Displaying publications 1 - 20 of 755 in total

  1. Wen LY, Wah LP, Mohamad NF, Singh S, Toong LY
    J Fam Pract, 2023 Mar;72(2):E1-E7.
    PMID: 36947782 DOI: 10.12788/jfp.0563
    A patient's age, clinical presentation, medical history, and circumstances at time of palsy onset suggest likely underlying causes and help prioritize choice of imaging.
    Matched MeSH terms: Magnetic Resonance Imaging*
  2. Manan HA, Franz EA, Yahya N
    Eur J Cancer Care (Engl), 2021 Jul;30(4):e13428.
    PMID: 33592671 DOI: 10.1111/ecc.13428
    PURPOSE: Resting-state functional Magnetic Resonance Imaging (rs-fMRI) is suggested to be a viable option for pre-operative mapping for patients with brain tumours. However, it remains an open issue whether the tool is useful in the clinical setting compared to task-based fMRI (T-fMRI) and intraoperative mapping. Thus, a systematic review was conducted to investigate the usefulness of this technique.

    METHODS: A systematic literature search of rs-fMRI methods applied as a pre-operative mapping tool was conducted using the PubMed/MEDLINE and Cochrane Library electronic databases following PRISMA guidelines.

    RESULTS: Results demonstrated that 50% (six out of twelve) of the studies comparing rs-fMRI and T-fMRI showed good concordance for both language and sensorimotor networks. In comparison to intraoperative mapping, 86% (six out of seven) studies found a good agreement to rs-fMRI. Finally, 87% (twenty out of twenty-three) studies agreed that rs-fMRI is a suitable and useful pre-operative mapping tool.

    CONCLUSIONS: rs-fMRI is a promising technique for pre-operative mapping in assessing the functional brain areas. However, the agreement between rs-fMRI with other techniques, including T-fMRI and intraoperative maps, is not yet optimal. Studies to ascertain and improve the sophistication in pre-processing of rs-fMRI imaging data are needed.

