A deep learning-based method for relative location prediction in CT scan images

TL;DR

This paper introduces a deep learning regression model using 1D CNNs to accurately predict the relative location of CT scan images, demonstrating superior performance over existing methods with low median and mean absolute errors.

Contribution

The study presents a novel 1D CNN-based regression approach for relative location prediction in CT images, validated on a public dataset with robust cross-validation.

Findings

Median absolute error of 1.04 cm

Mean absolute error of 1.69 cm

Outperforms state-of-the-art techniques

Abstract

Relative location prediction in computed tomography (CT) scan images is a challenging problem. In this paper, a regression model based on one-dimensional convolutional neural networks is proposed to determine the relative location of a CT scan image both robustly and precisely. A public dataset is employed to validate the performance of the study's proposed method using a 5-fold cross validation. Experimental results demonstrate an excellent performance of the proposed model when compared with the state-of-the-art techniques, achieving a median absolute error of 1.04 cm and mean absolute error of 1.69 cm.