Template Credit: Adapted from a template made available by Dr. Jason Brownlee of Machine Learning Mastery.
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 Malaria Parasite Detection dataset is a binary-class classification situation where we attempt to predict one of two possible outcomes.
INTRODUCTION: Biomedical researchers have developed a mobile application that runs on a standard Android smartphone attached to a conventional light microscope for detecting malaria disease. The smartphone’s built-in camera acquired thin blood smear images of slides for each microscopic field of view. An expert manually annotated the slides afterward. The dataset contains a total of 27,558 cell images with equal instances of parasitized and uninfected cells.
From iteration Take1, we constructed a CNN model using a simple three-block VGG architecture and tested the model’s performance using a held-out validation dataset.
In this Take2 iteration, we will construct a CNN model using the InceptionV3 architecture and test the model’s performance using a held-out validation dataset.
ANALYSIS: From iteration Take1, the model’s performance achieved an average accuracy score of 94.08% on the validation dataset after 20 epochs.
In this Take2 iteration, the model’s performance achieved an average accuracy score of 95.12% on the validation dataset after 20 epochs.
CONCLUSION: In this iteration, the InceptionV3 CNN model appeared to be suitable for modeling this dataset. We should consider experimenting with TensorFlow for further modeling.
Dataset Used: Malaria Parasite Detection
Dataset ML Model: Binary-class image classification with numerical attributes
Dataset Reference: https://lhncbc.nlm.nih.gov/LHC-publications/pubs/MalariaDatasets.html
A potential source of performance benchmark: https://doi.org/10.7717/peerj.4568 or https://doi.org/10.7717/peerj.6977
One potential source of performance benchmarks: https://www.kaggle.com/c/cassava-leaf-disease-classification/leaderboard
The HTML formatted report can be found here on GitHub.