    Matched MeSH terms: Magnetic Resonance Imaging*
  3. Chow LS, Paley MNJ
    Magn Reson Imaging, 2021 06;79:76-84.
    PMID: 33753137 DOI: 10.1016/j.mri.2021.03.014
    The optic nerve is known to be one of the largest nerve bundles in the human central nervous system. There have been many studies of optic nerve imaging and post-processing that have provided insights into pathophysiology of optic neuritis related to multiple sclerosis and neuromyelitis optica spectrum disorder, glaucoma, and Leber's hereditary optic neuropathy. There are many challenges in optic nerve imaging, due to the morphology of the nerve through its course to the optic chiasm, its mobility due to eye movements and the high signal from cerebrospinal fluid and orbital fat surrounding the optic nerve. Recently, many advanced and fast imaging sequences have been used with post-processing techniques in attempts to produce higher resolution images of the optic nerve for evaluating various diseases. Magnetic resonance imaging (MRI) is one of the most common imaging methodologies for the optic nerve. This review paper will focus on recent MRI advances in optic nerve imaging and explain several post-processing techniques being used for analysis of optic nerve images. Finally, some challenges and potential for future optic nerve studies will be discussed.
    Matched MeSH terms: Magnetic Resonance Imaging
  4. Nasaruddin, N.H., Yusoff, A.N., Sharanjeet Kaur, Nasrudin, N.F., Muda, S.
    Ocular abnormalities have apparent effects on brain activation. However, neuroimaging data about the ocular characteristics of healthy participants are still lacking to be compared with data for patients with ocular pathology. The objective of this multiple participants’ functional magnetic resonance imaging (fMRI) studies was to investigate the brain activation characteristics of healthy participants when they view stimuli of various shapes, pattern and size. During the fMRI scans, the participants view the growing ring, rotating wedge, flipping hour glass/bow tie, quadrant arc and full checker board stimuli. All stimuli have elements of black-and-white checkerboard pattern. Statistical parametric mapping (SPM) was used in generating brain activation via fixed-effects (FFX) and conjunction analyses. The stimuli of various shapes, pattern and size produce different brain activation with more activation concentrated in the left hemisphere. These results are supported by the conjunction analysis which indicated that the left pre-central, post-central, superior temporal and occipital gyrus as well as the left cingulate cortices were involved when the participants viewed each given stimulus. Differential activation analysis showed activation with high specificity in the occipital region due to the stimuli of various shapes, pattern and size. The activation in the right middle temporal gyrus was found to be significantly higher in response to moving stimuli as compared to stationary stimuli. This confi rms the involvement of the right middle temporal gyrus in the observation of movements. The black-and-white checkerboard stimuli of various shapes, pattern and size, stationary and moving was found to 1) activate visual as well as other cortices in temporal and parietal lobes, 2) cause asymmetry in brain function and 3) exhibit functional integration characteristics in several brain areas.
    Keywords: fMRI; SPM; visual stimulus; occipital gyrus; middle temporal gyrus
    Matched MeSH terms: Magnetic Resonance Imaging
  5. Khan DM, Kamel N, Muzaimi M, Hill T
    Brain Connect, 2021 02;11(1):12-29.
    PMID: 32842756 DOI: 10.1089/brain.2019.0721
    Introduction: With the recent technical advances in brain imaging modalities such as magnetic resonance imaging, positron emission tomography, and functional magnetic resonance imaging (fMRI), researchers' interests have inclined over the years to study brain functions through the analysis of the variations in the statistical dependence among various brain regions. Through its wide use in studying brain connectivity, the low temporal resolution of the fMRI represented by the limited number of samples per second, in addition to its dependence on brain slow hemodynamic changes, makes it of limited capability in studying the fast underlying neural processes during information exchange between brain regions. Materials and Methods: In this article, the high temporal resolution of the electroencephalography (EEG) is utilized to estimate the effective connectivity within the default mode network (DMN). The EEG data are collected from 20 subjects with alcoholism and 25 healthy subjects (controls), and used to obtain the effective connectivity diagram of the DMN using the Partial Directed Coherence algorithm. Results: The resulting effective connectivity diagram within the DMN shows the unidirectional causal effect of each region on the other. The variations in the causal effects within the DMN between controls and alcoholics show clear correlation with the symptoms that are usually associated with alcoholism, such as cognitive and memory impairments, executive control, and attention deficiency. The correlation between the exchanged causal effects within the DMN and symptoms related to alcoholism is discussed and properly analyzed. Conclusion: The establishment of the causal differences between control and alcoholic subjects within the DMN regions provides valuable insight into the mechanism by which alcohol modulates our cognitive and executive functions and creates better possibility for effective treatment of alcohol use disorder.
    Matched MeSH terms: Magnetic Resonance Imaging
  6. Hafizzi Awang NMS, Mohd Noor R, Ramli R, Abdullah B
    Gulf J Oncolog, 2022 Jan;1(38):78-81.
    PMID: 35156648
    BACKGROUND: The infratemporal fossa poses a great challenge to surgeons due to its complex anatomy and communications to many surrounding areas. The disorders that arise from this area can be infections and neoplasms. They can cause varieties of complications due to the extension of the pathologies and compression effect to the other adjacent structures. Inflammatory pseudotumor of the infratemporal fossa is one of the rare disorders of the head and neck.

    CASE PRESENTATION: We report a patient with a pseudotumor of infratemporal fossa that extends to the orbital area and cavernous sinus, causing orbital apex syndromes. The diagnostic imaging, different surgical approaches of the biopsy and methods of treatment of this case are discussed.

    DISCUSSION AND CONCLUSION: Radiological imaging and immunohistopathology are essential in establishing the diagnosis and determine the complications. The surgeons must well understand the characteristics and the impact of the disorders on the adjacent structure and give prompt decision to provide definitive treatments.

