LNDb Dataset

The Lung Nodule Database (LNDb) was developed as an external dataset complimentary to LIDCIDRI. The publication of this database gives continuity to LIDC-IDRI and allows the community to perform an external and comparable validation of proposed computer-aided diagnosis (CAD) systems.

The LNDb contains 294 CT scans collected retrospectively at the Centro Hospitalar e Universitário de São João (CHUSJ) in Porto, Portugal between 2016 and 2018. All data was acquired under approval from the CHUSJ Ethical Commitee and was anonymised prior to any analysis to remove personal information except for patient birth year and gender.

The database served as the basis for the Grand Challenge on automatic lung cancer patient management, or LNDb challenge.

THIS DATASET IS PUBLICALLY AVAILABLE UNDER A CREATIVE COMMONS CC-BY LICENSE (ATTRIBUTION)ESSENCIALLY, YOU ARE GRANTED ACCESS TO THE DATASET FOR USE IN YOUR RESEARCH AS LONG AS YOU CREDIT OUR WORK/PUBLICATIONS(*)

(*) Pedrosa, João, et al. "LNDb: a lung nodule database on computed tomography." arXiv preprint arXiv:1911.08434 (2019).

(*) Pedrosa, João, et al. "LNDb challenge on automatic lung cancer patient management." Medical image analysis 70 (2021): 102027.

DATASET Publication (Nov 20, 2020).

DATASET UPDATES (at Zenodo):

- Version v1 (Jun 4, 2022): Repository is created; 

- Version v2 (Oct 6, 2022): Test files are added; 

- Version v3 (Sep 1, 2023): The LNDb also had medical reports that had not yet been released. We have sought to establish a matching between annotated nodules and those described textually. Then, the following files have been added:i) chars_trainNodules.csv: the characteristics of nodules annotated by radiologists;ii) report.csv: tabular data from medical reports of the CT scans in the dataset;iii) allNods.csv: a list of all nodules manually annotated or described in textual reports;iv) rad2Fleischner.csv: a list of image-annotated nodules;v) text2Fleischner.csv: a list of those nodules reported in the medical reports.

- Version v4 (Sep 15, 2023):: A 'help.txt' file has been added to provide clarity on the variables within the files added in version 3 of the dataset. The license was updated, and version control has been documented within the description section to comprehensively record all modifications made during ongoing updates to the dataset.