Edit model card

(Thyroid) Thyroid Carcinoma

This model can additionally be run on our pathology reports platform

Credits: Dr. Yazeed Alwelaie (King Fahad Medical City, Riyadh, Saudi Arabia)

Introduction

This H&E thyroid 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 thyroid 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 20 publicly available TCGA-THCA H&E-stained whole slide images. Validation testing was carried out on non-overlapping cases from TCGA.

Classes

  1. Normal Thyroid
  2. Skeletal Muscle
  3. Connective Tissue
  4. Desmoplastic Stroma
  5. Blank space
  6. Inflammation
  7. Lymphocytic Thyroiditis
  8. Necrosis
  9. Papillae
  10. Tumor (ptc. follicular)
  11. Tumor (ptc. classic)
  12. Tumor (ptc. tall cell)
  13. Fibrosis and Hyalinization

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
8
Inference Examples
Inference API (serverless) does not yet support tf-keras models for this pipeline type.