Machine Learning on Mobile: An On-device Inference App for Skin Cancer Detection

Abstract

Mobile health (mHealth) is considered one of the most transformative drivers for health informatics delivery of ubiquitous medical applications. Machine learning has proven to be a powerful tool in classifying medical images for detecting various diseases. However, supervised machine learning requires a large amount of data to train the model, whose storage and processing pose considerable system requirements challenges for mobile applications. Therefore, many studies focus on deploying cloud-based machine learning, which takes advantage of the Internet connection to outsource data intensive computing. However, this approach comes with certain drawbacks such as those related to latency and privacy, which need to be considered in the context of sensitive data. To tackle these challenges of mHealth applications, we present an on-device inference App and use a dataset of skin cancer images to demonstrate a proof of concept. We pre-trained a Convolutional Neural Network model using 10,015 skin cancer images. The model is then deployed on a mobile device, where the inference process takes place, i.e. when presented with new test image all computations are executed locally where the test data remains. This approach reduces latency, saves bandwidth and improves privacy.