Litcius/Paper detail

Comparison of 2D vs. 3D Unet Organ Segmentation in abdominal 3D CT images

Nico Zettler, André Mastmeyer

2021Computer Science Research Notes15 citationsDOIOpen Access PDF

Abstract

A two-step concept for 3D segmentation on 5 abdominal organs inside volumetric CT images is presented. Firsteach relevant organ’s volume of interest is extracted as bounding box. The extracted volume acts as input for asecond stage, wherein two compared U-Nets with different architectural dimensions re-construct an organ segmen-tation as label mask. In this work, we focus on comparing 2D U-Nets vs. 3D U-Net counterparts. Our initial resultsindicate Dice improvements of about 6% at maximum. In this study to our surprise, liver and kidneys for instancewere tackled significantly better using the faster and GPU-memory saving 2D U-Nets. For other abdominal keyorgans, there were no significant differences, but we observe highly significant advantages for the 2D U-Net interms of GPU computational efforts for all organs under study.

Topics & Concepts

Minimum bounding boxComputer scienceDiceSegmentationFocus (optics)Image segmentationVolume (thermodynamics)Artificial intelligenceComputer visionImage (mathematics)MathematicsGeometryOpticsQuantum mechanicsPhysicsAdvanced Neural Network ApplicationsMedical Image Segmentation TechniquesMedical Imaging Techniques and Applications
Comparison of 2D vs. 3D Unet Organ Segmentation in abdominal 3D CT images | Litcius