    Matched MeSH terms: Magnetic Resonance Imaging
  7. Yeoh PSQ, Lai KW, Goh SL, Hasikin K, Hum YC, Tee YK, et al.
    Comput Intell Neurosci, 2021;2021:4931437.
    PMID: 34804143 DOI: 10.1155/2021/4931437
    Osteoarthritis (OA), especially knee OA, is the most common form of arthritis, causing significant disability in patients worldwide. Manual diagnosis, segmentation, and annotations of knee joints remain as the popular method to diagnose OA in clinical practices, although they are tedious and greatly subject to user variation. Therefore, to overcome the limitations of the commonly used method as above, numerous deep learning approaches, especially the convolutional neural network (CNN), have been developed to improve the clinical workflow efficiency. Medical imaging processes, especially those that produce 3-dimensional (3D) images such as MRI, possess ability to reveal hidden structures in a volumetric view. Acknowledging that changes in a knee joint is a 3D complexity, 3D CNN has been employed to analyse the joint problem for a more accurate diagnosis in the recent years. In this review, we provide a broad overview on the current 2D and 3D CNN approaches in the OA research field. We reviewed 74 studies related to classification and segmentation of knee osteoarthritis from the Web of Science database and discussed the various state-of-the-art deep learning approaches proposed. We highlighted the potential and possibility of 3D CNN in the knee osteoarthritis field. We concluded by discussing the possible challenges faced as well as the potential advancements in adopting 3D CNNs in this field.
    Matched MeSH terms: Magnetic Resonance Imaging
  8. Abdullah BJ, Bux SI, Chien D
    Med J Malaysia, 1997 Dec;52(4):445-53; quiz 454.
    PMID: 10968127
    MRI is now an important diagnostic tool in medical management. There are numerous safety issues to be considered by the clinicians prior to requesting an MRI examination for their patients. These include those related to the magnetic field, gradient magnetic fields, the patient and contrast medium. This paper discusses the dangers and necessary precautions essential to reduce the risk of untoward complications from MRI.
    Matched MeSH terms: Magnetic Resonance Imaging/adverse effects*
  9. Chuah SH, Md Sari NA, Chew BT, Tan LK, Chiam YK, Chan BT, et al.
    Phys Med, 2020 Oct;78:137-149.
    PMID: 33007738 DOI: 10.1016/j.ejmp.2020.08.022
    Differential diagnosis of hypertensive heart disease (HHD) and hypertrophic cardiomyopathy (HCM) is clinically challenging but important for treatment management. This study aims to phenotype HHD and HCM in 3D + time domain by using a multiparametric motion-corrected personalized modeling algorithm and cardiac magnetic resonance (CMR). 44 CMR data, including 12 healthy, 16 HHD and 16 HCM cases, were examined. Multiple CMR phenotype data consisting of geometric and dynamic variables were extracted globally and regionally from the models over a full cardiac cycle for comparison against healthy models and clinical reports. Statistical classifications were used to identify the distinctive characteristics and disease subtypes with overlapping functional data, providing insights into the challenges for differential diagnosis of both types of disease. While HCM is characterized by localized extreme hypertrophy of the LV, wall thickening/contraction/strain was found to be normal and in sync, though it was occasionally exaggerated at normotrophic/less severely hypertrophic regions during systole to preserve the overall ejection fraction (EF) and systolic functionality. Additionally, we observed that hypertrophy in HHD could also be localized, although at less extreme conditions (i.e. more concentric). While fibrosis occurs mostly in those HCM cases with aortic obstruction, only minority of HHD patients were found affected by fibrosis. We demonstrate that subgroups of HHD (i.e. preserved and reduced EF: HHDpEF & HHDrEF) have different 3D + time CMR characteristics. While HHDpEF has cardiac functions in normal range, dilation and heart failure are indicated in HHDrEF as reflected by low LV wall thickening/contraction/strain and synchrony, as well as much reduced EF.
    Matched MeSH terms: Magnetic Resonance Imaging; Magnetic Resonance Imaging, Cine
  10. Liong CC, Rahmat K, Mah JS, Lim SY, Tan AH
    Can J Neurol Sci, 2016 Sep;43(5):719-20.
    PMID: 27670213 DOI: 10.1017/cjn.2016.269
    Matched MeSH terms: Magnetic Resonance Imaging*
  11. Hanafiah M, Johari B, Ab Mumin N, Musa AA, Hanafiah H
    Br J Radiol, 2022 May 01;95(1133):20210857.
    PMID: 35007174 DOI: 10.1259/bjr.20210857
    OBJECTIVE: Primary open-angle glaucoma (POAG) is a degenerative optic neuropathy disease which has somewhat similar pathophysiology to Alzheimer's disease (AD). This study aims to determine the presence of medial temporal atrophy and parietal lobe atrophy in patients with POAG compared to normal controls using medial temporal atrophy (MTA) scoring and posterior cortical atrophy (PCA) scoring system on T1 magnetization-prepared rapid gradient-echo.

    METHODS: 50 POAG patients and 50 normal subjects were recruited and an MRI brain with T1-magnetization-prepared rapid gradient-echo was performed. Medial temporal lobe and parietal lobe atrophy were by MTA and PCA/Koedam scoring. The score of the PCA and MTA were compared between the POAG group and the controls.

    RESULTS: There was a significant statistical difference between PCA score in POAG and the healthy control group (p-value = 0.026). There is no statistical difference between MTA score in POAG compared to the healthy control group (p-value = 0.58).

    CONCLUSION: This study suggests a correlation between POAG and PCA score. Potential application of this scoring method in clinical diagnosis and monitoring of POAG patients.

