1
|
Sultana J, Naznin M, Faisal TR. SSDL-an automated semi-supervised deep learning approach for patient-specific 3D reconstruction of proximal femur from QCT images. Med Biol Eng Comput 2024; 62:1409-1425. [PMID: 38217823 DOI: 10.1007/s11517-023-03013-8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/25/2023] [Accepted: 12/27/2023] [Indexed: 01/15/2024]
Abstract
Deep Learning (DL) techniques have recently been used in medical image segmentation and the reconstruction of 3D anatomies of a human body. In this work, we propose a semi-supervised DL (SSDL) approach utilizing a CNN-based 3D U-Net model for femur segmentation from sparsely annotated quantitative computed tomography (QCT) slices. Specifically, QCT slices at the proximal end of the femur forming ball and socket joint with acetabulum were annotated for precise segmentation, where a segmenting binary mask was generated using a 3D U-Net model to segment the femur accurately. A total of 5474 QCT slices were considered for training among which 2316 slices were annotated. 3D femurs were further reconstructed from segmented slices employing polynomial spline interpolation. Both qualitative and quantitative performance of segmentation and 3D reconstruction were satisfactory with more than 90% accuracy achieved for all of the standard performance metrics considered. The spatial overlap index and reproducibility validation metric for segmentation-Dice Similarity Coefficient was 91.8% for unseen patients and 99.2% for validated patients. An average relative error of 12.02% and 10.75% for volume and surface area, respectively, were computed for 3D reconstructed femurs. The proposed approach demonstrates its effectiveness in accurately segmenting and reconstructing 3D femur from QCT slices.
Collapse
Affiliation(s)
- Jamalia Sultana
- Department of Computer Science and Engineering, Bangladesh University of Engineering and Technology, Dhaka, Bangladesh
| | - Mahmuda Naznin
- Department of Computer Science and Engineering, Bangladesh University of Engineering and Technology, Dhaka, Bangladesh
| | - Tanvir R Faisal
- Department of Mechanical Engineering, University of Louisiana at Lafayette, Lafayette, LA, 70503, USA.
| |
Collapse
|
2
|
Lattanzi R. Methods for the Clinical Translation of Quantitative MRI for the Evaluation of Patients With Femoroacetabular Impingement. HSS J 2023; 19:442-446. [PMID: 37937089 PMCID: PMC10626928 DOI: 10.1177/15563316231193404] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Key Words] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 06/21/2023] [Accepted: 07/17/2023] [Indexed: 11/09/2023]
Affiliation(s)
- Riccardo Lattanzi
- Center for Advanced Imaging Innovation and Research (CAIR) and Bernard and Irene Schwartz Center for Biomedical Imaging, Department of Radiology, New York University Grossman School of Medicine, New York, NY, USA
| |
Collapse
|
3
|
Zhou H, Jia H, Lei G, Zhou T, Wu J, Chang Y, Wang L, Sheng M, Yang X. Quantitative assessment of normal hip cartilage in children under 9 years old by T2 mapping. MAGMA (NEW YORK, N.Y.) 2022; 35:459-466. [PMID: 34652541 DOI: 10.1007/s10334-021-00962-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 05/31/2021] [Revised: 09/19/2021] [Accepted: 09/21/2021] [Indexed: 06/13/2023]
Abstract
OBJECTIVE To investigate the variation in T2 at different zones of normal hip cartilage in children and the relationship between T2 value and age. MATERIALS AND METHODS Nineteen children with 30 normal hip joints were evaluated with a coronal T2 mapping sequence at a 3-Tesla MRI system. The femoral cartilage and acetabular cartilage were firstly segmented by mask-based interactive method and then equally divided into eight and six radial sections, respectively. Moreover, each radial section was further divided into two layers referring to the superficial and deep halves of the corresponding cartilage. Cartilage T2 of these sections and layers were measured and subsequently analyzed. RESULTS There was a negative correlation between the T2 values in the hip cartilage and the age of children (rs < - 0.6, P1 < 0.05). Articular cartilage T2 increased at angles close to the magic angle (54.7°). Femoral cartilage and acetabular cartilage had a relatively shorter T2 in the radial sections near the vertex of the femoral head. The T2 values in superficial layers of both cartilages were significantly higher than those in deep layers (P < 0.05). CONCLUSION The T2 value decreases as the cartilage developing into a more mature state. Cartilage T2 values in the weight-bearing areas are relatively low due to an increase of collagen density and the loss of interstitial water. The restriction of the water molecules by solid components in the deeper layer of cartilage may decrease the T2 values.
Collapse
Affiliation(s)
- Hongyan Zhou
- School of Medical Imaging, Xuzhou Medical University, Xuzhou, 221004, China
- Suzhou Institute of Biomedical Engineering and Technology, Chinese Academy of Sciences, Suzhou, 215163, China
| | - Huihui Jia
- Department of Radiology, Children's Hospital of Soochow University, Suzhou, 215025, China
| | - Gege Lei
- School of Electronic Engineering and Optoelectronic Technology, Nanjing University of Science and Technology, Nanjing, 210094, China
| | - Tianli Zhou
- School of Medical Imaging, Xuzhou Medical University, Xuzhou, 221004, China
- Suzhou Institute of Biomedical Engineering and Technology, Chinese Academy of Sciences, Suzhou, 215163, China
| | - Jizhi Wu
- Department of Radiology, Children's Hospital of Soochow University, Suzhou, 215025, China
| | - Yan Chang
- Suzhou Institute of Biomedical Engineering and Technology, Chinese Academy of Sciences, Suzhou, 215163, China
| | - Lei Wang
- School of Ophthalmology and Optometry, Eye Hospital of Wenzhou Medical University, Wenzhou, 325027, China
| | - Mao Sheng
- Department of Radiology, Children's Hospital of Soochow University, Suzhou, 215025, China.
| | - Xiaodong Yang
- School of Medical Imaging, Xuzhou Medical University, Xuzhou, 221004, China.
