Image Feature Extraction
timm
Safetensors
pathology
histopathology
her2
breast-cancer
h-and-e
vision-transformer
multiple-instance-learning
Instructions to use cloudkites/her2-reader with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- timm
How to use cloudkites/her2-reader with timm:
import timm model = timm.create_model("hf-hub:cloudkites/her2-reader", pretrained=True) - Notebooks
- Google Colab
- Kaggle
Download data/paper/paper-data/table_her2tasks_full.tex from cloudkites/her2-reader: direct link, hf CLI and curl.
- Browser
- Download file 1.86 kB
-
https://huggingface.co/cloudkites/her2-reader/resolve/main/data/paper/paper-data/table_her2tasks_full.tex
- Command line
-
hf download hf://cloudkites/her2-reader/data/paper/paper-data/table_her2tasks_full.tex
-
curl -L -o table_her2tasks_full.tex https://huggingface.co/cloudkites/her2-reader/resolve/main/data/paper/paper-data/table_her2tasks_full.tex
1.86 kB
| % Generated by docs/paper/paper_her2tasks.py (TCGA-BRCA; 10 paired seeds; p: exact one-sided Wilcoxon) | |
| \begin{tabularx}{\linewidth}{@{}>{\raggedright\arraybackslash}X c c c c c c c@{}} | |
| \toprule | |
| test & \textbf{ours} & Phikon & H-optimus-0 & Hibou-B & Midnight-12k & ResNet-50 & DINOv2-S \\ | |
| \midrule | |
| HER2-low, head & \textbf{0.649$^{4}$} & 0.741$^{1}$ & 0.692$^{2}$ & 0.678$^{3}$ & 0.626$^{5}$ & 0.615$^{6}$ & 0.613$^{7}$ \\ | |
| \quad SD; $p$ vs ours & 0.024; -- & 0.028; $<$0.01 & 0.026; $<$0.01 & 0.014; 0.02 & 0.036; 0.08 & 0.031; 0.02 & 0.037; $<$0.01 \\ | |
| HER2-low, reader Y & \textbf{0.456$^{6}$} & 0.479$^{4}$ & 0.500$^{2}$ & 0.542$^{1}$ & 0.494$^{3}$ & 0.462$^{5}$ & 0.441$^{7}$ \\ | |
| \quad SD; $p$ vs ours & 0.010; -- & 0.013; $<$0.01 & 0.007; $<$0.01 & 0.015; $<$0.01 & 0.010; $<$0.01 & 0.014; 0.28 & 0.019; 0.03 \\ | |
| HER2-low, reader T & \textbf{0.560$^{4}$} & 0.551$^{6}$ & 0.569$^{2}$ & 0.553$^{5}$ & 0.570$^{1}$ & 0.541$^{7}$ & 0.565$^{3}$ \\ | |
| \quad SD; $p$ vs ours & 0.026; -- & 0.044; 0.28 & 0.030; 0.28 & 0.032; 0.31 & 0.029; 0.28 & 0.028; 0.05 & 0.051; 0.31 \\ | |
| FISH, head & \textbf{0.544$^{2}$} & 0.475$^{5}$ & 0.546$^{1}$ & 0.485$^{4}$ & 0.538$^{3}$ & 0.468$^{7}$ & 0.471$^{6}$ \\ | |
| \quad SD; $p$ vs ours & 0.022; -- & 0.017; $<$0.01 & 0.025; 0.35 & 0.029; $<$0.01 & 0.034; 0.28 & 0.022; $<$0.01 & 0.048; $<$0.01 \\ | |
| FISH, reader Y & \textbf{0.682$^{2}$} & 0.619$^{6}$ & 0.706$^{1}$ & 0.672$^{3}$ & 0.650$^{4}$ & 0.575$^{7}$ & 0.632$^{5}$ \\ | |
| \quad SD; $p$ vs ours & 0.019; -- & 0.007; $<$0.01 & 0.009; $<$0.01 & 0.015; 0.12 & 0.005; $<$0.01 & 0.016; $<$0.01 & 0.014; $<$0.01 \\ | |
| FISH, reader T & \textbf{0.669$^{2}$} & 0.654$^{3}$ & 0.690$^{1}$ & 0.572$^{5}$ & 0.644$^{4}$ & 0.445$^{7}$ & 0.469$^{6}$ \\ | |
| \quad SD; $p$ vs ours & 0.024; -- & 0.020; 0.04 & 0.034; 0.04 & 0.034; $<$0.01 & 0.030; 0.01 & 0.030; $<$0.01 & 0.035; $<$0.01 \\ | |
| \bottomrule | |
| \end{tabularx} | |