    ADVANCES IN KNOWLEDGE: The scoring method used in AD may also be applied in the diagnosis and monitoring of POAGMRI brain, specifically rapid volumetric T1 spoiled gradient echo sequence, may be applied in POAG assessment.

    Matched MeSH terms: Magnetic Resonance Imaging/methods
  12. Liew A, Lee CC, Subramaniam V, Lan BL, Tan M
    J Magn Reson Imaging, 2023 Jun;57(6):1728-1740.
    PMID: 36208095 DOI: 10.1002/jmri.28456
    BACKGROUND: Research suggests that treatment of multiple brain metastases (BMs) with stereotactic radiosurgery shows improvement when metastases are detected early, providing a case for BM detection capabilities on small lesions.

    PURPOSE: To demonstrate automatic detection of BM on three MRI datasets using a deep learning-based approach. To improve the performance of the network is iteratively co-trained with datasets from different domains. A systematic approach is proposed to prevent catastrophic forgetting during co-training.

    STUDY TYPE: Retrospective.

    POPULATION: A total of 156 patients (105 ground truth and 51 pseudo labels) with 1502 BM (BrainMetShare); 121 patients with 722 BM (local); 400 patients with 447 primary gliomas (BrATS). Training/pseudo labels/validation data were distributed 84/51/21 (BrainMetShare). Training/validation data were split: 121/23 (local) and 375/25 (BrATS).

    FIELD STRENGTH/SEQUENCE: A 5 T and 3 T/T1 spin-echo postcontrast (T1-gradient echo) (BrainMetShare), 3 T/T1 magnetization prepared rapid acquisition gradient echo postcontrast (T1-MPRAGE) (local), 0.5 T, 1 T, and 1.16 T/T1-weighted-fluid-attenuated inversion recovery (T1-FLAIR) (BrATS).

    ASSESSMENT: The ground truth was manually segmented by two (BrainMetShare) and four (BrATS) radiologists and manually annotated by one (local) radiologist. Confidence and volume based domain adaptation (CAVEAT) method of co-training the three datasets on a 3D nonlocal convolutional neural network (CNN) architecture was implemented to detect BM.

    STATISTICAL TESTS: The performance was evaluated using sensitivity and false positive rates per patient (FP/patient) and free receiver operating characteristic (FROC) analysis at seven predefined (1/8, 1/4, 1/2, 1, 2, 4, and 8) FPs per scan.

    RESULTS: The sensitivity and FP/patient from a held-out set registered 0.811 at 2.952 FP/patient (BrainMetShare), 0.74 at 3.130 (local), and 0.723 at 2.240 (BrATS) using the CAVEAT approach with lesions as small as 1 mm being detected.

    DATA CONCLUSION: Improved sensitivities at lower FP can be achieved by co-training datasets via the CAVEAT paradigm to address the problem of data sparsity.


    Matched MeSH terms: Magnetic Resonance Imaging/methods
  13. Mabel HM, Othman NB, Cheah WK
    Med J Malaysia, 2022 May;77(3):403-405.
    PMID: 35638501
    Pontine infarct is a rare but clinically significant cause of an isolated facial nerve palsy. Prompt diagnosis with the use of magnetic resonance imaging (MRI) allows early initiation of treatment for such patients. We report a 62-year-old gentleman with diabetes, hypertension, and gout, presenting with lower motor neuron facial nerve palsy. This report highlights that isolated facial nerve palsy is not always associated with Bell's palsy, which remains the commonest cause of facial nerve paralysis. A thorough neurological examination and good clinical correlation with the patient's history and physical findings, coupled with the use of facial nerve anatomical knowledge and early employment of MRI, are imperative in clinching the diagnosis.
    Matched MeSH terms: Magnetic Resonance Imaging/methods
  14. Choong MK, Logeswaran R, Bister M
    J Med Syst, 2006 Jun;30(3):139-43.
    PMID: 16848126
    This paper attempts to improve the diagnostic quality of magnetic resonance (MR) images through application of lossy compression as a noise-reducing filter. The amount of imaging noise present in MR images is compared with the amount of noise introduced by the compression, with particular attention given to the situation where the compression noise is a fraction of the imaging noise. A popular wavelet-based algorithm with good performance, Set Partitioning in Hierarchical Trees (SPIHT), was employed for the lossy compression. Tests were conducted with a number of MR patient images and corresponding phantom images. Different plausible ratios between imaging noise and compression noise (ICR) were considered, and the achievable compression gain through the controlled lossy compression was evaluated. Preliminary results show that at certain ICR's, it becomes virtually impossible to distinguish between the original and compressed-decompressed image. Radiologists presented with a blind test, in certain cases, showed preference to the compressed image rather than the original uncompressed ones, indicating that under controlled circumstances, lossy image compression can be used to improve the diagnostic quality of the MR images.
    Matched MeSH terms: Magnetic Resonance Imaging/methods*
  15. Huang SG, Samdin SB, Ting CM, Ombao H, Chung MK
    J Neurosci Methods, 2020 02 01;331:108480.
    PMID: 31760059 DOI: 10.1016/j.jneumeth.2019.108480
    BACKGROUND: Recent studies have indicated that functional connectivity is dynamic even during rest. A common approach to modeling the dynamic functional connectivity in whole-brain resting-state fMRI is to compute the correlation between anatomical regions via sliding time windows. However, the direct use of the sample correlation matrices is not reliable due to the image acquisition and processing noises in resting-sate fMRI.