- Suzhou Institute of Biomedical Engineering and Technology, Chinese Academy of Sciences, Suzhou, 215163, China.
| |
Collapse
|
4
|
Yang M, Colak C, Chundru KK, Gaj S, Nanavati A, Jones MH, Winalski CS, Subhas N, Li X. Automated knee cartilage segmentation for heterogeneous clinical MRI using generative adversarial networks with transfer learning. Quant Imaging Med Surg 2022; 12:2620-2633. [PMID: 35502381 PMCID: PMC9014147 DOI: 10.21037/qims-21-459] [Citation(s) in RCA: 10] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/01/2021] [Accepted: 10/26/2021] [Indexed: 08/27/2023]
Abstract
BACKGROUND This study aimed to build a deep learning model to automatically segment heterogeneous clinical MRI scans by optimizing a pre-trained model built from a homogeneous research dataset with transfer learning. METHODS Conditional generative adversarial networks pretrained on the Osteoarthritis Initiative MR images was transferred to 30 sets of heterogenous MR images collected from clinical routines. Two trained radiologists manually segmented the 30 sets of clinical MR images for model training, validation and test. The model performance was compared to models trained from scratch with different datasets, as well as two radiologists. A 5-fold cross validation was performed. RESULTS The transfer learning model obtained an overall averaged Dice coefficient of 0.819, an averaged 95 percentile Hausdorff distance of 1.463 mm, and an averaged average symmetric surface distance of 0.350 mm on the 5 random holdout test sets. A 5-fold cross validation had a mean Dice coefficient of 0.801, mean 95 percentile Hausdorff distance of 1.746 mm, and mean average symmetric surface distance of 0.364 mm. It outperformed other models and performed similarly as the radiologists. CONCLUSIONS A transfer learning model was able to automatically segment knee cartilage, with performance comparable to human, using heterogeneous clinical MR images with a small training data size. In addition, the model proved robust when tested through cross validation and on images from a different vendor. We found it feasible to perform fully automated cartilage segmentation of clinical knee MR images, which would facilitate the clinical application of quantitative MRI techniques and other prediction models for improved patient treatment planning.
Collapse
Affiliation(s)
- Mingrui Yang
- Department of Biomedical Engineering, Lerner Research Institute, Cleveland Clinic, Cleveland, OH, USA
- Program of Advanced Musculoskeletal Imaging (PAMI), Cleveland Clinic, Cleveland, OH, USA
| | - Ceylan Colak
- Department of Diagnostic Radiology, Imaging Institute, Cleveland Clinic, Cleveland, OH, USA
| | - Kishore K. Chundru
- Department of Diagnostic Radiology, Imaging Institute, Cleveland Clinic, Cleveland, OH, USA
| | - Sibaji Gaj
- Department of Biomedical Engineering, Lerner Research Institute, Cleveland Clinic, Cleveland, OH, USA
- Program of Advanced Musculoskeletal Imaging (PAMI), Cleveland Clinic, Cleveland, OH, USA
| | - Andreas Nanavati
- Department of Biomedical Engineering, Lerner Research Institute, Cleveland Clinic, Cleveland, OH, USA
- Program of Advanced Musculoskeletal Imaging (PAMI), Cleveland Clinic, Cleveland, OH, USA
| | - Morgan H. Jones
- Department of Orthopaedic Surgery, Brigham and Women’s Hospital, Boston, MA, USA
| | - Carl S. Winalski
- Department of Biomedical Engineering, Lerner Research Institute, Cleveland Clinic, Cleveland, OH, USA
- Program of Advanced Musculoskeletal Imaging (PAMI), Cleveland Clinic, Cleveland, OH, USA
- Department of Diagnostic Radiology, Imaging Institute, Cleveland Clinic, Cleveland, OH, USA
| | - Naveen Subhas
- Program of Advanced Musculoskeletal Imaging (PAMI), Cleveland Clinic, Cleveland, OH, USA
- Department of Diagnostic Radiology, Imaging Institute, Cleveland Clinic, Cleveland, OH, USA
| | - Xiaojuan Li
- Department of Biomedical Engineering, Lerner Research Institute, Cleveland Clinic, Cleveland, OH, USA
- Program of Advanced Musculoskeletal Imaging (PAMI), Cleveland Clinic, Cleveland, OH, USA
- Department of Diagnostic Radiology, Imaging Institute, Cleveland Clinic, Cleveland, OH, USA
| |
Collapse
|
5
|
Bekkouch IEI, Maksudov B, Kiselev S, Mustafaev T, Vrtovec T, Ibragimov B. Multi-landmark environment analysis with reinforcement learning for pelvic abnormality detection and quantification. Med Image Anal 2022; 78:102417. [PMID: 35325712 DOI: 10.1016/j.media.2022.102417] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/09/2021] [Revised: 01/14/2022] [Accepted: 03/03/2022] [Indexed: 12/22/2022]
Abstract
Morphological abnormalities of the femoroacetabular (hip) joint are among the most common human musculoskeletal disorders and often develop asymptomatically at early easily treatable stages. In this paper, we propose an automated framework for landmark-based detection and quantification of hip abnormalities from magnetic resonance (MR) images. The framework relies on a novel idea of multi-landmark environment analysis with reinforcement learning. In particular, we merge the concepts of the graphical lasso and Morris sensitivity analysis with deep neural networks to quantitatively estimate the contribution of individual landmark and landmark subgroup locations to the other landmark locations. Convolutional neural networks for image segmentation are utilized to propose the initial landmark locations, and landmark detection is then formulated as a reinforcement learning (RL) problem, where each landmark-agent can adjust its position by observing the local MR image neighborhood and the locations of the most-contributive landmarks. The framework was validated on T1-, T2- and proton density-weighted MR images of 260 patients with the aim to measure the lateral center-edge angle (LCEA), femoral neck-shaft angle (NSA), and the anterior and posterior acetabular sector angles (AASA and PASA) of the hip, and derive the quantitative abnormality metrics from these angles. The framework was successfully tested using the UNet and feature pyramid network (FPN) segmentation architectures for landmark proposal generation, and the deep Q-network (DeepQN), deep deterministic policy gradient (DDPG), twin delayed deep deterministic policy gradient (TD3), and actor-critic policy gradient (A2C) RL networks for landmark position optimization. The resulting overall landmark detection error of 1.5 mm and angle measurement error of 1.4° indicates a superior performance in comparison to existing methods. Moreover, the automatically estimated abnormality labels were in 95% agreement with those generated by an expert radiologist.
Collapse
Affiliation(s)
- Imad Eddine Ibrahim Bekkouch
- Sorbonne Center for Artificial Intelligence, Sorbonne University, Paris, France; Institute of Data Science and Artificial Intelligence, Innopolis University, Innopolis, Russia
| | - Bulat Maksudov
- Institute of Data Science and Artificial Intelligence, Innopolis University, Innopolis, Russia; Department of Computer Science, University College Dublin, Dublin, Ireland
| | - Semen Kiselev
- Institute of Data Science and Artificial Intelligence, Innopolis University, Innopolis, Russia
| | - Tamerlan Mustafaev
- Institute of Data Science and Artificial Intelligence, Innopolis University, Innopolis, Russia; Public Hospital #2, Department of Radiology, Kazan, Russia
| | - Tomaž Vrtovec
- Faculty of Electrical Engineering, University of Ljubljana, Ljubljana, Slovenia
| | - Bulat Ibragimov
- Faculty of Electrical Engineering, University of Ljubljana, Ljubljana, Slovenia; Department of Computer Science, University of Copenhagen, Copenhagen, Denmark.
