Towards whole-body CT Bone Segmentation

TL;DR

This paper presents a deep learning-based method for automatic whole-body bone segmentation from CT scans, achieving high accuracy and efficiency, which is crucial for disease assessment and treatment planning.

Contribution

A novel UNet-inspired architecture tailored for whole-body bone segmentation in CT images, demonstrating high accuracy on a large in-house dataset.

Findings

Dice score of 0.96 on the dataset

IOU of 0.94 achieved

Effective for disease staging and lesion localization

Abstract

Bone segmentation from CT images is a task that has been worked on for decades. It is an important ingredient to several diagnostics or treatment planning approaches and relevant to various diseases. As high-quality manual and semi-automatic bone segmentation is very time-consuming, a reliable and fully automatic approach would be of great interest in many scenarios. In this publication, we propose a UNet inspired architecture to address the task using Deep Learning. We evaluated the approach on whole-body CT scans of patients suffering from multiple myeloma. As the disease decomposes the bone, an accurate segmentation is of utmost importance for the evaluation of bone density, disease staging and localization of focal lesions. The method was evaluated on an in-house data-set of 6000 2D image slices taken from 15 whole-body CT scans, achieving a dice score of 0.96 and an IOU of 0.94.