    NEW METHOD: To overcome these limitations, we propose a new statistical model that smooths out the noise by exploiting the geometric structure of correlation matrices. The dynamic correlation matrix is modeled as a linear combination of symmetric positive-definite matrices combined with cosine series representation. The resulting smoothed dynamic correlation matrices are clustered into disjoint brain connectivity states using the k-means clustering algorithm.

    RESULTS: The proposed model preserves the geometric structure of underlying physiological dynamic correlation, eliminates unwanted noise in connectivity and obtains more accurate state spaces. The difference in the estimated dynamic connectivity states between males and females is identified.

    COMPARISON WITH EXISTING METHODS: We demonstrate that the proposed statistical model has less rapid state changes caused by noise and improves the accuracy in identifying and discriminating different states.

    CONCLUSIONS: We propose a new regression model on dynamically changing correlation matrices that provides better performance over existing windowed correlation and is more reliable for the modeling of dynamic connectivity.

    Matched MeSH terms: Magnetic Resonance Imaging*
  16. Bilal M, Shah JA, Qureshi IM, Kadir K
    Int J Biomed Imaging, 2018;2018:7803067.
    PMID: 29610569 DOI: 10.1155/2018/7803067
    Transformed domain sparsity of Magnetic Resonance Imaging (MRI) has recently been used to reduce the acquisition time in conjunction with compressed sensing (CS) theory. Respiratory motion during MR scan results in strong blurring and ghosting artifacts in recovered MR images. To improve the quality of the recovered images, motion needs to be estimated and corrected. In this article, a two-step approach is proposed for the recovery of cardiac MR images in the presence of free breathing motion. In the first step, compressively sampled MR images are recovered by solving an optimization problem using gradient descent algorithm. TheL1-norm based regularizer, used in optimization problem, is approximated by a hyperbolic tangent function. In the second step, a block matching algorithm, known as Adaptive Rood Pattern Search (ARPS), is exploited to estimate and correct respiratory motion among the recovered images. The framework is tested for free breathing simulated andin vivo2D cardiac cine MRI data. Simulation results show improved structural similarity index (SSIM), peak signal-to-noise ratio (PSNR), and mean square error (MSE) with different acceleration factors for the proposed method. Experimental results also provide a comparison betweenk-tFOCUSS with MEMC and the proposed method.
    Matched MeSH terms: Magnetic Resonance Imaging; Magnetic Resonance Imaging, Cine
  17. Gandhamal A, Talbar S, Gajre S, Razak R, Hani AFM, Kumar D
    Comput Biol Med, 2017 Sep 01;88:110-125.
    PMID: 28711767 DOI: 10.1016/j.compbiomed.2017.07.008
    Knee osteoarthritis (OA) progression can be monitored by measuring changes in the subchondral bone structure such as area and shape from MR images as an imaging biomarker. However, measurements of these minute changes are highly dependent on the accurate segmentation of bone tissue from MR images and it is challenging task due to the complex tissue structure and inadequate image contrast/brightness. In this paper, a fully automated method for segmenting subchondral bone from knee MR images is proposed. Here, the contrast of knee MR images is enhanced using a gray-level S-curve transformation followed by automatic seed point detection using a three-dimensional multi-edge overlapping technique. Successively, bone regions are initially extracted using distance-regularized level-set evolution followed by identification and correction of leakages along the bone boundary regions using a boundary displacement technique. The performance of the developed technique is evaluated against ground truths by measuring sensitivity, specificity, dice similarity coefficient (DSC), average surface distance (AvgD) and root mean square surface distance (RMSD). An average sensitivity (91.14%), specificity (99.12%) and DSC (90.28%) with 95% confidence interval (CI) in the range 