LNDb: A Lung Nodule Database on Computed Tomography

TL;DR

This paper introduces LNDb, a new lung nodule CT database designed to improve computer-aided detection and diagnosis, emphasizing radiologist variability and clinical relevance, and evaluates current methods against manual annotations.

Contribution

The paper presents LNDb, a novel lung nodule database that highlights radiologist variability and clinical context, and assesses state-of-the-art detection and characterization methods.

Findings

State-of-the-art methods can match radiologists in follow-up recommendations.

Detection performance decreases on the new LNDb database.

Combining radiologists and AI improves diagnostic consistency.

Abstract

Lung cancer is the deadliest type of cancer worldwide and late detection is the major factor for the low survival rate of patients. Low dose computed tomography has been suggested as a potential screening tool but manual screening is costly, time-consuming and prone to variability. This has fueled the development of automatic methods for the detection, segmentation and characterisation of pulmonary nodules but its application to clinical routine is challenging. In this study, a new database for the development and testing of pulmonary nodule computer-aided strategies is presented which intends to complement current databases by giving additional focus to radiologist variability and local clinical reality. State-of-the-art nodule detection, segmentation and characterization methods are tested and compared to manual annotations as well as collaborative strategies combining multiple radiologists and radiologists and computer-aided systems. It is shown that state-of-the-art methodologies can determine a patient's follow-up recommendation as accurately as a radiologist, though the nodule detection method used shows decreased performance in this database.