-
Notifications
You must be signed in to change notification settings - Fork 11
idc_new_data_v17_to_v24.md
Andrey Fedorov edited this page May 29, 2026
·
1 revision
Generated: 2026-05-29
| Prompt | summarize the new data in IDC since v17 |
| Skill |
imaging-data-commons v1.6.4 |
| Model | claude-sonnet-4-6 |
| IDC data version | v24 |
| idc-index | 0.12.3 |
| Version | New Collections | New Patients | New Series | Size Added |
|---|---|---|---|---|
| v18 | 4 | 26,934 | 384,653 | 15.0 TB |
| v19 | 45 | 11,172 | 42,103 | 12.5 TB |
| v20 | 27 | 7,679 | 12,363 | 6.7 TB |
| v21 | 10 | 1,987 | 3,393 | 1.9 TB |
| v22 | 25 | 8,266 | 14,473 | 5.6 TB |
| v23 | 36 | 9,775 | 27,709 | 0.5 TB |
| v24 | 16 | 6,039 | 39,872 | 5.7 TB |
| Total | 163 | 71,852 | 524,566 | ~47 TB |
| collection_id | Cancer Types | Patients | Supporting Data |
|---|---|---|---|
advanced_mri_breast_lesions |
Breast Cancer | 632 | Clinical |
| collection_id | Cancer Types | Patients | Supporting Data |
|---|---|---|---|
ccdi_mci |
Various | 4,407 | — |
cmb_aml |
Acute Myeloid Leukemia | 11 | Clinical |
cmb_crc |
Colorectal Cancer | 74 | Clinical |
cmb_gec |
Gastroesophageal Cancer | 16 | Clinical |
cmb_lca |
Lung Cancer | 162 | Clinical |
cmb_mel |
Melanoma | 54 | Clinical |
cmb_mml |
Multiple Myeloma | 138 | Clinical |
cmb_pca |
Prostate Cancer | 51 | Clinical |
gtex |
Non-diseased (controls) | 971 | Clinical, Genomics |
| collection_id | Cancer Types | Patients | Supporting Data |
|---|---|---|---|
cmb_brca |
Breast Invasive Carcinoma | 78 | Clinical |
cmb_ov |
Ovarian Cancer | 31 | Clinical |
mediastinal_lymph_node_seg |
Multi-cancer (11 types) | 513 | Clinical |
spine_mets_ct_seg |
Spine mets, 9 cancer types | 55 | Clinical |
| collection_id | Cancer Types | Patients | Supporting Data |
|---|---|---|---|
varepop_apollo |
8 types (esophageal, HNSCC, lung, pancreatic, thymoma, colon) | 41 | — |
| collection_id | Cancer Types | Patients | Supporting Data |
|---|---|---|---|
bonemarrowwsi_pediatricleukemia |
Leukemia (WSI) | 245 | Clinical |
cbis_ddsm |
Breast Cancer / Non-Cancer (mammography) | 6,671 | Image Analyses |
cc_radiomics_phantom |
Lung Phantom | 17 | Image Analyses |
cc_radiomics_phantom_2 |
Phantom | 251 | — |
cc_radiomics_phantom_3 |
Head/Chest/Phantom | 95 | Image Analyses |
ct4harmonization_multicentric |
Liver Phantom | 1 | Software/Source Code |
qiba_ct_liver_phantom |
Liver Phantom | 3 | Image Analyses |
qin_breast_02 |
Breast Cancer | 13 | Clinical |
qin_pet_phantom |
Phantom | 2 | — |
rider_phantom_mri |
Phantom | 10 | — |
rider_phantom_pet_ct |
Phantom | 20 | Image Analyses |
| collection_id | Cancer Types | Patients | Supporting Data |
|---|---|---|---|
catch |
Melanoma, SCC, MPNST, skin fibrous histiocytoma (WSI) | 282 | — |
cddp_eagle_1 |
Lung Adenocarcinoma | 49 | — |
