Segmentation of Defective Skulls from CT Data for Tissue Modelling

TL;DR

This paper introduces an advanced CNN-based method for automatic segmentation of defective skulls from CT data, improving accuracy and reducing artifacts for better tissue modeling and implant design.

Contribution

It demonstrates how encoder-decoder architectures, boundary terms, and graph-cut optimization enhance skull segmentation accuracy in complex cases.

Findings

Encoder-decoder CNNs outperform simple patch-based models.

Adding boundary terms reduces segmentation artifacts.

Both 2D and 3D CNNs achieve clinically acceptable segmentation.

Abstract

In this work we present a method of automatic segmentation of defective skulls for custom cranial implant design and 3D printing purposes. Since such tissue models are usually required in patient cases with complex anatomical defects and variety of external objects present in the acquired data, most deep learning-based approaches fall short because it is not possible to create a sufficient training dataset that would encompass the spectrum of all possible structures. Because CNN segmentation experiments in this application domain have been so far limited to simple patch-based CNN architectures, we first show how the usage of the encoder-decoder architecture can substantially improve the segmentation accuracy. Then, we show how the number of segmentation artifacts, which usually require manual corrections, can be further reduced by adding a boundary term to CNN training and by globally optimizing the segmentation with graph-cut. Finally, we show that using the proposed method, 3D segmentation accurate enough for clinical application can be achieved with 2D CNN architectures as well as their 3D counterparts.