W8Yi/tcga-wsi-uni2h-features
Viewer • Updated • 600 • 13.6k • 3
Weiyi Qin
W8Yi
AI & ML interests
None yet
Recent Activity
updated a dataset 1 day ago
W8Yi/tcga-wsi-uni2h-features reacted to theirpost with 🚀 5 days ago
I built a TCGA WSI feature dataset using UNI2-h.
The official release currently has incomplete coverage (see discussion):
https://huggingface.co/datasets/MahmoodLab/UNI2-h-features/discussions/2#681b5ed184d0a008fca99297
To make the features easier to use for research, I generated a new dataset:
https://huggingface.co/datasets/W8Yi/tcga-wsi-uni2h-features
Key differences from the official release:
• All detected tissue tiles are encoded (not a sampled subset)
• Features can be downloaded per slide instead of large ZIP archives
• QC overlay images are provided for visual inspection
• UNI2-h 1536-D tile embeddings stored in H5 format
• Organized by TCGA project for easier use in MIL / retrieval pipelines
Example layout:
```
TCGA-HNSC/
features/*.h5
vis/*__overlay.png
```
Hope this helps others working on computational pathology and TCGA WSI research.
posted an update 6 days ago
I built a TCGA WSI feature dataset using UNI2-h.
The official release currently has incomplete coverage (see discussion):
https://huggingface.co/datasets/MahmoodLab/UNI2-h-features/discussions/2#681b5ed184d0a008fca99297
To make the features easier to use for research, I generated a new dataset:
https://huggingface.co/datasets/W8Yi/tcga-wsi-uni2h-features
Key differences from the official release:
• All detected tissue tiles are encoded (not a sampled subset)
• Features can be downloaded per slide instead of large ZIP archives
• QC overlay images are provided for visual inspection
• UNI2-h 1536-D tile embeddings stored in H5 format
• Organized by TCGA project for easier use in MIL / retrieval pipelines
Example layout:
```
TCGA-HNSC/
features/*.h5
vis/*__overlay.png
```
Hope this helps others working on computational pathology and TCGA WSI research.
Organizations
None yet
updated a
dataset 1 day ago
reactedto their post with 🚀 5 days ago
Post
2721
I built a TCGA WSI feature dataset using UNI2-h.
The official release currently has incomplete coverage (see discussion):
MahmoodLab/UNI2-h-features#2
To make the features easier to use for research, I generated a new dataset:
W8Yi/tcga-wsi-uni2h-features
Key differences from the official release:
• All detected tissue tiles are encoded (not a sampled subset)
• Features can be downloaded per slide instead of large ZIP archives
• QC overlay images are provided for visual inspection
• UNI2-h 1536-D tile embeddings stored in H5 format
• Organized by TCGA project for easier use in MIL / retrieval pipelines
Example layout:
Hope this helps others working on computational pathology and TCGA WSI research.
The official release currently has incomplete coverage (see discussion):
MahmoodLab/UNI2-h-features#2
To make the features easier to use for research, I generated a new dataset:
W8Yi/tcga-wsi-uni2h-features
Key differences from the official release:
• All detected tissue tiles are encoded (not a sampled subset)
• Features can be downloaded per slide instead of large ZIP archives
• QC overlay images are provided for visual inspection
• UNI2-h 1536-D tile embeddings stored in H5 format
• Organized by TCGA project for easier use in MIL / retrieval pipelines
Example layout:
TCGA-HNSC/
features/*.h5
vis/*__overlay.pngHope this helps others working on computational pathology and TCGA WSI research.
posted an update 6 days ago
Post
2721
I built a TCGA WSI feature dataset using UNI2-h.
The official release currently has incomplete coverage (see discussion):
MahmoodLab/UNI2-h-features#2
To make the features easier to use for research, I generated a new dataset:
W8Yi/tcga-wsi-uni2h-features
Key differences from the official release:
• All detected tissue tiles are encoded (not a sampled subset)
• Features can be downloaded per slide instead of large ZIP archives
• QC overlay images are provided for visual inspection
• UNI2-h 1536-D tile embeddings stored in H5 format
• Organized by TCGA project for easier use in MIL / retrieval pipelines
Example layout:
Hope this helps others working on computational pathology and TCGA WSI research.
The official release currently has incomplete coverage (see discussion):
MahmoodLab/UNI2-h-features#2
To make the features easier to use for research, I generated a new dataset:
W8Yi/tcga-wsi-uni2h-features
Key differences from the official release:
• All detected tissue tiles are encoded (not a sampled subset)
• Features can be downloaded per slide instead of large ZIP archives
• QC overlay images are provided for visual inspection
• UNI2-h 1536-D tile embeddings stored in H5 format
• Organized by TCGA project for easier use in MIL / retrieval pipelines
Example layout:
TCGA-HNSC/
features/*.h5
vis/*__overlay.pngHope this helps others working on computational pathology and TCGA WSI research.
updated a
dataset 6 days ago
published a
dataset 7 days ago
Access request pending – quick question
1
#1 opened 11 days ago
by W8Yi
liked a
model 11 days ago
updated a
collection 13 days ago
updated a
model 13 days ago
published a
model 13 days ago
[bot] Conversion to Parquet
#1 opened 14 days ago
by 
parquet-converter
liked a
dataset 14 days ago
published a
dataset 16 days ago
liked a
dataset about 2 months ago
liked a
model 6 months ago
liked a
model over 1 year ago
authored a
paper almost 2 years ago
upvoted a paper almost 2 years ago
HTTPError: HTTP Error 403: Forbidden
👍 2
1
#1 opened almost 3 years ago
by 
yulianiu