Development of an algorithm for medical image segmentation of bone tissue in interaction with metallic implants

TL;DR

This study develops a U-Net based AI algorithm for segmenting bone tissue in microtomography images with metallic implants, achieving high accuracy and providing more precise volume estimates than traditional methods.

Contribution

Introduces a novel AI segmentation algorithm tailored for bone-implant images, demonstrating high accuracy and improved volume estimation over conventional techniques.

Findings

Achieved around 98% network accuracy.

Estimated bone volume at 15% of traditional overestimations.

Method shows good performance with potential for further improvement.

Abstract

This preliminary study focuses on the development of a medical image segmentation algorithm based on artificial intelligence for calculating bone growth in contact with metallic implants. %as a result of the problem of estimating the growth of new bone tissue due to artifacts. %the presence of various types of distortions and errors, known as artifacts. Two databases consisting of computerized microtomography images have been used throughout this work: 100 images for training and 196 images for testing. Both bone and implant tissue were manually segmented in the training data set. The type of network constructed follows the U-Net architecture, a convolutional neural network explicitly used for medical image segmentation. In terms of network accuracy, the model reached around 98\%. Once the prediction was obtained from the new data set (test set), the total number of pixels belonging to bone tissue was calculated. This volume is around 15\% of the volume estimated by conventional techniques, which are usually overestimated. This method has shown its good performance and results, although it has a wide margin for improvement, modifying various parameters of the networks or using larger databases to improve training.