Breast Cancer Mitosis Detector

Get this modelTry the API

Overview

This model takes a 64 x 64 PNG image file extracted from the whole slide image as input, and outputs the predicted probability of the image containing mitosis. The model consists of a modified ResNet-50 model trained on the TUPAC16 auxiliary mitosis dataset. For more information and additional features, check out the deep-histopath repository on GitHub.

Model Metadata

Domain Application Industry Framework Training Data Input Data Format
Vision Image Classification Health Care Keras TUPAC16 64×64 PNG Image

References

Licenses

Component License Link
Model Github Repository Apache 2.0 LICENSE
Training Data Custom License TUPAC16

Options available for deploying this model

This model can be deployed using the following mechanisms:

  • Deploy from Dockerhub:
docker run -it -p 5000:5000 codait/max-breast-cancer-mitosis-detector
  • Deploy on Kubernetes:
kubectl apply -f https://raw.githubusercontent.com/IBM/MAX-Breast-Cancer-Mitosis-Detector/master/max-breast-cancer-mitosis-detector.yaml

Example Usage

Once deployed, you can test the model from the command line. For example if running locally:

curl -F "image=@assets/true.png" -XPOST http://localhost:5000/model/predict
{
  "predictions": [
    {
      "probability": 0.9884441494941711
    }
  ],
  "status": "ok"
}
  • deep-histopath: Predict breast cancer proliferation scores with TensorFlow, Keras, and Apache Spark