datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
NSCLC-PleuralEffusion
NSCLC-PleuralEffusion (PleThora)
Voxel-level thoracic-cavity and pleural-effusion segmentations on the
NSCLC-Radiomics
CT collection. Published by Kiser et al. (Medical Physics 2020) as PleThora,
"Pleural effusion and thoracic cavity segmentations in diseased lungs for
benchmarking chest CT processing pipelines."
Dataset Details
Field
Value
Modality
CT (chest, contrast and non-contrast mixed)
Body part
Chest — thoracic cavity, pleural effusion
Tasks… See the full description on the dataset page: https://huggingface.co/datasets/MedOtter/NSCLC-PleuralEffusion.NSCLC-Radiomics-NIFTI
The Cancer Genome Atlas Ovarian Cancer (NSCLC-Radiomics)
The models featured in this repository uses images from the publicly available NSCLC-Radiomics Dataset.
Download the data from TCIA with Classic Directory Name download option.
Converting Format
Convert DICOM images and segmentation to NIFTI format using SimpleITK, pydicom and pydicom-seg. Run:
user@machine:~/NSCLC-Radiomics-NIFTI$ python convert.py
Segmentations
Images will have one of the following… See the full description on the dataset page: https://huggingface.co/datasets/farrell236/NSCLC-Radiomics-NIFTI.NSCLC-Radiomics-Interobserver1
NSCLC-Radiomics-Interobserver1
Multiple-delineation inter-observer / inter-method variability study of
gross-tumour-volume (GTV) contouring on pre-treatment thoracic CT of
non-small-cell lung cancer (NSCLC). For each tumour, five radiation
oncologists independently delineated the GTV twice — once manually
(vis) and once auto-segmentation-assisted then edited (auto) — giving up
to 10 GTV delineations per patient. The collection exists specifically to
quantify contouring… See the full description on the dataset page: https://huggingface.co/datasets/MedOtter/NSCLC-Radiomics-Interobserver1.NSCLC-THESIS-WSI-DATASET-EMBEDDING
NSCLC-THESIS-WSI-DATASET-EMBEDDING
Public staging mirror for a thesis pipeline (gated acknowledgment before download).One dataset URL — raw slides under wsi/, precomputed features under embeddings/. Pull only the folder you need.
Repo: thanminh01/NSCLC-THESIS-WSI-DATASET-EMBEDDING
WSI upload of all four cohorts is complete. Integrity checks below passed on 2026-08-14. Embeddings are still empty stubs (thesis Stage 2).
Layout
README.md
manifests/
tooling/… See the full description on the dataset page: https://huggingface.co/datasets/okbro1234/NSCLC-THESIS-WSI-DATASET-EMBEDDING.GAPS-NSCLC-preview
GAPS Medical AI Evaluation Dataset - GAPS-NSCLC-preview
Paper: GAPS: A Clinically Grounded, Automated Benchmark for Evaluating AI Clinicians
Code: https://github.com/AQ-MedAI/MedicalAiBenchEval
Dataset Description
The GAPS Medical AI Evaluation Dataset is a comprehensive evaluation system designed specifically for assessing AI models in clinical scenarios. Based on the GAPS (Grounded, Automated, Personalized, Scalable) methodology, this dataset provides both a curated… See the full description on the dataset page: https://huggingface.co/datasets/AQ-MedAI/GAPS-NSCLC-preview.NSCLC-Radiogenomics
NSCLC-Radiogenomics
Non-small cell lung cancer (NSCLC) radiogenomic dataset on TCIA: pretreatment
CT scans of 211 NSCLC patients with matching gene-expression, clinical, and
mutation data. This HuggingFace mirror contains only the 144 patients with
a DICOM SEG of the primary lung tumor (the segmentation-usable subset).
Dataset Details
Field
Value
Modality
CT (pretreatment, multi-vendor, multi-slice-thickness)
Body part
Lung (primary non-small cell… See the full description on the dataset page: https://huggingface.co/datasets/MedOtter/NSCLC-Radiogenomics.lung_sarg_nsclc_radiogenomics
Lung-SARG nsclc_radiogenomics collection
Lung-SARG is a fully open-source and local-first platform
that improves how communities collaborate on open data to diagnose lung cancer and perform epidemiology
on local populations in low and middle income countries.
NSCLC Radiogenomics
Source: https://www.cancerimagingarchive.net/collection/nsclc-radiogenomics/
Medical image biomarkers of cancer promise improvements in patient care through advances in precision… See the full description on the dataset page: https://huggingface.co/datasets/radiogenomics/lung_sarg_nsclc_radiogenomics.nsclc-radiomics
NSCLC-Radiomics Dataset
Dataset Description
The NSCLC-Radiomics dataset for non-small cell lung cancer segmentation. This dataset contains CT scans with dense segmentation annotations.
Dataset Details
Modality: CT
Target: thoracic cavity, lung effusion
Format: NIfTI (.nii.gz)
Dataset Structure
Each sample in the JSONL file contains:
{
"image": "path/to/image.nii.gz",
"mask": "path/to/mask.nii.gz",
"label": ["organ1", "organ2"… See the full description on the dataset page: https://huggingface.co/datasets/MedOtter/nsclc-radiomics.synthetic-nsclc-10kE2.P1-External_cohort_NSCLC_Study
SYNTHETIC EXTERNAL CONTROL COHORT — ADVANCED NSCLC (Phase 2: Full 50,000-Patient Base Cohort)
SYNTHETIC DATA — NOT REAL PATIENT DATA — NOT FOR CLINICAL OR REGULATORY USE
Organization: Auric Grid Laboratory
Data type: 100% synthetic, computer-generated patient-level data
Real patients: None. Clinical evidence: None.
Not for clinical decision-making, patient care, regulatory claims, or estimation
of real-world treatment efficacy/safety.
Run summary… See the full description on the dataset page: https://huggingface.co/datasets/AuricGrid-Laboratory/E2.P1-External_cohort_NSCLC_Study.E2.P3-Clinical_Trial_Feasibility_NSCLC
Auric Grid Synthetic Clinical Trial Feasibility Population for Advanced NSCLC
Dataset ID: AG-NSCLC-CTF-001
Produced by: Auric Grid Laboratory
ENTIRELY SYNTHETIC DATA — NOT REAL PATIENTS, NOT REAL RECRUITMENT RATES, NOT CLINICAL EVIDENCE
This dataset consists entirely of synthetic patient data. It does not represent real patients, actual patient availability, real-world recruitment rates, or clinical evidence.
1. Purpose
This dataset is a large, fully synthetic… See the full description on the dataset page: https://huggingface.co/datasets/AuricGrid-Laboratory/E2.P3-Clinical_Trial_Feasibility_NSCLC.NSCLC_Guidelines