Dataset Information

Deep learning-based thigh muscle segmentation for reproducible fat fraction quantification using fat-water decomposition MRI.

ABSTRACT: BACKGROUND:Time-efficient and accurate whole volume thigh muscle segmentation is a major challenge in moving from qualitative assessment of thigh muscle MRI to more quantitative methods. This study developed an automated whole thigh muscle segmentation method using deep learning for reproducible fat fraction quantification on fat-water decomposition MRI. RESULTS:This study was performed using a public reference database (Dataset 1, 25 scans) and a local clinical dataset (Dataset 2, 21 scans). A U-net was trained using 23 scans (16 from Dataset 1, seven from Dataset 2) to automatically segment four functional muscle groups: quadriceps femoris, sartorius, gracilis and hamstring. The segmentation accuracy was evaluated on an independent testing set (3?×?3 repeated scans in Dataset 1 and four scans in Dataset 2). The average Dice coefficients between manual and automated segmentation were?>?0.85. The average percent difference (absolute) in volume was 7.57%, and the average difference (absolute) in mean fat fraction (meanFF) was 0.17%. The reproducibility in meanFF was calculated using intraclass correlation coefficients (ICCs) for the repeated scans, and automated segmentation produced overall higher ICCs than manual segmentation (0.921 vs. 0.902). A preliminary quantitative analysis was performed using two-sample t test to detect possible differences in meanFF between 14 normal and 14 abnormal (with fat infiltration) thighs in Dataset 2 using automated segmentation, and significantly higher meanFF was detected in abnormal thighs. CONCLUSIONS:This automated thigh muscle segmentation exhibits excellent accuracy and higher reproducibility in fat fraction estimation compared to manual segmentation, which can be further used for quantifying fat infiltration in thigh muscles.

SUBMITTER: Ding J

PROVIDER: S-EPMC7704819 | biostudies-literature | 2020 Nov

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Deep learning-based thigh muscle segmentation for reproducible fat fraction quantification using fat-water decomposition MRI.

Ding Jie J Cao Peng P Chang Hing-Chiu HC Gao Yuan Y Chan Sophelia Hoi Shan SHS Vardhanabhuti Varut V

Insights into imaging 20201130 1

<h4>Background</h4>Time-efficient and accurate whole volume thigh muscle segmentation is a major challenge in moving from qualitative assessment of thigh muscle MRI to more quantitative methods. This study developed an automated whole thigh muscle segmentation method using deep learning for reproducible fat fraction quantification on fat-water decomposition MRI.<h4>Results</h4>This study was performed using a public reference database (Dataset 1, 25 scans) and a local clinical dataset (Dataset 2 ...[more]

PMID: 33252711

Similar Datasets

Project description:BACKGROUND:Increased breast density is a significant independent risk factor for breast cancer, and recent studies show that this risk is modifiable. Hence, breast density measures sensitive to small changes are desired. PURPOSE:Utilizing fat-water decomposition MRI, we propose an automated, reproducible breast density measurement, which is nonionizing and directly comparable to mammographic density (MD). STUDY TYPE:Retrospective study. POPULATION:The study included two sample sets of breast cancer patients enrolled in a clinical trial, for concordance analysis with MD (40 patients) and reproducibility analysis (10 patients). FIELD STRENGTH/SEQUENCE:The majority of MRI scans (59 scans) were performed with a 1.5T GE Signa scanner using radial IDEAL-GRASE sequence, while the remaining (seven scans) were performed with a 3T Siemens Skyra using 3D Cartesian 6-echo GRE sequence with a similar fat-water separation technique. ASSESSMENT:After automated breast segmentation, breast density was calculated using FraGW, a new measure developed to reliably reflect the amount of fibroglandular tissue and total water content in the entire breast. Based on its concordance with MD, FraGW was calibrated to MR-based breast density (MRD) to be comparable to MD. A previous breast density measurement, Fra80-the ratio of breast voxels with <80% fat fraction-was also calculated for comparison with FraGW. STATISTICAL TESTS:Pearson correlation was performed between MD (reference standard) and FraGW (and Fra80). Test-retest reproducibility of MRD was evaluated using the difference between test-retest measures (?1-2 ) and intraclass correlation coefficient (ICC). RESULTS:Both FraGW and Fra80 were strongly correlated with MD (Pearson ?: 0.96 vs. 0.90, both P?<?0.0001). MRD converted from FraGW showed higher test-retest reproducibility (?1-2 variation: 1.1%?±?1.2%; ICC: 0.99) compared to MD itself (literature intrareader ICC ?0.96) and Fra80. DATA CONCLUSION:The proposed MRD is directly comparable with MD and highly reproducible, which enables the early detection of small breast density changes and treatment response. LEVEL OF EVIDENCE:3 Technical Efficacy: Stage 1 J. Magn. Reson. Imaging 2018;48:971-981.

