# Automatic Bone Removal in CBCT Scans of the Body Trunk: Thorax, Abdomen, and Pelvis

## TL;DR

This study evaluates a fully automated software for removing bones from CBCT scans of the thorax, abdomen, and pelvis to improve vascular visibility and diagnostic quality.

## Contribution

A modified 3D U-Net enables fully automated bone removal in CBCT scans, validated across multiple body regions with high accuracy.

## Key findings

- The software achieved high accuracy with minimal erosion of non-target structures (B-rating 1.01 ± 0.07, V-rating 1.02 ± 0.13).
- Vessel assessment improved significantly, with VA-rating of 1.0 ± 0 indicating better visualization of contrast material.
- Quantitative metrics showed strong agreement with manual expert delineation (Dice coefficient 0.95 ± 0.02, IoU 0.9 ± 0.03).

## Abstract

To evaluate a fully automated bone removal software for cone beam computed tomography (CBCT) of the thorax, abdomen, and pelvis, enhancing vascular visualization by eliminating bone interference and improving diagnostic quality.

1035 CBCT scans from adults age 66.5 ± 11.9 18–87 years (mean ± std min–max) across nine centers were retrospectively analyzed, divided into training (n = 855, 515 abdomen, 229 pelvis, 111 thorax) and testing (n = 180, 60 for each region, 114 male, 53 female, 13 unknown). Manual bone segmentation was performed using ITK-SNAP. A modified 3D U-Net was trained and clinically evaluated through multireader analysis using ordinal scales from 1 (perfect) to 4 (not usable) bone subtraction (B-rating) and erosion of non-target structures (V-rating) in addition to a vessel assessment (VA-rating), categorizing the subtracted image as “better” (1), “same” (2), or “worse” (3). Quantitative metrics include Sørensen–Dice coefficient and intersection over union (IoU).

The software demonstrated high accuracy with a B-rating of 1.01 ± 0.07 and a V-rating of 1.02 ± 0.13, indicating minimal erosion of non-target structures. A VA-rating of 1.0 ± 0 suggests an improved vessel assessment and the depiction of contrast material deposition, enhancing the diagnostic quality of CBCT images. Quantitative analysis closely matched the manual expert delineation (Sørensen–Dice coefficient 0.95 ± 0.02, IoU of 0.9 ± 0.03).

The software provides robust, fully automated bone removal in CBCT scans. This technology may enhance vascular system visualization without compromising non-target structures, potentially improving the accuracy and efficiency of interventional and diagnostic radiology procedures.

The online version contains supplementary material available at 10.1007/s00270-025-04293-3.