Abstract
To explore the feasibility of a fully automated workflow for whole-body volumetric analyses based on deep reinforcement learning (DRL) and to investigate the influence of contrast-phase (CP) and slice thickness (ST) on the calculated organ volume. This retrospective study included 431 multiphasic CT datasets—including three CP and two ST reconstructions for abdominal organs—totaling 10,508 organ volumes (10,344 abdominal organ volumes: liver, spleen, and kidneys, 164 lung volumes). Whole-body organ volumes were determined using multi-scale DRL for 3D anatomical landmark detection and 3D organ segmentation. Total processing time for all volumes and mean calculation time per case were recorded. Repeated measures analyses of variance (ANOVA) were conducted to test for robustness considering CP and ST. The algorithm calculated organ volumes for the liver, spleen, and right and left kidney (mean volumes in milliliter (interquartile range), portal venous CP, 5 mm ST: 1868.6 (1426.9, 2157.8), 350.19 (45.46, 395.26), 186.30 (147.05, 214.99) and 181.91 (143.22, 210.35), respectively), and for the right and left lung (2363.1 (1746.3, 2851.3) and 1950.9 (1335.2, 2414.2)). We found no statistically significant effects of the variable contrast phase or the variable slice thickness on the organ volumes. Mean computational time per case was 10 seconds. The evaluated approach, using state-of-the art DRL, enables a fast processing of substantial amounts irrespective of CP and ST, allowing building up organ-specific volumetric databases. The thus derived volumes may serve as reference for quantitative imaging follow-up.
Highlights
Accurate whole-body organ volumetric analyses could have a substantial impact on clinical practice
Patients were only included in the evaluation if nc, art, and pv phases with both 1.5-mm and 5-mm slice thickness reconstructions and—if available— pv series covering the lung in 5-mm slice thickness were available, and the parenchyma of all organs of interest was covered on all series
We found no significant effects of the between-group variable contrast phase neither of the within-subject variable
Summary
Accurate whole-body organ volumetric analyses could have a substantial impact on clinical practice. But are not limited to, imaging of patients with chronic hepatitis [1], nonalcoholic fatty liver disease [2], acute liver failure [3], change in kidney volume after kidney transplant [4], assessing splenomegaly [5] , or assessing lung volumes after reduction for emphysema [6]. A potential solution is the use of artificial intelligence, more precisely deep reinforcement learning (DRL) using 3D landmark detection [10] With this technology, whole body organ volumetric analyses can be derived in a short amount of time. Applying this to liver volumetric analyses has recently been shown to yield an excellent agreement with human readers [9].
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