Project description:Background: Bone marrow fat (BMF) fraction quantification in vertebral bodies is used as a novel imaging biomarker to assess and characterize chronic lower back pain. However, manual segmentation of vertebral bodies is time consuming and laborious. Purpose: (1) Develop a deep learning pipeline for segmentation of vertebral bodies using quantitative water-fat MRI. (2) Compare BMF measurements between manual and automatic segmentation methods to assess performance. Materials and Methods: In this retrospective study, MR images using a 3D spoiled gradient-recalled echo (SPGR) sequence with Iterative Decomposition of water and fat with Echo Asymmetry and Least-squares estimation (IDEAL) reconstruction algorithm were obtained in 57 subjects (28 women, 29 men, mean age, 47.2 ± 12.6 years). An artificial network was trained for 100 epochs on a total of 165 lumbar vertebrae manually segmented from 31 subjects. Performance was assessed by analyzing the receiver operating characteristic curve, precision-recall, F1 scores, specificity, sensitivity, and similarity metrics. Bland-Altman analysis was used to assess performance of BMF fraction quantification using the predicted segmentations. Results: The deep learning segmentation method achieved an AUC of 0.92 (CI 95%: 0.9186, 0.9195) on a testing dataset (n = 24 subjects) on classification of pixels as vertebrae. A sensitivity of 0.99 and specificity of 0.80 were achieved for a testing dataset, and a mean Dice similarity coefficient of 0.849 ± 0.091. Comparing manual and automatic segmentations on fat fraction maps of lumbar vertebrae (n = 124 vertebral bodies) using Bland-Altman analysis resulted in a bias of only -0.605% (CI 95% = -0.847 to -0.363%) and agreement limits of -3.275% and +2.065%. Automatic segmentation was also feasible in 16 ± 1 s. Conclusion: Our results have demonstrated the feasibility of automated segmentation of vertebral bodies using deep learning models on water-fat MR (Dixon) images to define vertebral regions of interest with high specificity. These regions of interest can then be used to quantify BMF with comparable results as manual segmentation, providing a framework for completely automated investigation of vertebral changes in CLBP.

Project description:Purpose: Infiltration of fat into lower limb muscles is one of the key markers for the severity of muscle pathologies. The level of fat infiltration varies in its severity across and within patients, and it is traditionally estimated using visual radiologic inspection. Precise quantification of the severity and spatial distribution of this pathological process requires accurate segmentation of lower limb anatomy into muscle and fat. Methods: Quantitative magnetic resonance imaging (qMRI) of the calf and thigh muscles is one of the most effective techniques for estimating pathological accumulation of intra-muscular adipose tissue (IMAT) in muscular dystrophies. In this work, we present a new deep learning (DL) network tool for automated and robust segmentation of lower limb anatomy that is based on the quantification of MRI's transverse (T2) relaxation time. The network was used to segment calf and thigh anatomies into viable muscle areas and IMAT using a weakly supervised learning process. A new disease biomarker was calculated, reflecting the level of abnormal fat infiltration and disease state. A biomarker was then applied on two patient populations suffering from dysferlinopathy and Charcot-Marie-Tooth (CMT) diseases. Results: Comparison of manual vs. automated segmentation of muscle anatomy, viable muscle areas, and intermuscular adipose tissue (IMAT) produced high Dice similarity coefficients (DSCs) of 96.4%, 91.7%, and 93.3%, respectively. Linear regression between the biomarker value calculated based on the ground truth segmentation and based on automatic segmentation produced high correlation coefficients of 97.7% and 95.9% for the dysferlinopathy and CMT patients, respectively. Conclusions: Using a combination of qMRI and DL-based segmentation, we present a new quantitative biomarker of disease severity. This biomarker is automatically calculated and, most importantly, provides a spatially global indication for the state of the disease across the entire thigh or calf.

Project description:Chemical-shift encoded MRI (CSE-MRI) is a widely used technique for the study of body composition and metabolic disorders, where derived fat and water signals enable the quantification of adipose tissue and muscle. The UK Biobank is acquiring whole-body Dixon MRI (a specific implementation of CSE-MRI) for over 100,000 participants. Current processing methods associated with large whole-body volumes are time intensive and prone to artifacts during fat-water separation performed by the scanner, making quantitative analysis challenging. The most common artifacts are fat-water swaps, where the labels are inverted at the voxel level. It is common for researchers to discard swapped data (generally around 10%), which is wasteful and may lead to unintended biases. Given the large number of whole-body Dixon MRI acquisitions in the UK Biobank, thousands of swaps are expected to be present in the fat and water volumes from image reconstruction performed on the scanner. If they go undetected, errors will propagate into processes such as organ segmentation, and dilute the results in population-based analyses. There is a clear need for a robust method to accurately separate fat and water volumes in big data collections like the UK Biobank. We formulate fat-water separation as a style transfer problem, where swap-free fat and water volumes are predicted from the acquired Dixon MRI data using a conditional generative adversarial network, and introduce a new loss function for the generator model. Our method is able to predict highly accurate fat and water volumes free from artifacts in the UK Biobank. We show that our model separates fat and water volumes using either single input (in-phase only) or dual input (in-phase and opposed-phase) data, with the latter producing superior results. Our proposed method enables faster and more accurate downstream analysis of body composition from Dixon MRI in population studies by eliminating the need for visual inspection or discarding data due to fat-water swaps.Supplementary informationThe online version contains supplementary material available at 10.1186/s40537-022-00677-1.

