Evaluation of a Fully Automatic Deep Learning-Based Method for the Measurement of Psoas Muscle Area

Development and validation of a reliable method for automated measurements of psoas muscle volume in CT scans using deep learning-based segmentation: a cross-sectional study

OBJECTIVES

We aimed to develop an automated method for measuring the volume of the psoas muscle using CT to aid sarcopenia research efficiently.

METHODS

We used a data set comprising the CT scans of 520 participants who underwent health check-ups at a health promotion centre. We developed a psoas muscle segmentation model using deep learning in a three-step process based on the nnU-Net method. The automated segmentation method was evaluated for accuracy, reliability, and time required for the measurement.

RESULTS

The Dice similarity coefficient was used to compare the manual segmentation with automated segmentation; an average Dice score of 0.927 ± 0.019 was obtained, with no critical outliers. Our automated segmentation system had an average measurement time of 2 min 20 s ± 20 s, which was 48 times shorter than that of the manual measurement method (111 min 6 s ± 25 min 25 s).

CONCLUSION

We have successfully developed an automated segmentation method to measure the psoas muscle volume that ensures consistent and unbiased estimates across a wide range of CT images.

Pediatric body composition based on automatic segmentation of computed tomography scans: a pilot study

BACKGROUND

Body composition during childhood may predispose to negative health outcomes later in life. Automatic segmentation may assist in quantifying pediatric body composition in children.

OBJECTIVE

To evaluate automatic segmentation for body composition on pediatric computed tomography (CT) scans and to provide normative data on muscle and fat areas throughout childhood using automatic segmentation.

MATERIALS AND METHODS

In this pilot study, 537 children (ages 1-17 years) who underwent abdominal CT after high-energy trauma at a Dutch tertiary center (2002-2019) were retrospectively identified. Of these, the CT images of 493 children (66% boys) were used to establish normative data. Muscle (psoas, paraspinal and abdominal wall) and fat (subcutaneous and visceral) areas were measured at the third lumbar vertebral (L3) level by automatic segmentation. A representative subset of 52 scans was also manually segmented to evaluate the performance of automatic segmentation.

RESULTS

For manually-segmented versus automatically-segmented areas (52 scans), mean Dice coefficients were high for muscle (0.87-0.90) and subcutaneous fat (0.88), but lower for visceral fat (0.60). In the control group, muscle area was comparable for both sexes until the age of 13 years, whereafter, boys developed relatively more muscle. From a young age, boys were more prone to visceral fat storage than girls. Overall, boys had significantly higher visceral-to-subcutaneous fat ratios (median 1.1 vs. 0.6, P<0.01) and girls higher fat-to-muscle ratios (median 1.0 vs. 0.7, P<0.01).

CONCLUSION

Automatic segmentation of L3-level muscle and fat areas allows for accurate quantification of pediatric body composition. Using automatic segmentation, the development in muscle and fat distribution during childhood (in otherwise healthy) Dutch children was demonstrated.

Optimizing carboplatin dosing by an improved prediction of carboplatin clearance using a CT-enhanced estimate of renal function

AIMS

Carboplatin is generally dosed based on a modified Calvert formula, in which the Cockcroft-Gault-based creatinine clearance (CRCL) is used as proxy for the glomerular filtration rate (GFR). The Cockcroft-Gault formula (CG) overpredicts CRCL in patients with an aberrant body composition. The CT-enhanced estimate of RenAl FuncTion (CRAFT) was developed to compensate for this overprediction. We aimed to evaluate whether carboplatin clearance is better predicted by CRCL based on the CRAFT compared to the CG.

METHODS

Data of four previously conducted trials was used. The CRAFT was divided by serum creatinine to derive CRCL. The difference between CRAFT- and CG-based CRCL was assessed by population pharmacokinetic modelling. Furthermore, the difference in calculated carboplatin dose was assessed in a heterogeneous dataset.

RESULTS

In total, 108 patients were included in the analysis. Addition of the CRAFT- and CG-based CRCL as covariate on carboplatin clearance led, respectively, to an improved model fit with a 26-point drop in objective function value and a worsened model fit with an increase of 8 points. In 19 subjects with serum creatinine <50 μmol/L, the calculated carboplatin dose was 233 mg higher using the CG.

CONCLUSIONS

Carboplatin clearance is better predicted by CRAFT vs. CG-based CRCL. In subjects with low serum creatinine, the calculated carboplatin dose using CG exceeds the dose using CRAFT, which might explain the need for dose capping when using the CG. Therefore, the CRAFT might be an alternative for dose capping while still dosing accurately.

The association of radiologic body composition parameters with clinical outcomes in level-1 trauma patients

PURPOSE

The present study aims to assess whether CT-derived muscle mass, muscle density, and visceral fat mass are associated with in-hospital complications and clinical outcome in level-1 trauma patients.

