Automatic atlas-based three-label cartilage segmentation from MR knee images

Liang, Shan; Charles, Cecil; Niethammer, Marc

doi:10.1109/mmbia.2012.6164757

Cited by 27 publications

(43 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The supervised learning was performed by removing the image translation branch from the R‐Net while keeping the aforementioned training procedure the same. To compare SUSAN with state‐of‐the‐art conventional segmentation methods, a multiatlas registration algorithm from the Knee Segmentation and Registration Toolkit (KSRT, https://bitbucket.org/marcniethammer/ksrt) was evaluated. Multiple atlases were built from all 60 subjects in SKI10 image dataset, and the registration workflow and parameters were kept the same as the default setting implemented in the source code and stated in the original study .…”

Section: Methodsmentioning

confidence: 99%

SUSAN: segment unannotated image structure using adversarial network

Liu

2018

Magnetic Resonance in Med

View full text Add to dashboard Cite

Purpose To describe and evaluate a segmentation method using joint adversarial and segmentation convolutional neural network to achieve accurate segmentation using unannotated MR image datasets. Theory and Methods A segmentation pipeline was built using joint adversarial and segmentation network. A convolutional neural network technique called cycle‐consistent generative adversarial network (CycleGAN) was applied as the core of the method to perform unpaired image‐to‐image translation between different MR image datasets. A joint segmentation network was incorporated into the adversarial network to obtain additional functionality for semantic segmentation. The fully automated segmentation method termed as SUSAN was tested for segmenting bone and cartilage on 2 clinical knee MR image datasets using images and annotated segmentation masks from an online publicly available knee MR image dataset. The segmentation results were compared using quantitative segmentation metrics with the results from a supervised U‐Net segmentation method and 2 registration methods. The Wilcoxon signed‐rank test was used to evaluate the value difference of quantitative metrics between different methods. Results The proposed method SUSAN provided high segmentation accuracy with results comparable to the supervised U‐Net segmentation method (most quantitative metrics having P > 0.05) and significantly better than a multiatlas registration method (all quantitative metrics having P < 0.001) and a direct registration method (all quantitative metrics having P< 0.0001) for the clinical knee image datasets. SUSAN also demonstrated the applicability for segmenting knee MR images with different tissue contrasts. Conclusion SUSAN performed rapid and accurate tissue segmentation for multiple MR image datasets without the need for sequence specific segmentation annotation. The joint adversarial and segmentation network and training strategy have promising potential applications in medical image segmentation.

show abstract

Section: Methodsmentioning

confidence: 99%

SUSAN: segment unannotated image structure using adversarial network

Liu

2018

Magnetic Resonance in Med

View full text Add to dashboard Cite

show abstract

“…Articular cartilage segmentation is often performed manually or semiautomatically, which introduces user variation and utilizes extensive human resources and time. Recently, several automatic techniques have been proposed for the knee articular cartilage segmentation including: statistical‐based active shape model‐based, texture‐based, and atlas‐based methods.…”

mentioning

confidence: 99%

Fully automatic analysis of the knee articular cartilageT_1ρrelaxation time using voxel-based relaxometry

Pedoia

et al. 2015

J. Magn. Reson. Imaging

127

View full text Add to dashboard Cite

Purpose To develop and compare with classical ROI-based approach, a fully-automatic, local and unbiased way of studying the knee T1ρ relaxation time by creating an atlas and using Voxel Based Relaxometry (VBR) in OA and ACL subjects Materials and Methods In this study 110 subjects from 2 cohorts: (i) Mild OA 40 patients with mild-OA KL ≤ 2 and 15 controls KL ≤ 1; (ii) ACL cohort (a model for early OA): 40 ACL-injured patients imaged prior to ACL reconstruction and 1-year post-surgery and 15 controls are analyzed. All the subjects were acquired at 3T with a protocol that includes: 3D-FSE (CUBE) and 3D-T1ρ. A Non-rigid registration technique was applied to align all the images on a single template. This allows for performing VBR to assess local statistical differences of T1ρ values using z-score analysis. VBR results are compared with those obtained with classical ROI-based technique Results ROI-based results from atlas-based segmentation were consistent with classical ROI-based method (CV = 3.83%). Voxel-based group analysis revealed local patterns that were overlooked by ROI-based approach; e.g. VBR showed posterior lateral femur and posterior lateral tibia significant T1ρ elevations in ACL injured patients (sample mean z-score=9.7 and 10.3). Those elevations were overlooked by the classical ROI-based approach (sample mean z-score =1.87, and −1.73) Conclusion VBR is a feasible and accurate tool for the local evaluation of the biochemical composition of knee articular cartilage. VBR is capable of detecting specific local patterns on T1ρ maps in OA and ACL subjects

show abstract

“…Future application of mean thickness and surface roughness to simultaneously characterize whole‐compartment and sub‐regional changes may enable earlier quantification of OA changes than currently possible. In addition, the geometric consistency of mesh parameterization mapping could enable future atlas‐based sub‐compartmental segmentation, improving repeatability and consistency.…”