| |
Collapse
|
6
|
Entropy and distance maps-guided segmentation of articular cartilage: data from the Osteoarthritis Initiative. Int J Comput Assist Radiol Surg 2022; 17:553-560. [PMID: 34988758 DOI: 10.1007/s11548-021-02555-2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/10/2021] [Accepted: 12/22/2021] [Indexed: 11/05/2022]
Abstract
PURPOSE Accurate segmentation of articular cartilage from MR images is crucial for quantitative investigation of pathoanatomical conditions such as osteoarthritis (OA). Recently, deep learning-based methods have made significant progress in hard tissue segmentation. However, it remains a challenge to develop accurate methods for automatic segmentation of articular cartilage. METHODS We propose a two-stage method for automatic segmentation of articular cartilage. At the first stage, nnU-Net is employed to get segmentation of both hard tissues and articular cartilage. Based on the initial segmentation, we compute distance maps as well as entropy maps, which encode the uncertainty information about the initial cartilage segmentation. At the second stage, both distance maps and entropy maps are concatenated to the original image. We then crop a sub-volume around the cartilage region based on the initial segmentation, which is used as the input to another nnU-Net for segmentation refinement. RESULTS We designed and conducted comprehensive experiments on segmenting three different types of articular cartilage from two datasets, i.e., an in-house dataset consisting of 25 hip MR images and a publicly available dataset from Osteoarthritis Initiative (OAI). Our method achieved an average Dice similarity coefficient (DSC) of [Formula: see text] for the combined hip cartilage, [Formula: see text] for the femoral cartilage and [Formula: see text] for the tibial cartilage, respectively. CONCLUSION In summary, we developed a new approach for automatic segmentation of articular cartilage from MR images. Comprehensive experiments conducted on segmenting articular cartilage of the knee and hip joints demonstrated the efficacy of the present approach. Our method achieved equivalent or better results than the state-of-the-art methods.
Collapse
|
7
|
Juras V, Szomolanyi P, Schreiner MM, Unterberger K, Kurekova A, Hager B, Laurent D, Raithel E, Meyer H, Trattnig S. Reproducibility of an Automated Quantitative MRI Assessment of Low-Grade Knee Articular Cartilage Lesions. Cartilage 2021; 13:646S-657S. [PMID: 32988236 PMCID: PMC8808824 DOI: 10.1177/1947603520961165] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 12/02/2022] Open
Abstract
OBJECTIVE The goal of this study was to assess the reproducibility of an automated knee cartilage segmentation of 21 cartilage regions with a model-based algorithm and to compare the results with manual segmentation. DESIGN Thirteen patients with low-grade femoral cartilage defects were included in the study and were scanned twice on a 7-T magnetic resonance imaging (MRI) scanner 8 days apart. A 3-dimensional double-echo steady-state (3D-DESS) sequence was used to acquire MR images for automated cartilage segmentation, and T2-mapping was performed using a 3D triple-echo steady-state (3D-TESS) sequence. Cartilage volume, thickness, and T2 and texture features were automatically extracted from each knee for each of the 21 subregions. DESS was used for manual cartilage segmentation and compared with automated segmentation using the Dice coefficient. The reproducibility of each variable was expressed using standard error of measurement (SEM) and smallest detectable change (SDC). RESULTS The Dice coefficient for the similarity between manual and automated segmentation ranged from 0.83 to 0.88 in different cartilage regions. Test-retest analysis of automated cartilage segmentation and automated quantitative parameter extraction revealed excellent reproducibility for volume measurement (mean SDC for all subregions of 85.6 mm3), for thickness detection (SDC = 0.16 mm) and also for T2 values (SDC = 2.38 ms) and most gray-level co-occurrence matrix features (SDC = 0.1 a.u.). CONCLUSIONS The proposed technique of automated knee cartilage evaluation based on the segmentation of 3D MR images and correlation with T2 mapping provides highly reproducible results and significantly reduces the segmentation effort required for the analysis of knee articular cartilage in longitudinal studies.
Collapse
Affiliation(s)
- Vladimir Juras
- High-Field MR Centre, Department of
Biomedical Imaging and Image-Guided Therapy, Medical University of Vienna, Vienna,
Austria,Institute of Measurement Science, Slovak
Academy of Sciences, Bratislava, Slovakia,Vladimir Juras, High-Field MR Centre,
Department of Biomedical Imaging and Image-Guided Therapy, Medical University of
Vienna, Waehringer Guertel 18-20, Vienna, 1090, Austria.
| | - Pavol Szomolanyi
- High-Field MR Centre, Department of
Biomedical Imaging and Image-Guided Therapy, Medical University of Vienna, Vienna,
Austria,Institute of Measurement Science, Slovak
Academy of Sciences, Bratislava, Slovakia
| | - Markus M. Schreiner
- Department of Orthopedics and Trauma
Surgery, Medical University of Vienna, Vienna, Austria
| | - Karin Unterberger
- Department of Orthopedics and Trauma
Surgery, Medical University of Vienna, Vienna, Austria
| | - Andrea Kurekova
- High-Field MR Centre, Department of
Biomedical Imaging and Image-Guided Therapy, Medical University of Vienna, Vienna,
Austria
| | - Benedikt Hager
- High-Field MR Centre, Department of
Biomedical Imaging and Image-Guided Therapy, Medical University of Vienna, Vienna,
Austria,CD Laboratory for Clinical Molecular MR
Imaging, Vienna, Austria
| | - Didier Laurent
- Novartis Institutes for Biomedical
Research, Department of Translational Medicine, Basel, Switzerland
| | | | | | - Siegfried Trattnig
- High-Field MR Centre, Department of
Biomedical Imaging and Image-Guided Therapy, Medical University of Vienna, Vienna,
Austria,CD Laboratory for Clinical Molecular MR
Imaging, Vienna, Austria,Austrian Cluster for Tissue
Regeneration, Vienna, Austria
| |
Collapse
|
8
|
Bugeja JM, Chandra SS, Neubert A, Fripp J, Lockard CA, Ho CP, Crozier S, Engstrom C. Automated analysis of immediate reliability of T2 and T2* relaxation times of hip joint cartilage from 3 T MR examinations. Magn Reson Imaging 2021; 82:42-54. [PMID: 34147595 DOI: 10.1016/j.mri.2021.06.008] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/18/2020] [Revised: 03/31/2021] [Accepted: 06/15/2021] [Indexed: 10/21/2022]
Abstract
BACKGROUND Magnetic resonance (MR) T2 and T2* mapping sequences allow in vivo quantification of biochemical characteristics within joint cartilage of relevance to clinical assessment of conditions such as hip osteoarthritis (OA). PURPOSE To evaluate an automated immediate reliability analysis of T2 and T2* mapping from MR examinations of hip joint cartilage using a bone and cartilage segmentation pipeline based around focused shape modelling. STUDY TYPE Technical validation. SUBJECTS 17 asymptomatic volunteers (M: F 7:10, aged 22-47 years, mass 50-90 kg, height 163-189 cm) underwent unilateral hip joint MR examinations. Automated analysis of cartilage T2 and T2* data immediate reliability was evaluated in 9 subjects (M: F 4: 5) for each sequence. FIELD STRENGTH/SEQUENCE A 3 T MR system with a body matrix flex-coil was used to acquire images with the following sequences: T2 weighted 3D-trueFast Imaging with Steady-State Precession (water excitation; 10.18 ms repetition time (TR); 4.3 ms echo time (TE); Voxel Size (VS): 0.625 × 0.625 × 0.65 mm; 160 mm field of view (FOV); Flip Angle (FA): 30 degrees; Pixel Bandwidth (PB): 140 Hz/pixel); a multi-echo spin echo (MESE) T2 mapping sequence (TR/TE: 2080/18-90 ms (5 echoes); VS: 4 × 0.78 × 0.78 mm; FOV: 200 mm; FA: 180 degrees; PB: 230 Hz/pixel) and a MESE T2* mapping sequence (TR/TE: 873/3.82-19.1 ms (5 echoes); VS: 3 × 0.625 × 0.625 mm; FOV: 160 mm; FA: 25 degrees; PB: 250 Hz/pixel). ASSESSMENT Automated cartilage segmentation and quantitative analysis provided T2 and T2* data from test-retest MR examinations to assess immediate reliability. STATISTICAL TESTS Coefficient of variation (CV) and intraclass correlations (ICC2, 1) to analyse automated T2 and T2* mapping reliability focusing on the clinically important superior cartilage regions of the hip joint. RESULTS Comparisons between test-retest T2 and (T2*) data revealed mean CV's of 3.385% (1.25%), mean ICC2, 1's of 0.871 (0.984) and median mean differences of -1.139ms (+0.195ms). CONCLUSION The T2 and T2* times from automated analyses of hip cartilage from test-retest MR examinations had high (T2) and excellent (T2*) immediate reliability.
