|
a/README.md |
|
b/README.md |
| 1 |
<h1 align="center">Welcome to PathFlowAI </h1> |
1 |
<h1 align="center">Welcome to PathFlowAI </h1> |
| 2 |
<p> |
2 |
|
| 3 |
<img alt="Version" src="https://img.shields.io/badge/version-0.1-blue.svg?cacheSeconds=2592000" /> |
|
|
| 4 |
<a href="https://jlevy44.github.io/PathFlowAI/"> |
|
|
| 5 |
<img alt="Documentation" src="https://img.shields.io/badge/documentation-yes-brightgreen.svg" target="_blank" /> |
|
|
| 6 |
</a> |
|
|
| 7 |
</p> |
|
|
| 8 |
|
3 |
|
| 9 |
> A Convenient High-Throughput Workflow for Preprocessing, Deep Learning Analytics and Interpretation in Digital Pathology |
4 |
A Convenient High-Throughput Workflow for Preprocessing, Deep Learning Analytics and Interpretation in Digital Pathology |
| 10 |
|
5 |
|
| 11 |
### 🏠 [Homepage](https://github.com/jlevy44/PathFlowAI) |
6 |
### 🏠 [Homepage](https://github.com/jlevy44/PathFlowAI) |
| 12 |
|
7 |
|
| 13 |
Published in the Proceedings of the Pacific Symposium for Biocomputing 2020, Manuscript: https://psb.stanford.edu/psb-online/proceedings/psb20/Levy.pdf |
8 |
Published in the Proceedings of the Pacific Symposium for Biocomputing 2020, Manuscript: https://psb.stanford.edu/psb-online/proceedings/psb20/Levy.pdf |
| 14 |
|
9 |
|
|
... |
|
... |
| 67 |
AUC-ROC curves for the test images that estimate overall accuracy given different sensitivity cutoffs, c) H&E patch |
62 |
AUC-ROC curves for the test images that estimate overall accuracy given different sensitivity cutoffs, c) H&E patch |
| 68 |
(left) with corresponding SHAP interpretations (right) for four patches; the probability value of portal classification |
63 |
(left) with corresponding SHAP interpretations (right) for four patches; the probability value of portal classification |
| 69 |
is shown, and on the SHAP value scale, red indicates regions that the model attributes to portal prediction, d) Model trained UMAP embeddings of patches colored by original portal coverage (area of patch covered by portal) as judged |
64 |
is shown, and on the SHAP value scale, red indicates regions that the model attributes to portal prediction, d) Model trained UMAP embeddings of patches colored by original portal coverage (area of patch covered by portal) as judged |
| 70 |
by pathologist and visualization of individual patches |
65 |
by pathologist and visualization of individual patches |