LUCQUE: A lung cancer screening dataset from Québec for reliable AI evaluation
arXiv cs.AI · 10 Nov 2026, 04:21 AEST
LUCQUE is a new lung cancer screening dataset from Québec designed for reliable AI evaluation. It addresses the limitations of existing datasets by providing comprehensive annotations and maintaining data privacy.
Key facts
- LUCQUE was curated and is hosted on PARADIM, a digital infrastructure supporting DICOM data de-identification, annotation, long-term storage and analysis.
- LUCQUE currently comprises 1,678 LDCT baseline studies from 1,678 participants.
- A total of 1,776 pulmonary nodules and 60 cysts were annotated, with a median volume of $89\, (56,\,159)\, \mathrm{mm}^3$ and $1,384\,(589,\,3793)\, \mathrm{mm}^3$ respectively.
- Compared to publicly available LCS datasets, LUCQUE currently represents the largest accessible annotated real-world LCS dataset.
Read aloud
LUCQUE is a new lung cancer screening dataset from Québec designed for reliable A I evaluation. It addresses the limitations of existing datasets by providing comprehensive annotations and maintaining data privacy. LUCQUE was curated and is hosted on PARADIM, a digital infrastructure supporting DICOM data de-identification, annotation, long-term storage and analysis. LUCQUE currently comprises one thousand six hundred seventy eight LDCT baseline studies from one thousand six hundred seventy eight participants. A total of one thousand seven hundred seventy six pulmonary nodules and sixty cysts were annotated, with a median volume of eighty nine dollars\, fifty six,\,one hundred fifty nine \, \mathrm mm ^three$ and one thousand three hundred eighty four dollars\, five hundred eighty nine,\,three thousand seven hundred ninety three \, \mathrm mm ^three$ respectively. Compared to publicly available LCS datasets, LUCQUE currently represents the largest accessible annotated real-world LCS dataset.
Sources in this cluster
- LUCQUE: A lung cancer screening dataset from Québec for reliable AI evaluation
arXiv cs.AI · 10 Nov 2026, 04:21 AEST