89.74-92.54%, 98.93-99.31% and 88.68-91.88% respectively is achieved for the femur bone segmentation in 8 datasets. For tibia bone, average sensitivity (90.69%), specificity (99.65%) and DSC (91.35%) with 95% CI in the range 88.59-92.79%, 99.50-99.80% and 88.68-91.88% respectively is achieved. AvgD and RMSD values for femur are 1.43 ± 0.23 (mm) and 2.10 ± 0.35 (mm) respectively while for tibia, the values are 0.95 ± 0.28 (mm) and 1.30 ± 0.42 (mm) respectively that demonstrates acceptable error between proposed method and ground truths. In conclusion, results obtained in this work demonstrate substantially significant performance with consistency and robustness that led the proposed method to be applicable for large scale and longitudinal knee OA studies in clinical settings.
    Matched MeSH terms: Magnetic Resonance Imaging/methods*
  18. Subudhi A, Acharya UR, Dash M, Jena S, Sabut S
    Comput Biol Med, 2018 12 01;103:116-129.
    PMID: 30359807 DOI: 10.1016/j.compbiomed.2018.10.016
    It is difficult to develop an accurate algorithm to detect the stroke lesions using magnetic resonance imaging (MRI) images due to variation in different lesion sizes, variation in morphological structure, and similarity in intensity of lesion with normal brain in three types of stroke, namely partial anterior circulation syndrome (PACS), lacunar syndrome (LACS) and total anterior circulation stroke (TACS). In this paper, we have integrated the advantages of Delaunay triangulation (DT) and fractional order Darwinian particle swarm optimization (FODPSO), called DT-FODPSO technique for automatic segmentation of the structure of the stroke lesion. The approach was validated on 192 MRI images obtained from different stroke subjects. Statistical and morphological features were extracted and classified according to the Oxfordshire community stroke project (OCSP) using support vector machine (SVM) and random forest (RF) classifiers. The method effectively detected the stroke lesions and achieved promising results with an average sensitivity of 0.93, accuracy of 0.95, JI of 0.89 and Dice similarity index of 0.93 using RF classifier. These promising results indicates the DT based optimized approach is efficient in detecting ischemic stroke and it can aid the neuro-radiologists to validate their routine screening.
    Matched MeSH terms: Magnetic Resonance Imaging/methods*
  19. Gan HS, Sayuti KA, Ramlee MH, Lee YS, Wan Mahmud WMH, Abdul Karim AH
    Int J Comput Assist Radiol Surg, 2019 May;14(5):755-762.
    PMID: 30859457 DOI: 10.1007/s11548-019-01936-y
    PURPOSE: Manual segmentation is sensitive to operator bias, while semiautomatic random walks segmentation offers an intuitive approach to understand the user knowledge at the expense of large amount of user input. In this paper, we propose a novel random walks seed auto-generation (SAGE) hybrid model that is robust to interobserver error and intensive user intervention.

    METHODS: Knee image is first oversegmented to produce homogeneous superpixels. Then, a ranking model is developed to rank the superpixels according to their affinities to standard priors, wherein background superpixels would have lower ranking values. Finally, seed labels are generated on the background superpixel using Fuzzy C-Means method.

    RESULTS: SAGE has achieved better interobserver DSCs of 0.94 ± 0.029 and 0.93 ± 0.035 in healthy and OA knee segmentation, respectively. Good segmentation performance has been reported in femoral (Healthy: 0.94 ± 0.036 and OA: 0.93 ± 0.034), tibial (Healthy: 0.91 ± 0.079 and OA: 0.88 ± 0.095) and patellar (Healthy: 0.88 ± 0.10 and OA: 0.84 ± 0.094) cartilage segmentation. Besides, SAGE has demonstrated greater mean readers' time of 80 ± 19 s and 80 ± 27 s in healthy and OA knee segmentation, respectively.

    CONCLUSIONS: SAGE enhances the efficiency of segmentation process and attains satisfactory segmentation performance compared to manual and random walks segmentation. Future works should validate SAGE on progressive image data cohort using OA biomarkers.

    Matched MeSH terms: Magnetic Resonance Imaging/methods*
Contact Us

Please provide feedback to Administrator (afdal@afpm.org.my)

External Links