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

Abstract

BackgroundManual muscle mass assessment based on Computed Tomography (CT) scans is recognized as a good marker for malnutrition, sarcopenia, and adverse outcomes. However, manual muscle mass analysis is cumbersome and time consuming. An accurate fully automated method is needed. In this study, we evaluate if manual psoas annotation can be substituted by a fully automatic deep learning-based method.MethodsThis study included a cohort of 583 patients with severe aortic valve stenosis planned to undergo Transcatheter Aortic Valve Replacement (TAVR). Psoas muscle area was annotated manually on the CT scan at the height of lumbar vertebra 3 (L3). The deep learning-based method mimics this approach by first determining the L3 level and subsequently segmenting the psoas at that level. The fully automatic approach was evaluated as well as segmentation and slice selection, using average bias 95% limits of agreement, Intraclass Correlation Coefficient (ICC) and within-subject Coefficient of Variation (CV). To evaluate performance of the slice selection visual inspection was performed. To evaluate segmentation Dice index was computed between the manual and automatic segmentations (0 = no overlap, 1 = perfect overlap).ResultsIncluded patients had a mean age of 81 ± 6 and 45% was female. The fully automatic method showed a bias and limits of agreement of −0.69 [−6.60 to 5.23] cm2, an ICC of 0.78 [95% CI: 0.74–0.82] and a within-subject CV of 11.2% [95% CI: 10.2–12.2]. For slice selection, 84% of the selections were on the same vertebra between methods, bias and limits of agreement was 3.4 [−24.5 to 31.4] mm. The Dice index for segmentation was 0.93 ± 0.04, bias and limits of agreement was −0.55 [1.71–2.80] cm2.ConclusionFully automatic assessment of psoas muscle area demonstrates accurate performance at the L3 level in CT images. It is a reliable tool that offers great opportunities for analysis in large scale studies and in clinical applications.

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

“…that this automatic tool is reliable and could substitute manual measurement of body composition. 28 Additionally, for almost all cancer patients, a CT scan is made before treatment. If the L3 slice is not incorporated in the scanned area, for example for head and neck cancer patients, the skeletal muscle area at the C3 slice could be used to calculate the skeletal muscle area at the L3 slice.…”

“…To the best of our knowledge, Quantib Body Composition is the only available software for automatic body composition analysis. Van Erck et al concluded that this automatic tool is reliable and could substitute manual measurement of body composition 28 . Additionally, for almost all cancer patients, a CT scan is made before treatment.…”

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

“…The PET-CT scans were made over a nine-year period and in nine different hospitals, which means there was natural variation in scanner vendor, model, tube current, voxel spacing, slice thickness and radiation dose. We used Quantib Body Composition version 0.2.1 (Quantib BV, Rotterdam, The Netherlands) for automated muscle measurements [ 22 ]. The CT scans were first resampled to a uniform slice thickness of 5mm.…”

Body composition and checkpoint inhibitor treatment outcomes in advanced melanoma: a multicenter cohort study

“…Metrics were obtained using Quantib Body Composition version 0.2.1, a dedicated deep learning segmentation algorithm that has proven to achieve high correspondence to manual segmentations in previous studies [18][19][20]. First, all baseline CT scans were resampled to a slice thickness of 5mm.…”