Project description:Fat fraction quantification and assessment of its distribution in the hepatic tissue become more important with the growing epidemic of obesity, and the increasing prevalence of diabetes mellitus type 2 and non-alcoholic fatty liver disease. At 3Tesla, the multi-echo, chemical-shift-encoded magnetic resonance imaging (CSE-MRI)-based acquisition allows the measurement of proton density fat-fraction (PDFF) even in clinical protocols. Further improvements in SNR can be achieved by the use of phased array coils and increased static magnetic field. The purpose of the study is to evaluate the feasibility of PDFF imaging using a multi-echo CSE-MRI technique at ultra-high magnetic field (7Tesla). Thirteen volunteers (M/F) with a broad range of age, body mass index, and hepatic PDFF were measured at 3 and 7T by multi-gradient-echo MRI and single-voxel spectroscopy MRS. All measurements were performed in breath-hold (exhalation); the MRI protocols were optimized for a short measurement time, thus minimizing motion-related problems. 7T data were processed off-line using Matlab® (MRI:multi-gradient-echo) and jMRUI (MRS), respectively. For quantitative validation of the PDFF results, a similar protocol was performed at 3T, including on-line data processing provided by the system manufacturer, and correlation analyses between 7 and 3T data were performed off-line. The multi-echo CSE-MRI measurements at 7T with a phased-array coil configuration and an optimal post-processing yielded liver volume coverage ranging from 30 to 90% for high- and low-BMI subjects, respectively. PDFFs ranged between 1 and 20%. We found significant correlations between 7T MRI and -MRS measurements (R2 ≅ 0.97; p < 0.005), and between MRI-PDFF at 7T and 3T fields (R2 ≅ 0.94; p < 0.005) in the evaluated volumes. Based on the measurements and analyses performed, the multi-echo CSE-MRI method using a 32-channel coil at 7T showed its aptitude for MRI-based quantitation of PDFF in the investigated volumes. The results are the first step toward qMRI of the whole liver at 7T with further improvements in hardware.

Project description:BackgroundWith the growing prevalence of obesity and metabolic syndrome, reliable quantitative imaging methods for adipose tissue are required. Monogenic forms of the metabolic syndrome include Dunnigan-variety familial partial lipodystrophy subtypes 2 and 3 (FPLD2 and FPLD3), which are characterized by the loss of subcutaneous fat in the extremities. Through magnetic resonance imaging (MRI) of FPLD patients, we have developed a method of quantifying the core FPLD anthropometric phenotype, namely adipose tissue in the mid-calf and mid-thigh regions.MethodsFour female subjects, including an FPLD2 subject (LMNA R482Q), an FPLD3 subject (PPARG F388L), and two control subjects were selected for MRI and analysis. MRI scans of subjects were performed on a 1.5T GE MR Medical system, with 17 transaxial slices comprising a 51 mm section obtained in both the mid-calf and mid-thigh regions. Using ImageJ 1.34 n software, analysis of raw MR images involved the creation of a connectedness map of the subcutaneous adipose tissue contours within the lower limb segment from a user-defined seed point. Quantification of the adipose tissue was then obtained after thresholding the connected map and counting the voxels (volumetric pixels) present within the specified region.ResultsMR images revealed significant differences in the amounts of subcutaneous adipose tissue in lower limb segments of FPLD3 and FPLD2 subjects: respectively, mid-calf, 15.5% and 0%, and mid-thigh, 25.0% and 13.3%. In comparison, old and young healthy controls had values, respectively, of mid-calf, 32.5% and 26.2%, and mid-thigh, 52.2% and 36.1%. The FPLD2 patient had significantly reduced subcutaneous adipose tissue compared to FPLD3 patient.ConclusionThus, semi-automated quantification of adipose tissue of the lower extremity can detect differences between individuals of various lipodystrophy genotypes and represents a potentially useful tool for extended quantitative phenotypic analysis of other genetic metabolic disorders.

Dataset Information

Deep learning-based thigh muscle segmentation for reproducible fat fraction quantification using fat-water decomposition MRI.

Publications

Deep learning-based thigh muscle segmentation for reproducible fat fraction quantification using fat-water decomposition MRI.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets