Identify Metastatic Cancer

Updated: ∙ 1 min read ∙ Tags: Data science, Machine learning, Deep learning, Python, Healthcare

In this project, we create an algorithm to identify metastatic cancer in small image patches taken from larger digital pathology scans. The data for this competition is a slightly modified version of the PatchCamelyon (PCam) benchmark dataset. The original PCam dataset contains duplicate images due to its probabilistic sampling, however, the version presented on Kaggle does not contain duplicates.

Dataset Links Kaggle

Model Plot

png

Training and validation Loss

png

Training and validation Accuracy

png

Receiver operating characteristic (roc) curve

png

Classification Report

png

Confusion Matrix

png

Improve this page:

Share on:

About

My name is Zakaria Alsahfi, and I am the Director of Information Affairs at the University of Business and Technology.

My primary responsibility is to interpret large amounts of data to understand trends in student enrollment and to ensure that accurate and relevant information is provided to both authorized external and internal stakeholders. In my role, I am privileged to have the opportunity to create and optimize workflows, which significantly improves efficiency. I also analyze extensive data sets and extract insights that propel the business forward, primarily using tools such as spreadsheets and Power BI. My introduction to predictive modeling using Python (having started with R but transitioning to Python) has opened a new realm of possibilities for me. I have embraced this evolution, dedicating myself to a deeper exploration of all things data-related.

This blog/portfolio is a showcase of the projects I have completed, those that are in progress, and a documentation of my learnings as I delve further into the data world. It’s been an exhilarating journey thus far, and I am committed to continually enriching this platform with my experiences and insights.

Identify Metastatic Cancer

Model Plot

Training and validation Loss

Training and validation Accuracy

Receiver operating characteristic (roc) curve

Classification Report

Confusion Matrix

Comments 💬

Zakaria Alsahfi

Error

Model Plot

Training and validation Loss

Training and validation Accuracy

Receiver operating characteristic (roc) curve

Classification Report

Confusion Matrix

Comments 💬

Templates (for web app):

Error