The LIDC-IDRI dataset contains lesion annotations from four experienced thoracic radiologists. LIDC-IDRI contains 1,018 low-dose lung CTs from 1010 lung patients.
Source: A 3D Probabilistic Deep Learning System for Detection and Diagnosis of Lung Cancer Using Low-Dose CT Scans
Image Source: https://thesai.org/Publications/ViewPaper?Volume=8&Issue=10&Code=IJACSA&SerialNo=15
Variants: LIDC-IDRI
This dataset is used in 4 benchmarks:
| Task | Model | Paper | Date |
|---|---|---|---|
| Lung Nodule Classification | MST | Medical Slice Transformer: Improved Diagnosis … | 2024-11-24 |
| Lung Nodule Classification | GVAE | Variational Autoencoders for Feature Exploration … | 2023-11-27 |
| Lung Nodule Classification | NASLung (ours) | Learning Efficient, Explainable and Discriminative … | 2021-01-19 |
| Neural Architecture Search | NASLung (ours) | Learning Efficient, Explainable and Discriminative … | 2021-01-19 |
| Lung Nodule Classification | ProCAN | ProCAN: Progressive Growing Channel Attentive … | 2020-10-29 |
| Lung Nodule Classification | Local-Global | Lung Nodule Classification using Deep … | 2019-04-23 |
| Lung Nodule Classification | Gated-Dilated | Gated-Dilated Networks for Lung Nodule … | 2019-01-01 |
| Lung Nodule Classification | DeepLung | DeepLung: Deep 3D Dual Path … | 2018-01-25 |
Recent papers with results on this dataset: