Deep learning-based body composition analysis from whole- body magnetic resonance imaging to predict all-cause mortality in a large western population

被引：2

作者：

Jung, Matthias ^{[1
,2
,3
,12
]}

Raghu, Vineet K. ^{[2
,3
]}

Reisert, Marco ^{[4
,5
]}

Rieder, Hanna ^{[1
]}

Rospleszcz, Susanne ^{[1
,6
]}

Pischon, Tobias ^{[7
]}

Niendorf, Thoralf ^{[8
]}

Kauczor, Hans-Ulrich ^{[9
]}

Voelzke, Henry ^{[10
]}

Billow, Robin ^{[11
]}

Russe, Maximilian F. ^{[1
]}

Schlett, Christopher L. ^{[1
]}

Lu, Michael T. ^{[2
,3
]}

Bamberg, Fabian ^{[1
]}

Weiss, Jakob ^{[1
,2
,3
]}

机构：

[1] Univ Freiburg, Univ Med Ctr Freiburg, Fac Med, Dept Diagnost & Intervent Radiol, Freiburg, Germany

[2] Massachusetts Gen Hosp, Cardiovasc Imaging Res Ctr, Dept Radiol, Massachusetts Gen Hosp, Boston, MA 02114 USA

[3] Harvard Med Sch, Boston, MA USA

[4] Univ Freiburg, Fac Med, Dept Diagnost & Intervent Radiol, Med Phys,Med Ctr, D-79106 Freiburg, Germany

[5] Univ Freiburg, Fac Med, Med Ctr, Dept Stereotact & Funct Neurosurg, D-79106 Freiburg, Germany

[6] Helmholtz Zentrum Munchen, Inst Epidemiol, German Res Ctr Environm Hlth, Neuherberg, Germany

[7] Helmholtz Assoc MDC, Max Delbruck Ctr Mol Med, Mol Epidemiol Res Grp, D-13125 Berlin, Germany

[8] Helmholtz Assoc MDC, Max Delbruck Ctr Mol Med, Berlin Ultrahigh Field Facil, D-13125 Berlin, Germany

[9] Univ Hosp Heidelberg, Inst Pathol, D-69120 Heidelberg, Germany

[10] Ernst Moritz Arndt Univ Greifswald, Inst Community Med, Greifswald, Germany

[11] Ernst Moritz Arndt Univ Greifswald, Univ Med, Univ Med Greifswald, D-17475 Greifswald, Germany

[12] Univ Med Ctr Freiburg, Dept Diagnost & Intervent Radiol, Hugstetter Str 55, D-79106 Freiburg, Germany

来源：

EBIOMEDICINE | 2024年 / 110卷

关键词：

Magnetic resonance imaging; Artificial intelligence; Deep learning; Body composition; Public health; Mortality; SUBCUTANEOUS ADIPOSE-TISSUE; SLICE; OBESITY; FAT;

D O I：

10.1016/j.ebiom.2024.105467

中图分类号：

R5 [内科学];

学科分类号：

1002 ; 100201 ;