Collapse
Affiliation(s)
- Jessica M Bugeja
- School of Information Technology and Electrical Engineering, The University of Queensland, Australia; Australian e-Health Research Centre, CSIRO, Australia.
| | - Shekhar S Chandra
- School of Information Technology and Electrical Engineering, The University of Queensland, Australia.
| | - Aleš Neubert
- School of Information Technology and Electrical Engineering, The University of Queensland, Australia; Australian e-Health Research Centre, CSIRO, Australia.
| | - Jurgen Fripp
- Australian e-Health Research Centre, CSIRO, Australia.
| | - Carly A Lockard
- Imaging Research Department, Steadman Philippon Research Institute, USA.
| | - Charles P Ho
- Imaging Research Department, Steadman Philippon Research Institute, USA.
| | - Stuart Crozier
- School of Information Technology and Electrical Engineering, The University of Queensland, Australia.
| | - Craig Engstrom
- School of Human Movement Studies, The University of Queensland, Australia.
| |
Collapse
|
9
|
Li M, Venäläinen MS, Chandra SS, Patel R, Fripp J, Engstrom C, Korhonen RK, Töyräs J, Crozier S. Discrete element and finite element methods provide similar estimations for hip joint contact mechanics during walking gait. J Biomech 2020; 115:110163. [PMID: 33338974 DOI: 10.1016/j.jbiomech.2020.110163] [Citation(s) in RCA: 6] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/07/2020] [Revised: 11/07/2020] [Accepted: 11/25/2020] [Indexed: 12/13/2022]
Abstract
Finite element analysis (FEA) provides a powerful approach for estimating the in-vivo loading characteristics of the hip joint during various locomotory and functional activities. However, time-consuming procedures, such as the generation of high-quality FE meshes and setup of FE simulation, typically make the method impractical for rapid applications which could be used in clinical routine. Alternatively, discrete element analysis (DEA) has been developed to quantify mechanical conditions of the hip joint in a fraction of time compared to FEA. Although DEA has proven effective in the estimation of contact stresses and areas in various complex applications, it has not yet been well characterised by its ability to evaluate contact mechanics for the hip joint during gait cycle loading using data from several individuals. The objective of this work was to compare DEA modelling against well-established FEA for analysing contact mechanics of the hip joint during walking gait. Subject-specific models were generated from magnetic resonance images of the hip joints in five asymptomatic subjects. The DEA and FEA models were then simulated for 13 loading time-points extracted from a full gait cycle. Computationally, DEA was substantially more efficient compared to FEA (simulation times of seconds vs. hours). The DEA and FEA methods had similar predictions for contact pressure distribution for the hip joint during normal walking. In all 13 simulated loading time-points across five subjects, the maximum difference in average contact pressures between DEA and FEA was within ±0.06 MPa. Furthermore, the difference in contact area ratio computed using DEA and FEA was less than ±6%.
Collapse
Affiliation(s)
- Mao Li
- School of Information Technology and Electrical Engineering, University of Queensland, Brisbane, Australia
| | - Mikko S Venäläinen
- School of Information Technology and Electrical Engineering, University of Queensland, Brisbane, Australia; Turku Bioscience Centre, University of Turku and Åbo Akademi University, Turku, Finland.
| | - Shekhar S Chandra
- School of Information Technology and Electrical Engineering, University of Queensland, Brisbane, Australia
| | - Rushabh Patel
- School of Mechanical and Mining Engineering, University of Queensland, Brisbane, Australia
| | - Jurgen Fripp
- School of Information Technology and Electrical Engineering, University of Queensland, Brisbane, Australia; The Australian e-Health Research Centre, CSIRO Health and Biosecurity, Brisbane, Australia
| | - Craig Engstrom
- School of Human Movement Studies, University of Queensland, Brisbane, Australia
| | - Rami K Korhonen
- Department of Applied Physics, University of Eastern Finland, Kuopio, Finland
| | - Juha Töyräs
- School of Information Technology and Electrical Engineering, University of Queensland, Brisbane, Australia; Department of Applied Physics, University of Eastern Finland, Kuopio, Finland; Diagnostic Imaging Centre, Kuopio University Hospital, Kuopio, Finland
| | - Stuart Crozier
- School of Information Technology and Electrical Engineering, University of Queensland, Brisbane, Australia
| |
Collapse
|
10
|
Machine learning methods to support personalized neuromusculoskeletal modelling. Biomech Model Mechanobiol 2020; 19:1169-1185. [DOI: 10.1007/s10237-020-01367-8] [Citation(s) in RCA: 15] [Impact Index Per Article: 3.8] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/22/2020] [Accepted: 07/08/2020] [Indexed: 12/19/2022]
|
11
|
Hesper T, Bittersohl B, Schleich C, Hosalkar H, Krauspe R, Krekel P, Zilkens C. Automatic Cartilage Segmentation for Delayed Gadolinium-Enhanced Magnetic Resonance Imaging of Hip Joint Cartilage: A Feasibility Study. Cartilage 2020; 11:32-37. [PMID: 29926743 PMCID: PMC6921955 DOI: 10.1177/1947603518783481] [Citation(s) in RCA: 7] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 02/03/2023] Open
Abstract
OBJECTIVE Automatic segmentation for biochemical cartilage evaluation holds promise for an efficient and reader-independent analysis. This pilot study aims to investigate the feasibility and to compare delayed gadolinium-enhanced magnetic resonance imaging of cartilage (dGEMRIC) hip joint assessment with manual segmentation of acetabular and femoral head cartilage and dGEMRIC hip joint assessment using automatic surface and volume processing software at 3 Tesla. DESIGN Three-dimensional (3D) dGEMRIC data sets of 6 patients with hip-related pathology were assessed (1) manually including multiplanar image reformatting and regions of interest (ROI) analysis and (2) automated by using a combined surface and volume processing software. For both techniques, T1Gd values were obtained in acetabular and femoral head cartilage at 7 regions (anterior, anterior-superior, superior-anterior, superior, superior-posterior, posterior-superior, and posterior) in central and peripheral portions. Correlation between both techniques was calculated utilizing Spearman's rank correlation coefficient. RESULTS A high correlation between both techniques was observed for acetabular (ρ = 0.897; P < 0.001) and femoral head (ρ = 0.894; P < 0.001) cartilage in all analyzed regions of the hip joint (ρ between 0.755 and 0.955; P < 0.001). CONCLUSIONS Automatic cartilage segmentation with dGEMRIC assessment for hip joint cartilage evaluation seems feasible providing high to excellent correlation with manually performed ROI analysis. This technique is feasible for an objective, reader-independant and reliable assessment of biochemical cartilage status.