cgci_blgsp |
Burkitt Lymphoma | 388 | — |
cgci_htmcp_cc |
Cervical Squamous Cell Carcinoma | 211 | — |
cgci_htmcp_dlbcl |
Diffuse Large B-Cell Lymphoma | 43 | — |
cgci_htmcp_lc |
Non-Small Cell Carcinoma (lung) | 27 | — |
cptac_stad |
Stomach Adenocarcinoma | 20 | Clinical, Genomics, Proteomics |
eay131 |
NCI-MATCH basket trial, 47 cancer types | 2,813 | Clinical |
hcmi_cmdc |
7 cancer types across 14 body sites | 382 | — |
htan_tnp_sardana |
Colon Mucinous Adenocarcinoma | 1 | — |
ldct_and_projection_data |
Lung Cancer (low-dose CT + raw projections) | 200 | — |
pdxnet |
PDX Network, 29 cancer types | 919 | Clinical, Image Analyses, Genomics |
psma_pet_ct_lesions |
Prostate Cancer (PSMA PET/CT + segmentations) | 378 | Image Analyses |
spinal_multiple_myeloma_seg |
Multiple Myeloma (spine segmentations) | 67 | Clinical |
uw_cirp_mouse_pet_ct_nsclc |
Lung SCC (mouse model, PET/CT) | 14 | Image Analyses, Clinical |
| Version | analysis_result_id | Content | Series | Size |
|---|---|---|---|---|
| v18 | TotalSegmentator-CT-Segmentations |
Multi-organ auto-segmentations (TotalSegmentator) | 378,153 | 14.3 TB |
| v18 | RMS-Mutation-Prediction-Expert-Annotations |
Expert annotations for RMS mutation prediction | 193 | 7 GB |
| v19 | Pan-Cancer-Nuclei-Seg-DICOM |
Pan-cancer nuclei segmentations (pathology WSI) | 12,149 | 7.0 TB |
| v19 | Pancreas-CT-SEG |
Pancreas CT segmentations | 80 | 0.2 GB |
| v23 | Lung-PET-CT-Dx-Annotations |
Lung PET/CT diagnostic annotations | 1,091 | 0.1 GB |
| v23 | NLSTSeg |
NLST lung segmentations | 1,803 | 0.4 GB |
| v23 | NLST-Sybil |
NLST risk prediction outputs (Sybil model) | 970 | — |
| v23 | ProstateX-Targets |
ProstateX biopsy target annotations | 345 | — |
| v23 | TCGA-GBM360 |
TCGA GBM 360° annotations | 691 | 0.4 GB |
| v23 | TCGA-SBU-TIL-Maps |
TCGA tumor-infiltrating lymphocyte maps | 21,030 | 2.0 GB |
| v24 | EAY131-Tumor-Annotations |
Tumor annotations for NCI-MATCH (eay131) | 15,799 | 1.1 GB |
- TotalSegmentator (v18) is the single largest addition: 14.3 TB of multi-organ CT auto-segmentations across 378K series
-
Cancer Moonshot Biobank (v19) introduced 7 clinical cohorts (
cmb_*) with multi-omic supporting data spanning blood, GI, lung, and prostate cancers - CCDI-MCI (v19) added the largest new patient cohort (~4,400 subjects) with broad pediatric/young adult cancer coverage
- NCI-MATCH (eay131) (v24) added a multi-institution basket trial cohort with 47 cancer types and 2,813 patients
- PDXNet (v24) added patient-derived xenograft imaging across 29 cancer types with genomics
- CGCI suite (v24) added 4 lymphoma/cervical/lung cohorts with 669 total patients
- Pan-Cancer-Nuclei-Seg-DICOM (v19) added 7 TB of pathology nuclei segmentations
- GTEx (v19) provides non-diseased tissue controls (971 subjects) paired with genomics data