Plug & Play AI microscope for urine sediment examination with CNN-based vision system

What is it all about?

In a urine sediment analysis, laboratory employees examine the solid components of a urine sample under a microscope to diagnose diseases of the kidney or urinary organs. However, manual examinations under microscopes generally carry a risk of errors and take up valuable time. Many laboratories therefore use automated systems. These differ according to the required performance, functionality, complexity, and design size, which also means they vary in terms of their integrated vision system. Opto’s AI digital microscope represented below features a convolutional neural network (CNN)-based embedded vision system. The cost-effective and high-performance microscope is a significant first step to automate lab analytics and processes.

What is the problem?

Lab analyses must increasingly be provided quickly and inexpensively without compromising on reliability. The decisive factor is the integration of the right hardware and software components - namely those that are coordinated with each other. Here it is realized with a CNN-based analysis algorithm on the right embedded vision system from Basler, completely integrated into a compact, robust Imaging Module profileM from Opto.

The solution

The AI microscope offers a reliable and inexpensive CNN-based vision system suitable for tasks such as automated microscopic examination of urine sediment.

The uniqueness of the solution lies in the integration of a high-performance transmitted digital light microscope out of the Opto imaging Module family and the powerful vision system consisting of a 5 MP color camera module and the Embedded Vision Processing Board.

The digital microscope has a magnification of 20x and an integrated transmitted white light LED condenser, optimized to the application of urine sediment analysis. The camera and processing board are completely integrated inside the full aluminum microscope frame and can be controlled through a one cable USB 3.0 connection. This results in an ultra-compact edge processing AI microscope sensor for the implementation in high throughput machineries or in a point of care (POC) analysis device.

The AI microscope presented here will come with an intuitive user interface for the urine sediment analysis and a pre-trained CNN for major marker to classify the urine sample for further diagnostics. The on-board software coordinates the image acquisition, processing and adjusts the LED.

To make this package plug & play, Opto offers as a service for OEM integration, individual training assistance for the CNN, and integration support in local network architectures. Opto can adjust existing algorithms to automate specific pre-classification of the patient samples.

Want the latest science news straight to your inbox? Become a SelectScience member for free today>>