Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

LiverUSRecon: Automatic 3D Reconstruction and Volumetry of the Liver with a Few Partial Ultrasound Scans

Kaushalya Sivayogaraj, Sahan T. Guruge, Udari Liyanage, Jeevani Udupihille, Saroj Jayasinghe, Gerard Fernando, Ranga Rodrigo, M. Rukshani Liyanaarachchi

TL;DR

This is the first automatic liver volumetry system using a few incomplete US scans given a set of CT scans of livers for SSM, and is statistically much closer to the volume estimated using CT scans than the volume computed using Childs' method by radiologists.

Abstract

3D reconstruction of the liver for volumetry is important for qualitative analysis and disease diagnosis. Liver volumetry using ultrasound (US) scans, although advantageous due to less acquisition time and safety, is challenging due to the inherent noisiness in US scans, blurry boundaries, and partial liver visibility. We address these challenges by using the segmentation masks of a few incomplete sagittal-plane US scans of the liver in conjunction with a statistical shape model (SSM) built using a set of CT scans of the liver. We compute the shape parameters needed to warp this canonical SSM to fit the US scans through a parametric regression network. The resulting 3D liver reconstruction is accurate and leads to automatic liver volume calculation. We evaluate the accuracy of the estimated liver volumes with respect to CT segmentation volumes using RMSE. Our volume computation is statistically much closer to the volume estimated using CT scans than the volume computed using Childs' method by radiologists: p-value of 0.094 (>0.05) says that there is no significant difference between CT segmentation volumes and ours in contrast to Childs' method. We validate our method using investigations (ablation studies) on the US image resolution, the number of CT scans used for SSM, the number of principal components, and the number of input US scans. To the best of our knowledge, this is the first automatic liver volumetry system using a few incomplete US scans given a set of CT scans of livers for SSM.

LiverUSRecon: Automatic 3D Reconstruction and Volumetry of the Liver with a Few Partial Ultrasound Scans

TL;DR

This is the first automatic liver volumetry system using a few incomplete US scans given a set of CT scans of livers for SSM, and is statistically much closer to the volume estimated using CT scans than the volume computed using Childs' method by radiologists.

Abstract

3D reconstruction of the liver for volumetry is important for qualitative analysis and disease diagnosis. Liver volumetry using ultrasound (US) scans, although advantageous due to less acquisition time and safety, is challenging due to the inherent noisiness in US scans, blurry boundaries, and partial liver visibility. We address these challenges by using the segmentation masks of a few incomplete sagittal-plane US scans of the liver in conjunction with a statistical shape model (SSM) built using a set of CT scans of the liver. We compute the shape parameters needed to warp this canonical SSM to fit the US scans through a parametric regression network. The resulting 3D liver reconstruction is accurate and leads to automatic liver volume calculation. We evaluate the accuracy of the estimated liver volumes with respect to CT segmentation volumes using RMSE. Our volume computation is statistically much closer to the volume estimated using CT scans than the volume computed using Childs' method by radiologists: p-value of 0.094 (>0.05) says that there is no significant difference between CT segmentation volumes and ours in contrast to Childs' method. We validate our method using investigations (ablation studies) on the US image resolution, the number of CT scans used for SSM, the number of principal components, and the number of input US scans. To the best of our knowledge, this is the first automatic liver volumetry system using a few incomplete US scans given a set of CT scans of livers for SSM.
Paper Structure (6 sections, 2 equations, 4 figures, 3 tables)

This paper contains 6 sections, 2 equations, 4 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Methodology
  3. Experiments and Results
  4. Conclusion
  5. Acknowledgments.
  6. Disclosure of Interests.

Figures (4)

  • Figure 1: The proposed framework: binary masks of the three US slices generate the shape parameters through the parametric regression MLP. These warp the SSM to generate the 3D liver reconstruction.
  • Figure 2: US segmentation and 3D reconstruction results: Three input US sagittal plane images, corresponding segmentations, and 3D liver reconstructions using the shape parameters for three subjects.
  • Figure 3: Three visualizations (anterior, posterior and absolute point to point distance) of reconstruction accuracy of two livers: ground truth (yellow , liver models generated from CT segmentation) overlaps well with our results (green ).
  • Figure 4: Box plot of liver volumes calculated from Childs' method, CT segmentation, and the proposed method: Childs' method has outliers, but the proposed method has no outliers and its liver volume distribution falls within CT segmentation's liver volume distribution.