Collapse
Affiliation(s)
- Tobias Hesper
- Department of Orthopedics, Medical
Faculty, University of Düsseldorf, Düsseldorf, Germany
| | - Bernd Bittersohl
- Department of Orthopedics, Medical
Faculty, University of Düsseldorf, Düsseldorf, Germany,Bernd Bittersohl, Department of Orthopedics,
Heinrich-Heine University, Düsseldorf, Moorenstr. 5, 40225 Düsseldorf, Germany.
| | - Christoph Schleich
- Department of Diagnostic and
Interventional Radiology, Medical Faculty, University of Düsseldorf, Düsseldorf,
Germany
| | - Harish Hosalkar
- Paradise Valley Hospital, San Diego, CA,
USA,Tri-city Medical Center, San Diego, CA,
USA
| | - Rüdiger Krauspe
- Department of Orthopedics, Medical
Faculty, University of Düsseldorf, Düsseldorf, Germany
| | | | - Christoph Zilkens
- Department of Orthopedics, Medical
Faculty, University of Düsseldorf, Düsseldorf, Germany
| |
Collapse
|
12
|
Holistic decomposition convolution for effective semantic segmentation of medical volume images. Med Image Anal 2019; 57:149-164. [DOI: 10.1016/j.media.2019.07.003] [Citation(s) in RCA: 15] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/24/2018] [Revised: 05/22/2019] [Accepted: 07/04/2019] [Indexed: 11/24/2022]
|
13
|
Liu H, Dai G, Pu F. Hip-Joint CT Image Segmentation Based on Hidden Markov Model with Gauss Regression Constraints. J Med Syst 2019; 43:309. [PMID: 31446505 DOI: 10.1007/s10916-019-1439-6] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.2] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/13/2019] [Accepted: 08/20/2019] [Indexed: 11/24/2022]
Abstract
Hip-joint CT images have low organizational contrast, irregular shape of boundaries and image noises. Traditional segmentation algorithms often require manual intervention or introduction of some prior information, which results in low efficiency and is unable to meet clinical needs. In order to overcome the sensitivity of classical fuzzy clustering image segmentation algorithm to image noise, this paper proposes a fuzzy clustering image segmentation algorithm combining Gaussian regression model (GRM) and hidden Markov random field (HMRF). The algorithm uses the prior information to regularize the objective function of the fuzzy C-means, and then improves it with KL information. The HMRF model establishes the neighborhood relationship of the label field by prior probability, while CRM model establishes the neighborhood relationship of feature field on the basis of the consistency between the central pixel label and its neighborhood pixel label. The experimental results show that the proposed algorithm has high segmentation accuracy.
Collapse
Affiliation(s)
- Haiyang Liu
- Department of Radiology, Shangluo Central Hospital, Shangluo, 726000, Shaanxi, China
| | - Guochao Dai
- Image Center of the First People's Hospital of Kashgar, Kashgar, Xinjiang, 844000, China
| | - Fushun Pu
- Southern Central Hospital of Yunnan Province (The First People's Hospital of Honghe State), Mengzi, 661199, Yunnan, China.
| |
Collapse
|
14
|
Petersen J, Arias-Lorza AM, Selvan R, Bos D, van der Lugt A, Pedersen JH, Nielsen M, de Bruijne M. Increasing Accuracy of Optimal Surfaces Using Min-Marginal Energies. IEEE TRANSACTIONS ON MEDICAL IMAGING 2019; 38:1559-1568. [PMID: 30605096 DOI: 10.1109/tmi.2018.2890386] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.2] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/09/2023]
Abstract
Optimal surface methods are a class of graph cut methods posing surface estimation as an n-ary ordered labeling problem. They are used in medical imaging to find interacting and layered surfaces optimally and in low order polynomial time. Representing continuous surfaces with discrete sets of labels, however, leads to discretization errors and, if graph representations are made dense, excessive memory usage. Limiting memory usage and computation time of graph cut methods are important and graphs that locally adapt to the problem has been proposed as a solution. Min-marginal energies computed using dynamic graph cuts offer a way to estimate solution uncertainty and these uncertainties have been used to decide where graphs should be adapted. Adaptive graphs, however, introduce extra parameters, complexity, and heuristics. We propose a way to use min-marginal energies to estimate continuous solution labels that does not introduce extra parameters and show empirically on synthetic and medical imaging datasets that it leads to improved accuracy. The increase in accuracy was consistent and in many cases comparable with accuracy otherwise obtained with graphs up to eight times denser, but with proportionally less memory usage and improvements in computation time.
