Edit model card

(Kidney) Papillary, Clear Cell and Chromophobe Renal Cell Carcinoma

This model can additionally be run on our pathology reports platform

Credits: Dr. Vincent Castillo & Dr. Rola Saleeb (University of Toronto, Canada)

Introduction

This H&E kidney renal cell carcinoma tissue classifier was developed using transfer learning on a histology optimized version of the VGG19 CNN (DOI: 10.1038/s42256-019-0068-6) and trained to recognize kidney clear, papillary, and chromophobe renal cell carcinoma and other surrounding tissue elements.

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) from 55 local H&E-stained whole slide images. Validation testing was carried out on non-overlapping image tiles from the same cases.

Classes

  1. Blood Vessel
  2. Chromophobe Renal Cell Carcinoma
  3. Clear Cell Renal Cell Carcinoma
  4. Cyst Fluid
  5. Fibrocollagenous Tissue
  6. Hemorrhage
  7. Hemosiderin
  8. Necrosis
  9. Papillary Renal Cell Carcinoma
  10. Renal Parenchyma
  11. Renal Pelvis
  12. Blank space

This information can be found in the inference.json file

Evaluation Metrics

Classifier validation can be found on the pathology reports platform

Downloads last month
0
Inference Examples
Inference API (serverless) does not yet support tf-keras models for this pipeline type.