Deep learning enhanced mobile-phone microscopy

TL;DR

This paper demonstrates how deep learning can correct distortions in mobile-phone microscopy images, enabling high-resolution, color-accurate imaging comparable to traditional microscopes, suitable for telemedicine and biomedical use.

Contribution

It introduces a deep learning approach to enhance mobile-phone microscopy images, correcting distortions and improving image quality for clinical and biomedical applications.

Findings

High-resolution images comparable to benchtop microscopes

Effective correction of spatial and spectral distortions

Applicable to various low-cost imaging systems

Abstract

Mobile-phones have facilitated the creation of field-portable, cost-effective imaging and sensing technologies that approach laboratory-grade instrument performance. However, the optical imaging interfaces of mobile-phones are not designed for microscopy and produce spatial and spectral distortions in imaging microscopic specimens. Here, we report on the use of deep learning to correct such distortions introduced by mobile-phone-based microscopes, facilitating the production of high-resolution, denoised and colour-corrected images, matching the performance of benchtop microscopes with high-end objective lenses, also extending their limited depth-of-field. After training a convolutional neural network, we successfully imaged various samples, including blood smears, histopathology tissue sections, and parasites, where the recorded images were highly compressed to ease storage and transmission for telemedicine applications. This method is applicable to other low-cost, aberrated imaging systems, and could offer alternatives for costly and bulky microscopes, while also providing a framework for standardization of optical images for clinical and biomedical applications.