Collapse
|
15
|
Yan K, Xi Y, Sasiponganan C, Zerr J, Wells JE, Chhabra A. Does 3DMR provide equivalent information as 3DCT for the pre-operative evaluation of adult Hip pain conditions of femoroacetabular impingement and Hip dysplasia? Br J Radiol 2018; 91:20180474. [PMID: 30048144 DOI: 10.1259/bjr.20180474] [Citation(s) in RCA: 8] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/12/2022] Open
Abstract
OBJECTIVE: Femoroacetabular impingement (FAI) and hip dysplasia (HD) are frequently evaluated by isotropic CT (3DCT) for preoperative planning at the expense of radiation. The aim was to determine if isotropic MRI (3DMR) imaging can provide similar quantitative and qualitative morphological information as 3DCT. METHODS: 25 consecutive patients with a final diagnosis of FAI or HD were retrospectively selected from December 2016-December 2017. Two readers (R1, R2) performed quantitative angular measurements on 3DCT and 3DMR, blinded to the diagnosis and each other's measurements. 3DMR and 3DCT of the hips were qualitatively and independently evaluated by a radiologist (R3), surgeon (R4), and fellow (R5). Interobserver and intermodality comparisons were performed. RESULTS: The ICC was good to excellent for all measurements between R1 and R2 (ICC:0.60-0.98) and the majority of intermodality measurements for R1 and R2. Average inter-reader and inter-modality PABAK showed good to excellent agreement for qualitative reads. On CT, all alpha angles (AA) were significantly lower in dysplasia patients than in cam patients (p < 0.05). All lateral center-edge angle (LCEA) were significantly lower in dysplasia than in cam patients (p < 0.05). On MR, AA at 12, 1, and 2 o'clock, and LCEA at center were significantly lower in dysplasia patients than in cam patients (p < 0.05). CONCLUSION: 3DMR offers similar qualitative and quantitative analysis as 3DCT in adult painful hip conditions. ADVANCES IN KNOWLEDGE: 3DMR has good potential to replace 3DCT and serve as a one-stop modality for bone and soft tissue characterizations in the pre-operative evaluation of FAI and HD.
Collapse
Affiliation(s)
- Kevin Yan
- 1 Department of Radiology, UT South western Medical Center , Dallas, TX , USA
| | - Yin Xi
- 1 Department of Radiology, UT South western Medical Center , Dallas, TX , USA
| | | | - Joseph Zerr
- 1 Department of Radiology, UT South western Medical Center , Dallas, TX , USA
| | - Joel E Wells
- 2 Department of Orthopedics, UT South western Medical Center , Dallas, TX , USA
| | - Avneesh Chhabra
- 1 Department of Radiology, UT South western Medical Center , Dallas, TX , USA.,2 Department of Orthopedics, UT South western Medical Center , Dallas, TX , USA
| |
Collapse
|
16
|
Fernquest S, Park D, Marcan M, Palmer A, Voiculescu I, Glyn-Jones S. Segmentation of hip cartilage in compositional magnetic resonance imaging: A fast, accurate, reproducible, and clinically viable semi-automated methodology. J Orthop Res 2018; 36:2280-2287. [PMID: 29469172 DOI: 10.1002/jor.23881] [Citation(s) in RCA: 8] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 10/19/2017] [Accepted: 02/16/2018] [Indexed: 02/04/2023]
Abstract
Manual segmentation is a significant obstacle in the analysis of compositional MRI for clinical decision-making and research. Our aim was to produce a fast, accurate, reproducible, and clinically viable semi-automated method for segmentation of hip MRI. We produced a semi-automated segmentation method for cartilage segmentation of hip MRI sequences consisting of a two step process: (i) fully automated hierarchical partitioning of the data volume generated using a bespoke segmentation approach applied recursively, followed by (ii) user selection of the regions of interest using a region editor. This was applied to dGEMRIC scans at 3T taken from a prospective longitudinal study of individuals considered at high-risk of developing osteoarthritis (SibKids) which were also manually segmented for comparison. Fourteen hips were segmented both manually and using our semi-automated method. Per hip, processing time for semi-automated and manual segmentation was 10-15, and 60-120 min, respectively. Accuracy and Dice similarity coefficient (DSC) for the comparison of semi-automated and manual segmentations was 0.9886 and 0.8803, respectively. Intra-observer and inter-observer reproducibility of the semi-automated segmentation method gave an accuracy of 0.9997 and 0.9991, and DSC of 0.9726 and 0.9354, respectively. We have proposed a fast, accurate, reproducible, and clinically viable semi-automated method for segmentation of hip MRI sequences. This enables accurate anatomical and biochemical measurements to be obtained quickly and reproducibly. This is the first such method that shows clinical applicability, and could have large ramifications for the use of compositional MRI in research and clinically. © 2018 Orthopaedic Research Society. Published by Wiley Periodicals, Inc. J Orthop Res.
Collapse
Affiliation(s)
- Scott Fernquest
- Nuffield Department of Orthopaedics, Rheumatology, and Musculoskeletal Sciences, Botnar Research Centre, University of Oxford, Oxford, OX3 7LD, United Kingdom
| | - Daniel Park
- Nuffield Department of Orthopaedics, Rheumatology, and Musculoskeletal Sciences, Botnar Research Centre, University of Oxford, Oxford, OX3 7LD, United Kingdom
| | - Marija Marcan
- Department of Computer Science, University of Oxford, Oxford, OX1 3QD, United Kingdom
| | - Antony Palmer
- Nuffield Department of Orthopaedics, Rheumatology, and Musculoskeletal Sciences, Botnar Research Centre, University of Oxford, Oxford, OX3 7LD, United Kingdom
| | - Irina Voiculescu
- Department of Computer Science, University of Oxford, Oxford, OX1 3QD, United Kingdom
| | - Sion Glyn-Jones
- Nuffield Department of Orthopaedics, Rheumatology, and Musculoskeletal Sciences, Botnar Research Centre, University of Oxford, Oxford, OX3 7LD, United Kingdom
| |
Collapse
|
17
|
Chandra SS, Engstrom C, Fripp J, Neubert A, Jin J, Walker D, Salvado O, Ho C, Crozier S. Local contrast-enhanced MR images via high dynamic range processing. Magn Reson Med 2018; 80:1206-1218. [PMID: 29399889 DOI: 10.1002/mrm.27109] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/29/2017] [Revised: 12/08/2017] [Accepted: 01/06/2018] [Indexed: 02/04/2023]
Affiliation(s)
- Shekhar S Chandra
- School of Information Technology and Electrical Engineering, University of Queensland, Brisbane, Australia
| | - Craig Engstrom
- School of Human Movement Studies, University of Queensland, St Lucia, Australia
| | - Jurgen Fripp
- School of Information Technology and Electrical Engineering, University of Queensland, Brisbane, Australia
- The Australian e-Health Research Centre, CSIRO Health and Biosecurity, Herston, Australia
| | - Ales Neubert
- The Australian e-Health Research Centre, CSIRO Health and Biosecurity, Herston, Australia
| | - Jin Jin
- School of Information Technology and Electrical Engineering, University of Queensland, Brisbane, Australia
| | | | - Olivier Salvado
- School of Information Technology and Electrical Engineering, University of Queensland, Brisbane, Australia
- The Australian e-Health Research Centre, CSIRO Health and Biosecurity, Herston, Australia
| | - Charles Ho
- Steadman Philippon Research Institute (SPRI), Vail, Colorado
| | - Stuart Crozier
- School of Information Technology and Electrical Engineering, University of Queensland, Brisbane, Australia
| |
Collapse
|
18
|
