A Novel Approach for Testing Water Safety Using Deep Learning Inference of Microscopic Images of Unincubated Water Samples

TL;DR

DeepScope is a deep learning-based water safety testing method that rapidly detects contamination from microscopic images without incubation, significantly reducing testing time and cost while maintaining high accuracy.

Contribution

The paper introduces DeepScope, a novel deep learning approach that eliminates incubation in water safety testing, enabling rapid, cost-effective, and accurate detection of microbial contamination.

Findings

Achieved 93% accuracy in detecting water contamination

Reduced testing time by over 98% compared to traditional methods

Cost per test estimated at $0.44

Abstract

Fecal-contaminated water causes diseases and even death. Current microbial water safety tests require pathogen incubation, taking 24-72 hours and costing \$20-\$50 per test. This paper presents a solution (DeepScope) exceeding UNICEF's ideal Target Product Profile requirements for presence/absence testing, with an estimated per-test cost of \$0.44. By eliminating the need for pathogen incubation, DeepScope reduces testing time by over 98\%. In DeepScope, a dataset of microscope images of bacteria and water samples was assembled. An innovative augmentation technique, generating up to 21 trillion images from a single microscope image, was developed. Four convolutional neural network models were developed using transfer learning and regularization techniques, then evaluated on a field-test dataset comprising 100,000 microscope images of unseen, real-world water samples collected from fourteen different water sources across Sammamish, WA. Precision-recall analysis showed the DeepScope model achieves 93\% accuracy, with precision of 90\% and recall exceeding 94\%. The DeepScope model was deployed on a web server, and mobile applications for Android and iOS were developed, enabling Internet-based or smartphone-based water safety testing, with results obtained in seconds.