METHODS

A retrospective cohort study was conducted on adult patients admitted to the University Medical Center Utrecht following a trauma between January 1 and December 31, 2017. Trauma patients aged 16 years or older without severe neurological injuries, who underwent a CT that included the abdomen within 7 days of admission, were included. An artificial intelligence (AI) algorithm was used to retrieve muscle areas to calculate the psoas muscle index and to retrieve psoas muscle radiation attenuation and visceral fat (VF) area from axial CT images. Multivariable logistic and linear regression analyses were performed to assess associations between body composition parameters and outcomes.

RESULTS

A total of 404 patients were included for analysis. The median age was 49 years (interquartile range [IQR] 30-64), and 66.6% were male. Severe comorbidities (ASA 3-4) were seen in 10.9%, and the median ISS was 9 (IQR 5-14). Psoas muscle index was not independently associated with complications, but it was associated with ICU admission (odds ratio [OR] 0.79, 95% confidence interval [CI] 0.65-0.95), and an unfavorable Glasgow Outcome Scale (GOS) score at discharge (OR 0.62, 95% CI 0.45-0.85). Psoas muscle radiation attenuation was independently associated with the development of any complication (OR 0.60, 95% CI 0.42-0.85), pneumonia (OR 0.63, 95% CI 0.41-0.96), and delirium (OR 0.49, 95% CI 0.28-0.87). VF was associated with developing a delirium (OR 1.95, 95% CI 1.12-3.41).

CONCLUSION

In level-1 trauma patients without severe neurological injuries, automatically derived body composition parameters are able to independently predict an increased risk of specific complications and other poor outcomes.

Computed tomography measured epicardial adipose tissue and psoas muscle attenuation: new biomarkers to predict major adverse cardiac events and mortality in patients with heart disease and critically ill patients. Part II: Psoas muscle area and density

Sarcopenia is a syndrome characterised by loss of skeletal muscle mass, loss of muscle quality, and reduced muscle strength, resulting in low performance. Sarcopenia has been associated with increased mortality and complications after medical interventions. In daily clinical practice, sarcopenia is assessed by clinical assessment of muscle strength and performance tests and muscle mass quantification by dual-energy X-ray absorptio-metry (DXA) or bioelectrical impedance analysis (BIA). Assessment of the skeletal muscle quantity and quality obtained by abdominal computed tomography (CT) has gained interest in the medical community, as abdominal CT is performed for various medical reasons, and quantification of the psoas and skeletal muscle can be performed without additional radiation load and dye administration. The definitions of CT-derived skeletal muscle mass quantification are briefly reviewed: psoas muscle area (PMA), skeletal muscle area (SMA), and transverse psoas muscle thickness (TPMT). We explain how CT attenuation coefficient filters are used to determine PMA and SMA, resulting in the psoas muscle index (PMI) and skeletal muscle index (SMI), respectively, after indexation to body habitus. Psoas muscle density (PMD), a biomarker for skeletal muscle quality, can be assessed by measuring the psoas muscle CT attenuation coefficient, expressed in Hounsfield units. The concept of low-density muscle (LDM) is explained. Finally, we review the medical literature on PMI and PMD as predictors of adverse outcomes in patients undergoing trauma or elective major surgery, transplantation, and in patients with cardiovascular and internal disease. PMI and PMD are promising new biomarkers predicting adverse outcomes after medical interventions.

Do body composition parameters correlate with response to targeted therapy in ER+/HER2- metastatic breast cancer patients? Role of sarcopenia and obesity

Purpose

To investigate the association between body composition parameters, sarcopenia, obesity and prognosis in patients with metastatic ER+/HER2- breast cancer under therapy with cyclin-dependent kinase (CDK) 4/6 inhibitors.

Methods

92 patients with biopsy-proven metastatic ER+/HER2- breast cancer, treated with CDK 4/6 inhibitors between 2018 and 2021 at our center, were included in this retrospective analysis. Visceral Adipose Tissue (VAT), Subcutaneous Adipose Tissue (SAT) and Skeletal Muscle Index (SMI) were measured before starting therapy with CDK 4/6 inhibitors (Palbociclib, Abemaciclib or Ribociclib). Measurements were performed on a computed tomography-derived abdominal image at third lumbar vertebra (L3) level by an automatic dedicated software (Quantib body composition^®, Rotterdam, Netherlands). Visceral obesity was defined as a VAT area > 130 cm². Sarcopenia was defined as SMI < 40 cm²/m². Changes in breast lesion size were evaluated after 6 months of treatment. Response to therapy was assessed according to RECIST 1.1 criteria. Spearman’s correlation and χ² analyses were performed.

