LUCQUE releases annotated Québec LDCT lung-screening data for AI evaluation
Original title: LUCQUE: A lung cancer screening dataset from Québec for reliable AI evaluation
The set has 1,678 baseline studies, 1,776 annotated nodules, and 60 cysts, accessed only via model-to-data.
Researchers present LUCQUE, an annotated low-dose CT lung cancer screening dataset from Québec, hosted on PARADIM for privacy-preserving AI evaluation. It combines scans and clinical information with voxel-level expert segmentations of pulmonary nodules and cysts and Lung-RADS lesion characteristics. User code runs on the platform so data stays on premise. The collection currently has 1,678 baseline studies from 1,678 participants, most classified Lung-RADS 2, with 1,776 nodules and 60 cysts annotated.
- Median nodule volume is 89 mm³; median cyst volume is 1,384 mm³.
- Most studies were classified Lung-RADS 2.
- Access uses PARADIM’s model-to-data approach.
- Authors call it the largest accessible annotated real-world LCS dataset.
From the original article
1 min read at arxiv.orgBACKGROUND: AI-based tools are expected to play a key role in lung cancer screening (LCS). The evaluation of these tools often relied on private datasets or fragmented public datasets with inconsistent availability of clinical data and expert nodule annotations. This has hindered reproducibility, comparability, and independent assessment of AI tools.
By Johanna Topalis · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.