The Tumor Proliferation Assessment Challenge 2016 (TUPAC16) was created to develop state-of-the-art algorithms for automatic prediction of tumor proliferation scores from whole-slide histopathology images of breast tumors. The IBM CODAIT team trained a mitosis detection model (a modified ResNet-50 model) on the TUPAC16 auxiliary mitosis dataset, and then applied it to the whole slide images for predicting the tumor proliferation scores.

This repository contains code to instantiate and deploy the mitosis detection model mentioned above. 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. For more information and additional features, check out the deep-histopath repository on GitHub.

The code in this repository deploys the model as a web service in a Docker container. This repository was developed as part of the IBM Code Model Asset Exchange.

Note: Although this model supports different input data formats, the inference results are sensitive to the input data. In order to keep the extracted images the same as the original datasets, PNG image format should be used.

• Dusenberry, Mike, and Hu, Fei, Deep Learning for Breast Cancer Mitosis Detection, 2018.

• docker: The Docker command-line interface. Follow the installation instructions for your system.
• The minimum recommended resources for this model is 2GB Memory and 2 CPUs.
• If you are on x86-64/AMD64, your CPU must support AVX at the minimum.

• Deploy from Quay
• Deploy on Red Hat OpenShift
• Deploy on Kubernetes
• Run Locally

To run the docker image, which automatically starts the model serving API, run:

$ docker run -it -p 5000:5000 quay.io/codait/max-breast-cancer-mitosis-detector

This will pull a pre-built image from the Quay.io container registry (or use an existing image if already cached locally) and run it. If you'd rather checkout and build the model locally you can follow the run locally steps below.

You can deploy the model-serving microservice on Red Hat OpenShift by following the instructions for the OpenShift web console or the OpenShift Container Platform CLI in this tutorial, specifying quay.io/codait/max-breast-cancer-mitosis-detector as the image name.

You can also deploy the model on Kubernetes using the latest docker image on Quay.

On your Kubernetes cluster, run the following commands:

$ kubectl apply -f https://raw.githubusercontent.com/IBM/MAX-Breast-Cancer-Mitosis-Detector/master/max-breast-cancer-mitosis-detector.yaml

The model will be available internally at port 5000, but can also be accessed externally through the NodePort.

1. Build the Model
2. Deploy the Model
3. Use the Model
4. Development
5. Cleanup

Clone the MAX-Breast-Cancer-Mitosis-Detector repository locally. In a terminal, run the following command:

$ git clone https://github.com/IBM/MAX-Breast-Cancer-Mitosis-Detector.git

Change directory into the repository base folder:

$ cd MAX-Breast-Cancer-Mitosis-Detector

To build the docker image locally, run:

$ docker build -t max-breast-cancer-mitosis-detector .

All required model assets will be downloaded during the build process. Note that currently this docker image is CPU only (we will add support for GPU images later).

To run the docker image, which automatically starts the model serving API, run:

$ docker run -it -p 5000:5000 max-breast-cancer-mitosis-detector

The API server automatically generates an interactive Swagger documentation page. Go to http://localhost:5000 to load it. From there you can explore the API and also create test requests.

Use the model/predict endpoint to load a test image (you can use one of the test images from the samples folder) and get predicted labels for the image from the API.

You can also test it on the command line, for example:

$ curl -F "image=@samples/true.png" -XPOST http://localhost:5000/model/predict

You should see a JSON response like that below:

{"predictions": [{"probability": 0.9884441494941711}], "status": "ok"}

To run the Flask API app in debug mode, edit config.py to set DEBUG = True under the application settings. You will then need to rebuild the docker image (see step 1).

To stop the docker container type CTRL + C in your terminal.

• Transfer Learning in CNNs for Mitosis Detection: Interview on Transfer Learning in CNNs for Mitosis Detection at the OpenTech AI conference at IBM Finland, 2018
• Deep Learning for Breast Cancer Mitosis Detection: Presentation on SF Big Analytics Meetup, 2018

If you are interested in contributing to the Model Asset Exchange project or have any queries, please follow the instructions here.