Results

Out of 92 patients, 30 were included in the evaluation. Of the 30 patients (mean age 53 ± 12 years), 7 patients were sarcopenic, 16 were obese, while 7 patients were neither sarcopenic nor obese. Statistical analyses showed that good response to therapy was correlated to higher SMI values (p < 0.001), higher VAT values (p = 0.008) and obesity (p = 0.007); poor response to therapy was correlated to sarcopenia (p < 0.001). Moreover, there was a significant association between sarcopenia and menopause (p = 0.021) and between sarcopenia and the persistence of axillary lymphadenopathies after treatment (p = 0.003), while the disappearance of axillary lymphadenopathies was associated with obesity (p = 0.028).

Conclusions

There is a growing interest in body composition, especially in the field of breast cancer. Our results showed an interesting correlation between sarcopenia and progression of disease, and demonstrated that VAT can positively influence the response to targeted therapy with CDK 4/6 inhibitors. Larger-scale studies are needed to confirm these preliminary results.

Clinical Relevance

Sarcopenia and obesity seem to predict negative outcomes in many oncologic entities. Their prevalence and impact in current breast cancer care are promising but still controversial.

CT-Diagnosed Sarcopenia and Cardiovascular Biomarkers in Patients Undergoing Transcatheter Aortic Valve Replacement: Is It Possible to Predict Muscle Loss Based on Laboratory Tests?—A Multicentric Retrospective Analysis

Background: Patients with severe aortic valve stenosis (AS) often present with heart failure and sarcopenia. Sarcopenia, described as progressive degradation of skeletal muscle mass, has frequently been implicated as a cause of increased mortality, prolonged hospitalization and generalized poor outcome after transcatheter aortic valve replacement (TAVR). At present, sarcopenia is defined by the European Working Group on Sarcopenia in Older People (EWGSOP) based on clinical examination criteria and radiological imaging. The aim of the present study was to compare patients with Computed Tomography (CT)-diagnosed sarcopenia with regard to the expression of cardiovascular biomarkers in order to obtain additional, laboratory-chemical information. Methods: A total of 179 patients with severe AS were included in this retrospective study. Sarcopenia was determined via CT by measurement of the psoas muscle area (PMA), which was indexed to body surface area (PMAi). According to previous studies, the lowest tertile was defined as sarcopenic. Patients with (59/179) and without sarcopenia (120/179) in the overall cohort were compared by gender-specific cut-offs with regard to the expression of cardiovascular biomarkers such as brain natriuretic peptide (BNP), soluble suppression of tumorigenicity-2 (sST2), growth/differentiation of factor-15 (GDF-15), heart-type fatty-acid binding protein (H-FABP), insulin like growth factor binding protein 2 (IGF-BP2) and soluble urokinase-type plasminogen activator receptor (suPAR). Additionally, binary logistic regression analyses were calculated to detect possible predictors of the presence of sarcopenia. Results: No statistical differences regarding one-year survival could be detected between sarcopenic and non-sarcopenic patients in survival curves (log rank test p = 0.179). In the entire cohort, only BNP and hemoglobin (HB) showed a statistically significant difference, with only HB emerging as a relevant predictor for the presence of sarcopenia after binary logistic regression analysis (p = 0.015). No relevant difference in biomarker expression could be found in the male cohort. Regarding the female cohort, statistically significant differences were found in BNP, HB and hematocrit (HK). In binary logistic regression, however, none of the investigated criteria could be related to sarcopenia. Conclusion: Regardless of gender, patients with imaging-based muscle degradation did not demonstrate significantly different cardiovascular biomarker expression compared to those without it.

The Association between Muscle Quantity and Overall Survival Depends on Muscle Radiodensity: A Cohort Study in Non-Small-Cell Lung Cancer Patients

The prognostic value of CT-derived muscle quantity for overall survival (OS) in patients with non-small-cell lung cancer (NSCLC) is uncertain due to conflicting evidence. We hypothesize that increased muscle quantity is associated with better OS in patients with normal muscle radiodensity but not in patients with fatty degeneration of muscle tissue and low muscle radiodensity. We performed an observational cohort study in NSCLC patients treated with radiotherapy. A deep learning algorithm was used to measure muscle quantity as psoas muscle index (PMI) and psoas muscle radiodensity (PMD) on computed tomography. The potential interaction between PMI and PMD for OS was investigated using Cox proportional-hazards regression. Baseline adjustment variables were age, sex, histology, performance score and body mass index. We investigated non-linear effects of continuous variables and imputed missing values using multiple imputation. We included 2840 patients and observed 1975 deaths in 5903 patient years. The average age was 68.9 years (standard deviation 10.4, range 32 to 96) and 1692 patients (59.6%) were male. PMI was more positively associated with OS for higher values of PMD (hazard ratio for interaction 0.915; 95% confidence interval 0.861–0.972; p-value 0.004). We found evidence that high muscle quantity is associated with better OS when muscle radiodensity is higher, in a large cohort of NSCLC patients treated with radiotherapy. Future studies on the association between muscle status and OS should accommodate this interaction in their analysis for more accurate and more generalizable results.