More than 1.7 million women worldwide and 300,000 thousand women in the US are affected by breast cancer each year. The cancer classification model can help healthcare organizations especially in developing countries to improve their services and reduce their costs for the patients.
What it does
The classification of malignant and Benign breast cancers from the features that represent characteristics of cell nuclei of images generated after the Fine Needle Aspiration Method.
How I built it
The cancer classification project is using a scikit-learn model to classify the malignant and breast cancers and the model has been onboarded and published on the Acumos marketpace. We are using the Breast Cancer Wisconsin Diagnostic dataset from the UCI Machine Learning Repository https://archive.ics.uci.edu/ml/datasets/Breast+Cancer+Wisconsin+%28Diagnostic%29 to predict the Malignant or Benign cancer. RandomForest classification is used on these thirty features to predict the malignant or benign cancers over the Acumos Python Client Repository. The test data is available in the Documents on the Acumos marketplace and anyone can communicate with the microservice and test their own similar data or the data given to classify the malignant and benign breast cancers.
Challenges I ran into
The large number of feature variables in the dataset and learning about the Acumos Python Client Repository
Accomplishments that I'm proud of
Learning the Acumos platform and creating a model that can benefit and bring about a positive change in the world for many people around the world on this open-source platform
What I learned
Using the Acumos platform and marketplace and open-source future of AI on the Acumos platform
What's next for Cancer Classification
The future scope of this cancer classification Acumos project would be the improvement of the model performance and applications that would benefit healthcare professionals. Classification on digitized images of fine needle aspirate (FNA) data using convolutional neural networks. Similarly, the Acumos platform can be used for models to diagnose or classify diseases from X-rays, CT scan and MRI images