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 ResNet152V2 model’s performance achieved an accuracy score of 91.67% after ten epochs using the validation dataset. When we applied the model to the test dataset, the model achieved an accuracy score of 77.14%.
CONCLUSION: In this iteration, the TensorFlow ResNet152V2 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: https://www.kaggle.com/datasets/mohamedhanyyy/chest-ctscan-images
One source of potential performance benchmarks: https://www.kaggle.com/datasets/mohamedhanyyy/chest-ctscan-images/code
The HTML formatted report can be found here on GitHub.