Deep Learning-Based Automatic Segmentation of the Proximal Femur from MR Images. ADVANCES IN EXPERIMENTAL MEDICINE AND BIOLOGY 2018; 1093:73-79. [DOI: 10.1007/978-981-13-1396-7_6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 10/28/2022]
|
19
|
Hareendranathan AR, Zonoobi D, Mabee M, Diederichs C, Punithakumar K, Noga M, Jaremko JL. Hip segmentation from MRI volumes in infants for DDH diagnosis and treatment planning. ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. ANNUAL INTERNATIONAL CONFERENCE 2017; 2016:1046-1049. [PMID: 28268504 DOI: 10.1109/embc.2016.7590882] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/09/2022]
Abstract
Diagnosis and surgical management of Developmental Dysplasia of the Hip (DDH) relies on physical examination and 2D ultrasound scanning. Magnetic Resonance Imaging (MRI) can be used to complement existing techniques and could be advantageous in treatment planning due to its larger field of view. In this paper we propose a semi-automatic method to segment surface models of the acetabulum from MRI images. The method incorporates clinical knowledge in the form of intensity priors which are integrated into a Random Walker (RW) formulation. We use a modified RW framework which compensates for incomplete or blurred boundaries in the image by using information from neighboring slices in the sequence incorporated as node weights. We conducted a pilot study to evaluate the segmentation on a set of 10 infant hip MRI sequences using a 1.5 Tesla MR scanner. Contours obtained from the semi-automated segmentation were compared against manually segmented hip contours using Dice Ratio (DR), Hausdorff Distance (HD) and Root Mean Square (RMS) distance. The proposed method gave values of (DR = 0.84 ± 0.5, HD =3.0 ± 0.7, RMS =1.9 ± 0.3) and (DR=0.86 ± 0.2, HD=3.0 ± 0.1, RMS= 2.0 ± 0.6) for right and left acetabular contours respectively which was higher than the corresponding values obtained from conventional RW segmentation. The execution time of the segmentation algorithm was less than ~4 seconds on a 3.5 GHz CPU.
Collapse
|
20
|
Zeng G, Yang X, Li J, Yu L, Heng PA, Zheng G. 3D U-net with Multi-level Deep Supervision: Fully Automatic Segmentation of Proximal Femur in 3D MR Images. MACHINE LEARNING IN MEDICAL IMAGING 2017. [DOI: 10.1007/978-3-319-67389-9_32] [Citation(s) in RCA: 47] [Impact Index Per Article: 6.7] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 12/04/2022]
|
21
|
Pedoia V, Gallo MC, Souza RB, Majumdar S. Longitudinal study using voxel-based relaxometry: Association between cartilage T 1ρ and T 2 and patient reported outcome changes in hip osteoarthritis. J Magn Reson Imaging 2016; 45:1523-1533. [PMID: 27626787 DOI: 10.1002/jmri.25458] [Citation(s) in RCA: 31] [Impact Index Per Article: 3.9] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/05/2016] [Accepted: 08/18/2016] [Indexed: 11/07/2022] Open
Abstract
PURPOSE To study the local distribution of hip cartilage T1ρ and T2 relaxation times and their association with changes in patient reported outcome measures (PROMs) using a fully automatic, local, and unbiased method in subjects with and without hip osteoarthritis (OA). MATERIALS AND METHODS The 3 Tesla MRI studies of the hip were obtained for 37 healthy controls and 16 subjects with radiographic hip OA. The imaging protocol included a three-dimensional (3D) SPGR sequence and a combined 3D T1ρ and T2 sequence. Quantitative cartilage analysis was compared between a traditional region of interest (ROI)-based method and a fully automatic voxel-based relaxometry (VBR) method. Additionally, VBR was used to assess local T1ρ and T2 differences between subjects with and without OA, and to evaluate the association between T1ρ and T2 and 18-month changes PROMs. RESULTS Results for the two methods were consistent in the acetabular (R = 0.79; coefficients of variation [CV] = 2.9%) and femoral cartilage (R = 0.90; CV = 2.6%). VBR revealed local patterns of T1ρ and T2 elevation in OA subjects, particularly in the posterosuperior acetabular cartilage (T1ρ : P = 0.02; T2 : P = 0.038). Overall, higher T1ρ and T2 values at baseline, particularly in the anterosuperior acetabular cartilage (T1ρ : Rho = -0.42; P = 0.002; T2 : Rho = -0.44; P = 0.002), were associated with worsening PROMS at 18-month follow-up. CONCLUSION VBR is an accurate and robust method for quantitative MRI analysis in hip cartilage. VBR showed the capability to detect local variations in T1ρ and T2 values in subjects with and without osteoarthritis, and voxel based correlations demonstrated a regional dependence between baseline T1ρ and T2 values and changes in PROMs. LEVEL OF EVIDENCE 1 J. MAGN. RESON. IMAGING 2017;45:1523-1533.
Collapse
Affiliation(s)
- Valentina Pedoia
- Musculoskeletal Quantitative Imaging Research Group, Department of Radiology and Biomedical Imaging, University of California San Francisco, San Francisco, California, USA
| | - Matthew C Gallo
- Musculoskeletal Quantitative Imaging Research Group, Department of Radiology and Biomedical Imaging, University of California San Francisco, San Francisco, California, USA
| | - Richard B Souza
- Musculoskeletal Quantitative Imaging Research Group, Department of Radiology and Biomedical Imaging, University of California San Francisco, San Francisco, California, USA.,Department of Physical Therapy and Rehabilitation Science, University of California San Francisco, San Francisco, California, USA
| | - Sharmila Majumdar
- Musculoskeletal Quantitative Imaging Research Group, Department of Radiology and Biomedical Imaging, University of California San Francisco, San Francisco, California, USA
| |
Collapse
|
22
|
Pedoia V, Majumdar S, Link TM. Segmentation of joint and musculoskeletal tissue in the study of arthritis. MAGMA (NEW YORK, N.Y.) 2016; 29:207-21. [PMID: 26915082 PMCID: PMC7181410 DOI: 10.1007/s10334-016-0532-9] [Citation(s) in RCA: 38] [Impact Index Per Article: 4.8] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 07/24/2015] [Revised: 02/05/2016] [Accepted: 02/08/2016] [Indexed: 12/26/2022]
Abstract
As the most frequent cause of physical disability, musculoskeletal diseases such as arthritis and osteoporosis have a great social and economical impact. Quantitative magnetic resonance imaging (MRI) biomarkers are important tools that allow clinicians to better characterize, monitor, and even predict musculoskeletal disease progression. Post-processing pipelines often include image segmentation. Manually identifying the border of the region of interest (ROI) is a difficult and time-consuming task. Manual segmentation is also affected by inter- and intrauser variability, thus limiting standardization. Fully automatic or semi-automatic methods that minimize the user interaction are highly desirable. Unfortunately, an ultimate, highly reliable and extensively evaluated solution for joint and musculoskeletal tissue segmentation has not yet been proposed, and many clinical studies still adopt fully manual procedures. Moreover, the clinical translation of several promising quantitative MRI techniques is highly affected by the lack of an established, fast, and accurate segmentation method. The goal of this review is to present some of the techniques proposed in recent literature that have been adopted in clinical studies for joint and musculoskeletal tissue analyses in arthritis patients. The most widely used MRI sequences and image processing algorithms employed to accomplish segmentation challenges will be discussed in this paper.
