Heart hypertrophy detector

Interface of our model
Training results
Crop of W Plane
Crop frame W Plane
Original frames

Inspiration

It was inspired to help people's lives from our field that is Artificial Intelligence, creating a model that predicts cardiovascular diseases in heart hypertrophy.

What it does

Cardiovascular diseases are a major global health issue, and developing a model that can predict heart hypertrophy can be a significant contribution to the field of healthcare.

There are several steps made on this project:

Research and gather data: One of the first steps in building a machine learning model is to collect and organize data.
Preprocess and clean the data: Once you have collected your data, it was needed to preprocess and clean it. This includes tasks such as removing missing or duplicate data, standardizing values, and handling outliers. Preprocessing and cleaning the data is an important step that can significantly impact the performance of our model.
Choose and implement a machine learning model: There are various machine learning algorithms that can use to build our model. We used a CNN with an input size of 256x256.
Train and evaluate the model: It was trained it using the data that was obtained splitting each frame from it video that had collected. This involves feeding the model the data and adjusting the model's parameters to improve its performance. It was needed to evaluate the model using various metrics to determine how well it performs.
Create a interface to put our model in production