Android skin cancer detection and classification based on MobileNet v2 model

Abstract

The latest developments in the smartphone-based skin cancer diagnosis application allow simple ways for portable melanoma risk assessment and diagnosis for early skin cancer detection. Due to the trade-off problem (time complexity and error rate) on using a smartphone to run a machine learning algorithm for image analysis, most of the skin cancer diagnosis apps execute the image analysis on the server. In this study, we investigate the performance of skin cancer images detection and classification on android devices using the MobileNet v2 deep learning model. We compare the performance of several aspects; object detection and classification method, computer and android based image analysis, image acquisition method, and setting parameter. Skin cancer actinic Keratosis and Melanoma are used to test the performance of the proposed method. Accuracy, sensitivity, specificity, and running time of the testing methods are used for the measurement. Based on the experiment results, the best parameter for the MobileNet v2 model on android using images from the smartphone camera produces 95% accuracy for object detection and 70% accuracy for classification. The performance of the android app for object detection and classification model was feasible for the skin cancer analysis. Android-based image analysis remains within the threshold of computing time that denotes convenience for the user and has the same performance accuracy with the computer for the high-quality images. These findings motivated the development of disease detection processing on android using a smartphone camera, which aims to achieve real-time detection and classification with high accuracy.

Remote Monitoring of Colorectal Cancer Survivors Using a Smartphone App and Internet of Things–Based Device: Development and Usability Study

“…Client-side software was designed to be hybrid to run on different platforms. PWA and Android software have been used in various fields of health care [ 31 - 33 ]. Secure Sockets Layer protocol was installed on the webserver for communication security.…”

A Deep learning based patient care application for skin cancer detection

“…There have already been some healthcare applications designed in the form of smartphone mobile apps, examples include SkinVision, and DermIA [6]. However, these types of smartphone-based apps face several challenges.…”

“…First, the smartphonebased app does not have high accuracy in terms of melanoma detection. According to [6], deep learning network such as MobileNet tends to have a much lower accuracy when run on a mobile phone than in a professional environment like Jupyter Notebook. Moreover, the quality of smartphone taken images also are not good enough for satisfying performance as MobileNet v2 only fetched 60% accuracy under four times magnified smartphone lesion pictures [6].…”

“…According to [6], deep learning network such as MobileNet tends to have a much lower accuracy when run on a mobile phone than in a professional environment like Jupyter Notebook. Moreover, the quality of smartphone taken images also are not good enough for satisfying performance as MobileNet v2 only fetched 60% accuracy under four times magnified smartphone lesion pictures [6]. Secondly, while [6]'s experiment on MoileNet v2 successfully implemented pre-trained deep CNN on a smartphone, it also inherited one of the major drawbacks of machine learning classifiers in terms of melanoma detection.…”

“…Moreover, the quality of smartphone taken images also are not good enough for satisfying performance as MobileNet v2 only fetched 60% accuracy under four times magnified smartphone lesion pictures [6]. Secondly, while [6]'s experiment on MoileNet v2 successfully implemented pre-trained deep CNN on a smartphone, it also inherited one of the major drawbacks of machine learning classifiers in terms of melanoma detection. Classifiers like CNN tends to treat each skin lesion image individually instead of as components of the patients.…”