LNDb (240 files)
LNDb-0001.zip 114.89MB
LNDb-0002.zip 91.65MB
LNDb-0003.zip 108.99MB
LNDb-0004.zip 114.49MB
LNDb-0005.zip 118.99MB
LNDb-0007.zip 92.43MB
LNDb-0008.zip 112.34MB
LNDb-0010.zip 106.83MB
LNDb-0011.zip 121.45MB
LNDb-0013.zip 133.77MB
LNDb-0015.zip 116.84MB
LNDb-0016.zip 116.80MB
LNDb-0017.zip 99.71MB
LNDb-0018.zip 117.25MB
LNDb-0020.zip 111.99MB
LNDb-0021.zip 117.82MB
LNDb-0022.zip 118.72MB
LNDb-0024.zip 125.19MB
LNDb-0025.zip 115.42MB
LNDb-0026.zip 112.61MB
LNDb-0028.zip 130.62MB
LNDb-0031.zip 123.81MB
LNDb-0034.zip 111.32MB
LNDb-0035.zip 102.88MB
LNDb-0037.zip 111.30MB
LNDb-0039.zip 121.49MB
LNDb-0041.zip 125.67MB
LNDb-0043.zip 112.33MB
LNDb-0044.zip 104.17MB
LNDb-0046.zip 112.01MB
LNDb-0048.zip 110.19MB
LNDb-0049.zip 123.93MB
LNDb-0050.zip 119.74MB
LNDb-0051.zip 103.06MB
LNDb-0052.zip 98.47MB
LNDb-0053.zip 105.45MB
LNDb-0055.zip 110.77MB
LNDb-0056.zip 104.78MB
LNDb-0059.zip 110.97MB
LNDb-0060.zip 132.73MB
LNDb-0061.zip 128.68MB
LNDb-0062.zip 111.20MB
LNDb-0063.zip 117.44MB
LNDb-0064.zip 125.39MB
LNDb-0065.zip 116.50MB
LNDb-0066.zip 100.15MB
LNDb-0067.zip 120.41MB
LNDb-0068.zip 115.55MB
LNDb-0069.zip 102.60MB
Too many files! Click here to view them all.
Type: Dataset

title= {LNDb CT scan dataset (training)},
keywords= {},
author= {João Pedrosa and Guilherme Aresta and Carlos Ferreira and Márcio Rodrigues and Patrícia Leitão and André Silva Carvalho and João Rebelo and Eduardo Negrão and Isabel Ramos and António Cunha and Aurélio Campilho},
abstract= {The main goal of this challenge is the automatic classification of chest CT scans according to the 2017 Fleischner society pulmonary nodule guidelines for patient follow-up recommendation. 

The LNDb dataset 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. Further details on patient selection and data acquisition can be consulted on the database description paper.

Each CT scan was read by at least one radiologist at CHUSJ to identify pulmonary nodules and other suspicious lesions. A total of 5 radiologists with at least 4 years of experience reading up to 30 CTs per week participated in the annotation process throughout the project. Annotations were performed in a single blinded fashion, i.e. a radiologist would read the scan once and no consensus or review between the radiologists was performed. Each scan was read by at least one radiologist. The instructions for manual annotation were adapted from LIDC-IDRI. Each radiologist identified the following lesions:

 - nodule ⩾3mm: any lesion considered to be a nodule by the radiologist with greatest in-plane dimension larger or equal to 3mm;
 - nodule <3mm: any lesion considered to be a nodule by the radiologist with greatest in-plane dimension smaller than 3mm;
 - non-nodule: any pulmonary lesion considered not to be a nodule by the radiologist, but that contains features which could make it identifiable as a nodule;

The annotation process varied for the different categories. Nodules ⩾3mm were segmented and subjectively characterized according to LIDC-IDRI (ratings on subtlety, internal structure, calcification, sphericity, margin, lobulation, spiculation, texture and likelihood of malignancy). For a complete description of these characteristics the reader is referred to McNitt-Gray et al.. For nodules <3mm the nodule centroid was marked and subjective assessment of the nodule's characteristics was performed. For non-nodules, only the lesion centroid was marked. Given that different radiologists may have read the same CT and no consensus review was performed, variability in radiologist annotations is expected.

Note that from the 294 CTs of the LNDb dataset, 58 CTs with annotations by at least two radiologists have been withheld for the test set, as well as the corresponding annotations.

terms= {The dataset, or any data derived from it, cannot be given or redistributed under any circumstances to persons not belonging to the registered team. If the data in the dataset is remixed, transformed or built upon, the modified data cannot be redistributed under any circumstances;

The dataset cannot be used for commercial purposed under any circumstances;

Appropriate credit must be given to the authors any time this data is used, independent of purpose. Attribution must be done through citation of the database description paper (https://arxiv.org/abs/1911.08434) or (after publication) to the main challenge publication.},
license= {https://creativecommons.org/licenses/by-nc-nd/4.0/},
superseded= {},
url= {https://lndb.grand-challenge.org/Data/}

Hosted by users:

Send Feedback