Collapse
Affiliation(s)
- Valentina Pedoia
- Musculoskeletal Quantitative Imaging Research Group, Department of Radiology and Biomedical Imaging, UC San Francisco, 1700 Fourth Street, Suite 201, QB3 Building, San Francisco, CA, 94107, USA.
| | - Sharmila Majumdar
- Musculoskeletal Quantitative Imaging Research Group, Department of Radiology and Biomedical Imaging, UC San Francisco, 1700 Fourth Street, Suite 201, QB3 Building, San Francisco, CA, 94107, USA
| | - Thomas M Link
- Musculoskeletal Quantitative Imaging Research Group, Department of Radiology and Biomedical Imaging, UC San Francisco, 1700 Fourth Street, Suite 201, QB3 Building, San Francisco, CA, 94107, USA
| |
Collapse
|
23
|
Ramme AJ, Guss MS, Vira S, Vigdorchik JM, Newe A, Raithel E, Chang G. Evaluation of Automated Volumetric Cartilage Quantification for Hip Preservation Surgery. J Arthroplasty 2016; 31:64-9. [PMID: 26377376 DOI: 10.1016/j.arth.2015.08.009] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 05/15/2015] [Revised: 07/24/2015] [Accepted: 08/10/2015] [Indexed: 02/01/2023] Open
Abstract
Automating the process of femoroacetabular cartilage identification from magnetic resonance imaging (MRI) images has important implications to guiding clinical care by providing a temporal metric that allows for optimizing the timing for joint preservation surgery. In this paper, we evaluate a new automated cartilage segmentation method using a time trial, segmented volume comparison, overlap metrics, and Euclidean distance mapping. We report interrater overlap metrics using the true fast imaging with steady-state precession MRI sequence of 0.874, 0.546, and 0.704 for the total overlap, union overlap, and mean overlap, respectively. This method was 3.28× faster than manual segmentation. This technique provides clinicians with volumetric cartilage information that is useful for optimizing the timing for joint preservation procedures.
Collapse
Affiliation(s)
- Austin J Ramme
- Department of Orthopaedic Surgery, New York University Hospital for Joint Diseases, New York, New York
| | - Michael S Guss
- Department of Orthopaedic Surgery, New York University Hospital for Joint Diseases, New York, New York
| | - Shaleen Vira
- Department of Orthopaedic Surgery, New York University Hospital for Joint Diseases, New York, New York
| | - Jonathan M Vigdorchik
- Department of Orthopaedic Surgery, New York University Hospital for Joint Diseases, New York, New York
| | - Axel Newe
- Methodpark Engineering GmbH, Erlangen, Germany; Chair of Medical Informatics, Friedrich-Alexander University, Erlangen-Nuremberg, Erlangen, Germany
| | | | - Gregory Chang
- Department of Radiology, Center for Musculoskeletal Care, NYU Langone Medical Center, New York, New York
| |
Collapse
|
24
|
Xia Y, Fripp J, Chandra SS, Walker D, Crozier S, Engstrom C. Automated 3D quantitative assessment and measurement of alpha angles from the femoral head-neck junction using MR imaging. Phys Med Biol 2015; 60:7601-16. [DOI: 10.1088/0031-9155/60/19/7601] [Citation(s) in RCA: 12] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/12/2022]
|
25
|
Chandra SS, Surowiec R, Ho C, Xia Y, Engstrom C, Crozier S, Fripp J. Automated analysis of hip joint cartilage combining MR T2 and three‐dimensional fast‐spin‐echo images. Magn Reson Med 2015; 75:403-13. [DOI: 10.1002/mrm.25598] [Citation(s) in RCA: 11] [Impact Index Per Article: 1.2] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/20/2014] [Revised: 12/07/2014] [Accepted: 12/09/2014] [Indexed: 11/11/2022]
Affiliation(s)
- Shekhar S. Chandra
- School of Information Technology and Electrical EngineeringUniversity of Queensland Australia
| | | | - Charles Ho
- Steadman Philippon Research Institute (SPRI)Colorado USA
| | - Ying Xia
- School of Information Technology and Electrical EngineeringUniversity of Queensland Australia
- Australian e‐Health Research CentreCSIRO Computational Informatics Australia
| | - Craig Engstrom
- School of Human Movement Studies, University of Queensland Australia
| | - Stuart Crozier
- School of Information Technology and Electrical EngineeringUniversity of Queensland Australia
| | - Jurgen Fripp
- Australian e‐Health Research CentreCSIRO Computational Informatics Australia
| |
Collapse
|
26
|
Yang Z, Fripp J, Chandra SS, Neubert A, Xia Y, Strudwick M, Paproki A, Engstrom C, Crozier S. Automatic bone segmentation and bone-cartilage interface extraction for the shoulder joint from magnetic resonance images. Phys Med Biol 2015; 60:1441-59. [PMID: 25611124 DOI: 10.1088/0031-9155/60/4/1441] [Citation(s) in RCA: 14] [Impact Index Per Article: 1.6] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/11/2022]
Abstract
We present a statistical shape model approach for automated segmentation of the proximal humerus and scapula with subsequent bone-cartilage interface (BCI) extraction from 3D magnetic resonance (MR) images of the shoulder region. Manual and automated bone segmentations from shoulder MR examinations from 25 healthy subjects acquired using steady-state free precession sequences were compared with the Dice similarity coefficient (DSC). The mean DSC scores between the manual and automated segmentations of the humerus and scapula bone volumes surrounding the BCI region were 0.926 ± 0.050 and 0.837 ± 0.059, respectively. The mean DSC values obtained for BCI extraction were 0.806 ± 0.133 for the humerus and 0.795 ± 0.117 for the scapula. The current model-based approach successfully provided automated bone segmentation and BCI extraction from MR images of the shoulder. In future work, this framework appears to provide a promising avenue for automated segmentation and quantitative analysis of cartilage in the glenohumeral joint.
Collapse
Affiliation(s)
- Zhengyi Yang
- School of Information Technology and Electrical Engineering, The University of Queensland, Brisbane, Australia
| | | | | | | | | | | | | | | | | |
Collapse
|