The Foldscope is a microscope made of paper and a removable lense which costs 25 cents to make. In this project Foldscope is used to target Schistosomiasis, a parasitic disease second to Malaria in deaths and economic effect in developing countries. There is a cure that costs 8 cents per patient for the World Health Organization to distribute, but the diagnosis requires a microscope and a doctor.

Doctors diagnose Schistosomiasis by using microscopes to count the number of Schistosomiasis eggs in urine. If the number is greater than 50, a certain medication is given, and if it is less than 50, a different medication is administered. However, developing countries lack not only microscopes but also access to medical professionals.

This project uses an artificial intelligence algorithm called Generative Adversarial Network (GAN), a Foldscope, and a Raspberry Pi with camera to replace the current expensive diagnostics. First, I used miniscule plastic beads and artificial urine to model Schistosomiasis eggs found in urine. I took 350 images of these samples by attaching a Foldscope to a Raspberry Pi camera, and used them to train the GAN, GAN consists of two components: the generator and the classifier. The generator learns to produce fake images resembling the real ones, while the classifier learns to recognize both the fake and the real images and tell them apart. During training, the classifier places an image into one of the n+1 classes. The n classes are determined by the user, and the n+1-th is for the fake images. During testing, the classifier receives real images which it had never seen before and places them into n classes.

Four tests were conducted. In the first the classifier placed images into two categories: with and without eggs. 50% of sample images contained objects other than eggs, for urine often has other visible components especially in areas with dirty water. The accuracy in this test was 95%. The next test used three classes: 0 eggs, < 50 eggs, > 50 eggs. This test mirrors how the medication is prescribed for Schistosomiasis, and it was 94% accurate. Third test estimated actual egg count for each sample, and measured how many eggs on average the neural network is off from the true count. By the end of training, the accuracy was 0.25 eggs, less than one egg off. The fourth test was the same as the third, but the network had no generator (i.e. it was not a GAN). This test resulted in an accuracy of 11.5 eggs which demonstrates that GAN algorithm is essential for premium accuracy.

The trained network is downloaded onto the Raspberry Pi, so the device is autonomous and does not require wireless or cellular network to operate, making it suitable for remote areas. All together the GAN, the Foldscope, and the Raspberry Pi with camera cost less than $25 compared to $400 for the cheapest microscope and replaces the need for a trained diagnostics professional. Finally, while this device was trained to combat Schistosomiasis, it can be re-trained on any parasitic disease to prevent epidemics plaguing the developing world.