Deep Learning-Based Fully Automated Segmentation of Regional Muscle Volume and Spatial Intermuscular Fat Using CT

Zhang, Rui; An-zhi, HE; Xia, Wei; Su, Yongbin; Jian, Junming; Liu, Yandong; Guo, Zhe; Shi, Wei; Zhang, Zhenguang; He, Bo; Cheng, Xiaoguang; Gao, Xin; Liu, Yajun; Wang, Ling

doi:10.1016/j.acra.2023.06.009

Cited by 2 publications

(2 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…First, the number of participants was limited, and none of the evaluated muscles exhibited severe fat infiltration classified as Goutallier grade 3/4. Second, although manually delineating the VOI by experienced hands took about a minute, the application of Artificial Intelligence for fully automated segmentation and measurement has the potential to significantly boost efficiency ( 40 ). Our research team is actively exploring such AI-assisted approaches.…”

Section: Discussionmentioning

confidence: 99%

Quantification of volumetric thigh and paravertebral muscle fat content: comparison of quantitative Dixon (Q-Dixon) magnetic resonance imaging (MRI) with high-speed T2-corrected multiecho MR spectroscopy

Zhang,

Fu,

Yan

et al. 2024

Quant Imaging Med Surg

View full text Add to dashboard Cite

Background Muscle fat infiltration (MFI) is increasingly recognized as a critical factor influencing muscle function and metabolic health. Accurate quantification of MFI is essential for diagnosing and monitoring various muscular and metabolic disorders. Quantitative Dixon (Q-Dixon) magnetic resonance imaging (MRI) and high-speed T 2 -corrected multi-echo (HISTO) magnetic resonance spectroscopy (MRS) are both advanced imaging techniques that offer potential for detailed assessment of MFI. However, the validity and reliability of these methods in measuring volumetric changes in muscle composition, particularly in both thigh and paravertebral muscles, have not been thoroughly compared. This study aims to validate volumetric measurements using Q-Dixon MRI against HISTO MRS in thigh and paravertebral muscles, taking into account the heterogeneity of MFI. Methods A retrospective study was conducted with 54 subjects [mean age, 60 years; 38 male (M)/16 female (F)] for thigh muscle and 56 subjects (mean age, 50 years; 22 M/34 F) for paravertebral muscle assessment using a 3-Tesla MRI. The proton density fat fraction (PDFF) was measured with Q-Dixon MRI and HISTO MRS within the upper-middle part of quadriceps femoris and paravertebral muscles at L4/5 level in volumes-of-interest (VOIs). The corresponding volumetric Q-Dixon freehand VOI PDFF was measured. Scatterplots, Bland-Altman plots, Spearman correlation coefficients, and Wilcoxon signed rank test with Bonferroni correction were employed. The Kruskal-Wallis H tests followed by Bonferroni-corrected post hoc tests were analyzed to compare parameter differences with visual MFI grades. Results Q-Dixon cubic VOI PDFF correlated positively with HISTO MRS PDFF in thigh (r=0.96, P<0.001) and paravertebral groups (r=0.98, P<0.001), with insignificant differences (P=0.29, 0.82, respectively). Both PDFF values from cubic VOIs in Q-Dixon and HISTO MRS differed from the freehand Q-Dixon PDFF (all P<0.001). Only for <5% HISTO MRS PDFF, there was a difference between HISTO MRS PDFF and Q-Dixon cubic VOI PDFF (P=0.002). Conclusions Volumetric Q-Dixon cubic VOI PDFF exhibited good correlation and consistency with HISTO MRS PDFF for quantitative fat assessment in thigh and paravertebral muscles except for muscles with fat fraction <5%, and the Q-Dixon freehand VOI PDFF offers a more comprehensive assessment of the actual MFI compared to cubic VOI.

show abstract

Section: Discussionmentioning

confidence: 99%

Quantification of volumetric thigh and paravertebral muscle fat content: comparison of quantitative Dixon (Q-Dixon) magnetic resonance imaging (MRI) with high-speed T2-corrected multiecho MR spectroscopy

Zhang,

Fu,

Yan

et al. 2024

Quant Imaging Med Surg

View full text Add to dashboard Cite

show abstract

“…Volumetric measurements of muscles may improve this measurement bias. ( 39 ) Third, CT scans of the hip were performed at baseline and were not repeated, resulting in a lack of data on changes in the Goutallier grades of the gluteal muscles after the occurrence of the first hip fracture.…”

Section: Discussionmentioning

confidence: 99%

Associations of Quantitative and Qualitative Muscle Parameters With Second Hip Fracture Risk in Older Women: A Prospective Cohort Study

Zhang,

Ge,

Liu

et al. 2023

JBMR Plus

Self Cite

View full text Add to dashboard Cite

Older women with a first hip fracture exhibit heightened susceptibility and incidence of second fracture and potentially severe consequences. This prospective study was to compare the predictive power of qualitative and quantitative muscle parameters for a second hip fracture in older women with a first hip fracture. A total of 206 subjects were recruited from the longitudinal Chinese Second Hip Fracture Evaluation study. Hip computed tomography (CT) scans were obtained immediately after the first fracture. Muscle fat infiltration was assessed according to the Goutallier classification qualitatively. Quantitative parameters included cross‐sectional area and density of gluteus maximus (G.MaxM) and gluteus medius and minimus (G.Med/MinM) muscles. CT X‐ray absorptiometry was used to measure the areal bone mineral density (aBMD) of the contralateral femur. Cox proportional hazards models were used to compute hazard ratios (HR) of second hip fracture risk. The mean age of subjects was 74.9 (±9.5) years at baseline. After 4.5 years, 35 had a second hip fracture, 153 without a second hip fracture, and 18 died. Except for the combined G.MinM Goutallier grade 3 and 4 groups before adjustment for covariates (HR = 5.83; 95% confidence interval [CI] 1.49–22.83), there were no significant HRs for qualitative classification to predict a second hip fracture. Among quantitative metrics, after adjustment for covariates, G.Med/MinM density was significant in the original (HR = 1.44; CI 1.02–2.04) and competing risk analyses (HR = 1.46; CI 1.02–2.07). After additional adjustment for femoral neck (FN) aBMD, G.Med/MinM density remained borderline significant for predicting a second hip fracture in competing risk analysis (HR = 1.43; CI 0.99–2.06; p = 0.057). Our study revealed that Goutallier classification was less effective than quantitative muscle metrics for predicting hip second fracture in this elderly female cohort. After adjustment for FN aBMD, G.Med/MinM density is a borderline independent predictor of second hip fracture risk. © 2023 The Authors. JBMR Plus published by Wiley Periodicals LLC on behalf of American Society for Bone and Mineral Research.

show abstract

Deep Learning-Based Fully Automated Segmentation of Regional Muscle Volume and Spatial Intermuscular Fat Using CT

Cited by 2 publications

References 32 publications

Quantification of volumetric thigh and paravertebral muscle fat content: comparison of quantitative Dixon (Q-Dixon) magnetic resonance imaging (MRI) with high-speed T2-corrected multiecho MR spectroscopy

Quantification of volumetric thigh and paravertebral muscle fat content: comparison of quantitative Dixon (Q-Dixon) magnetic resonance imaging (MRI) with high-speed T2-corrected multiecho MR spectroscopy

Associations of Quantitative and Qualitative Muscle Parameters With Second Hip Fracture Risk in Older Women: A Prospective Cohort Study

Contact Info

Product

Resources

About