Multi-Class Image Classification Model for Chest CT-Scan Images Using TensorFlow Take 2

SUMMARY: This project aims to construct a predictive model using a TensorFlow convolutional neural network (CNN) and document the end-to-end steps using a template. The Chest CT-Scan Images Dataset is a multi-class classification situation where we attempt to predict one of several (more than two) possible outcomes.

INTRODUCTION: The research project aims to achieve early detection of lung cancer using CT-Scan images and AI models. The research team deployed deep learning-based classification models in this study to identify potential candidates. For this study, 1,000 chest CT-Scan images comprise the dataset.

ANALYSIS: The ConvNeXtBase model’s performance achieved an accuracy score of 83.33% after ten epochs using the validation dataset. When we applied the model to the test dataset, the model achieved an accuracy score of 72.70%.

CONCLUSION: In this iteration, the TensorFlow ConvNeXtBase CNN model appeared suitable for modeling this dataset.

Dataset ML Model: Multi-Class classification with numerical features

Dataset Used: Chest CT-Scan Images Dataset

Dataset Reference:

One source of potential performance benchmarks:

The HTML formatted report can be found here on GitHub.