, MD 21287, USA
| | - Peter A. Calabresi
- Department of Neurology, The Johns Hopkins University School of Medicine, Baltimore, MD 21287, USA
| | - Dzung L. Pham
- Center for Neuroscience and Regenerative Medicine, Henry M. Jackson Foundation, Bethesda, MD 20892, USA
| | - Daniel S. Reich
- Department of Biostatistics, The Johns Hopkins University, Baltimore, MD 21205, USA
- Translational Neuroradiology Unit, Neuroimmunology Branch, National Institute of Neurological Disease and Stroke, National Institute of Health, Bethesda, MD 20892, USA
- Department of Radiology, The Johns Hopkins University School of Medicine, Baltimore, MD 21287, USA
- Department of Neurology, The Johns Hopkins University School of Medicine, Baltimore, MD 21287, USA
| | | |
Collapse
|
180
|
Weiss N, Rueckert D, Rao A. Multiple sclerosis lesion segmentation using dictionary learning and sparse coding. MEDICAL IMAGE COMPUTING AND COMPUTER-ASSISTED INTERVENTION : MICCAI ... INTERNATIONAL CONFERENCE ON MEDICAL IMAGE COMPUTING AND COMPUTER-ASSISTED INTERVENTION 2013; 16:735-42. [PMID: 24505733 DOI: 10.1007/978-3-642-40811-3_92] [Citation(s) in RCA: 36] [Impact Index Per Article: 3.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 12/12/2022]
Abstract
The segmentation of lesions in the brain during the development of Multiple Sclerosis is part of the diagnostic assessment for this disease and gives information on its current severity. This laborious process is still carried out in a manual or semiautomatic fashion by clinicians because published automatic approaches have not been universal enough to be widely employed in clinical practice. Thus Multiple Sclerosis lesion segmentation remains an open problem. In this paper we present a new unsupervised approach addressing this problem with dictionary learning and sparse coding methods. We show its general applicability to the problem of lesion segmentation by evaluating our approach on synthetic and clinical image data and comparing it to state-of-the-art methods. Furthermore the potential of using dictionary learning and sparse coding for such segmentation tasks is investigated and various possibilities for further experiments are discussed.
Collapse
Affiliation(s)
| | | | - Anil Rao
- Imperial College London, London, UK
| |
Collapse
|