Multi-scale analysis of lung computed tomography images

TL;DR

This paper presents a multi-scale computer-aided detection system for identifying lung nodules in low-dose CT images, combining segmentation, filtering, and neural techniques to improve accuracy.

Contribution

It introduces a novel multi-scale approach integrating segmentation, filtering, and neural methods for lung nodule detection in low-dose CT scans.

Findings

Effective nodule detection demonstrated on low-dose CT datasets.

Improved false positive reduction using multi-scale neural techniques.

System performance evaluated with FROC curves.

Abstract

A computer-aided detection (CAD) system for the identification of lung internal nodules in low-dose multi-detector helical Computed Tomography (CT) images was developed in the framework of the MAGIC-5 project. The three modules of our lung CAD system, a segmentation algorithm for lung internal region identification, a multi-scale dot-enhancement filter for nodule candidate selection and a multi-scale neural technique for false positive finding reduction, are described. The results obtained on a dataset of low-dose and thin-slice CT scans are shown in terms of free response receiver operating characteristic (FROC) curves and discussed.