摘要：

Background Manually extracted imaging-based body composition measures from a single-slice area (A) have shown associations with clinical outcomes in patients with cardiometabolic disease and cancer. With advances in artificial intelligence, fully automated volumetric (V) segmentation approaches are now possible, but it is unknown whether these measures carry prognostic value to predict mortality in the general population. Here, we developed and tested a deep learning framework to automatically quantify volumetric body composition measures from whole-body magnetic resonance imaging (MRI) and investigated their prognostic value to predict mortality in a large Western population. Methods The framework was developed using data from two large Western European population-based cohort studies, the UK Biobank (UKBB) and the German National Cohort (NAKO). Body composition was defined as (i) subcutaneous adipose tissue (SAT), (ii) visceral adipose tissue (VAT), (iii) skeletal muscle (SM), SM fat fraction (SMFF), and (iv) intramuscular adipose tissue (IMAT). The prognostic value of the body composition measures was assessed in the UKBB using Cox regression analysis. Additionally, we extracted body composition areas for every level of the thoracic and lumbar spine (i) to compare the proposed volumetric whole-body approach to the currently established single-slice area approach on the height of the L3 vertebra and (ii) to investigate the correlation between volumetric and single slice area body composition measures on the level of each vertebral body. Findings In 36,317 UKBB participants (mean age 65.1 +/- 7.8 years, age range 45-84 years; 51.7% female; 1.7% [634/36,471] all-cause deaths; median follow-up 4.8 years), Cox regression revealed an independent association between V-SM (adjusted hazard ratio [aHR]: 0.88, 95% confidence interval [CI] [0.81-0.91], p = 0.00023), V-SMFF (aHR: 1.06, 95% CI [1.02-1.10], p = 0.0043), and V-IMAT (aHR: 1.19, 95% CI [1.05-1.35], p = 0.0056) and mortality after adjustment for demographics (age, sex, BMI, race) and cardiometabolic risk factors (alcohol consumption, smoking status, hypertension, diabetes, history of cancer, blood serum markers). This association was attenuated when using traditional single-slice area measures. Highest correlation coefficients (R) between volumetric and single-slice area body composition measures were located at vertebra L5 for SAT (R = 0.820) and SMFF (R = 0.947), at L3 for VAT (R = 0.892), SM (R = 0.944), and at L4 for IMAT (R = 0.546) (all p < 0.0001). A similar pattern was found in 23,725 NAKO participants (mean age 53.9 +/- 8.3 years, age range 40-75; 44.9% female). Interpretation Automated volumetric body composition assessment from whole-body MRI predicted mortality in a large Western population beyond traditional clinical risk factors. Single slice areas were highly correlated with volumetric body composition measures but their association with mortality attenuated after multivariable adjustment. As volumetric body composition measures are increasingly accessible using automated techniques, identifying high-risk individuals may help to improve personalised prevention and lifestyle interventions.

引用

页数：11

共 33 条

[1] Neeland I.J., Ross R., Despres J.P., Et al., Visceral and ectopic fat, atherosclerosis, and cardiometabolic disease: a position statement, Lancet Diabetes Endocrinol, 7, 9, pp. 715-725, (2019)
[2] Bates D.D.B., Pickhardt P.J., CT-derived body composition assessment as a prognostic tool in oncologic patients: from opportunistic research to artificial intelligence-based clinical implementation, AJR Am J Roentgenol, 219, 4, pp. 671-680, (2022)
[3] Bradshaw P.T., Body composition and cancer survival: a narrative review, Br J Cancer, 130, 2, pp. 176-183, (2024)
[4] Brown J.C., Caan B.J., Prado C.M., Et al., Body composition and cardiovascular events in patients with colorectal cancer: a population-based retrospective cohort study, JAMA Oncol, 5, 7, pp. 967-972, (2019)
[5] Caan B.J., Cespedes Feliciano E.M., Prado C.M., Et al., Association of muscle and adiposity measured by computed tomography with survival in patients with nonmetastatic breast cancer, JAMA Oncol, 4, 6, pp. 798-804, (2018)
[6] Neeland I.J., Poirier P., Despres J.P., Cardiovascular and metabolic heterogeneity of obesity: clinical challenges and implications for management, Circulation, 137, 13, pp. 1391-1406, (2018)
[7] Thomas E.L., Bell J.D., Influence of undersampling on magnetic resonance imaging measurements of intra-abdominal adipose tissue, Int J Obes Relat Metab Disord, 27, 2, pp. 211-218, (2003)
[8] Shen W., Chen J., Gantz M., Velasquez G., Punyanitya M., Heymsfield S.B., A single MRI slice does not accurately predict visceral and subcutaneous adipose tissue changes during weight loss, Obesity (Silver Spring), 20, 12, pp. 2458-2463, (2012)
[9] Faron A., Luetkens J.A., Schmeel F.C., Kuetting D.L.R., Thomas D., Sprinkart A.M., Quantification of fat and skeletal muscle tissue at abdominal computed tomography: associations between single-slice measurements and total compartment volumes, Abdom Radiol (NY), 44, 5, pp. 1907-1916, (2019)
[10] Koitka S., Kroll L., Malamutmann E., Oezcelik A., Nensa F., Fully automated body composition analysis in routine CT imaging using 3D semantic segmentation convolutional neural networks, Eur Radiol, 31, 4, pp. 1795-1804, (2021)

← 1 2 3 4 →