Section: Discussionmentioning

confidence: 99%

Articular cartilage surface roughness as an imaging‐based morphological indicator of osteoarthritis: A preliminary investigation of osteoarthritis initiative subjects

Newton

Osborne

Gawronski

et al. 2017

Journal Orthopaedic Research

View full text Add to dashboard Cite

Current imaging-based morphometric indicators of osteoarthritis (OA) using whole-compartment mean cartilage thickness (MCT) and volume changes can be insensitive to mild degenerative changes of articular cartilage (AC) due to areas of adjacent thickening and thinning. The purpose of this preliminary study was to evaluate cartilage thickness-based surface roughness as a morphometric indicator of OA. 3D magnetic resonance imaging (MRI) datasets were collected from osteoarthritis initiative (OAI) subjects with Kellgren-Lawrence (KL) OA grades of 0, 2, and 4 (n = 10/group). Femoral and tibial AC volumes were converted to two-dimensional thickness maps, and MCT, arithmetic surface roughness (S ), and anatomically normalized S (normS ) were calculated. Thickness maps enabled visualization of degenerative changes with increasing KL grade, including adjacent thinning and thickening on the femoral condyles. No significant differences were observed in MCT between KL grades. S was significantly higher in KL4 compared to KL0 and KL2 in the whole femur (KL0: 0.55 ± 0.10 mm, KL2: 0.53 ± 0.09 mm, KL4: 0.79 ± 0.18 mm), medial femoral condyle (KL0: 0.42 ± 0.07 mm, KL2: 0.48 ± 0.07 mm, KL4: 0.76 ± 0.22 mm), and medial tibial plateau (KL0: 0.42 ± 0.07 mm, KL2: 0.43 ± 0.09 mm, KL4: 0.68 ± 0.27 mm). normS was significantly higher in KL4 compared to KL0 and KL2 in the whole femur (KL0: 0.22 ± 0.02, KL2: 0.22 ± 0.02, KL4: 0.30 ± 0.03), medial condyle (KL0: 0.17 ± 0.02, KL2: 0.20 ± 0.03, KL4: 0.29 ± 0.06), whole tibia (KL0: 0.34 ± 0.04, KL2: 0.33 ± 0.05, KL4: 0.48 ± 0.11) and medial plateau (KL0: 0.23 ± 0.03, KL2: 0.24 ± 0.04, KL4: 0.40 ± 0.10), and significantly higher in KL2 compared to KL0 in the medial femoral condyle. Surface roughness metrics were sensitive to degenerative morphologic changes, and may be useful in OA characterization and early diagnosis. © 2017 Orthopaedic Research Society. Published by Wiley Periodicals, Inc. J Orthop Res 35:2755-2764, 2017.

show abstract

Automatic atlas-based three-label cartilage segmentation from MR knee images

Cited by 27 publications

References 9 publications

SUSAN: segment unannotated image structure using adversarial network

SUSAN: segment unannotated image structure using adversarial network

Fully automatic analysis of the knee articular cartilageT_1ρrelaxation time using voxel-based relaxometry

Articular cartilage surface roughness as an imaging‐based morphological indicator of osteoarthritis: A preliminary investigation of osteoarthritis initiative subjects

Contact Info

Product

Resources

About

Automatic atlas-based three-label cartilage segmentation from MR knee images

Cited by 27 publications

References 9 publications

SUSAN: segment unannotated image structure using adversarial network

SUSAN: segment unannotated image structure using adversarial network

Fully automatic analysis of the knee articular cartilageT1ρrelaxation time using voxel-based relaxometry

Articular cartilage surface roughness as an imaging‐based morphological indicator of osteoarthritis: A preliminary investigation of osteoarthritis initiative subjects

Contact Info

Product

Resources

About

Fully automatic analysis of the knee articular cartilageT_1ρrelaxation time using voxel-based relaxometry