Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,37 @@
|
|
1 |
-
---
|
2 |
-
license: apache-2.0
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- vision
|
5 |
+
- image-classification
|
6 |
+
---
|
7 |
+
|
8 |
+
### (Breast) Breast Invasive Carcinoma
|
9 |
+
|
10 |
+
This model can additionally be run on our [pathology reports platform](https://www.pathologyreports.ai/marketplace/browse/ccbc6666-c7c1-45c4-9a62-e8165603c613)
|
11 |
+
|
12 |
+
Credits: Dr. Kiran Jakate
|
13 |
+
|
14 |
+
### Introduction
|
15 |
+
|
16 |
+
This H&E breast invasive carcinoma tissue classifier was developed using transfer learning on a histology optimized version of the VGG19 CNN [(DOI: 10.1038/s42256-019-0068-6)](https://doi.org/10.1038/s42256-019-0068-6) and trained to recognize breast invasive carcinoma and other surrounding tissue elements.
|
17 |
+
|
18 |
+
Annotations were carried out on batches of image tiles (dimensions: 512 x 512 px) grouped using image-based clustering [(HAVOC, DOI: 10.1126/sciadv.adg1894)](https://doi.org/10.1126/sciadv.adg1894) from 5 publicly available TCGA-BRCA H&E-stained whole slide images. The validation was carried out on non-overlapping cases from TCGA.
|
19 |
+
|
20 |
+
### Classes
|
21 |
+
|
22 |
+
1. Adipose Tissue
|
23 |
+
2. Adipose Tissue Interfaced With Another Tissue Type
|
24 |
+
3. Blank Space
|
25 |
+
4. Blood Vessel
|
26 |
+
5. Fibroconnective Tissue
|
27 |
+
6. Fibrosis
|
28 |
+
7. Lymph Node Capsule
|
29 |
+
8. Lymph Node Cortex
|
30 |
+
9. Lymph node hilum area
|
31 |
+
10. Nodal Metastatic Carcinoma
|
32 |
+
|
33 |
+
This information can be found in the inference.json file
|
34 |
+
|
35 |
+
### Evaluation Metrics
|
36 |
+
|
37 |
+
Classifier validation can be found on the [pathology reports platform](https://www.pathologyreports.ai/marketplace/browse/ccbc6666-c7c1-45c4-9a62-e8165603c613)
|