Video Instead of Dozens of Shots: Urine Analysis Made Easier express
A drop of urine under a microscope isn't a flat puddle but a multi-layered volume. Like a stack of transparent pages: if you focus on one, the neighboring ones blur. The microscope's light only shows one depth layer sharply. To see all the cells, a lab technician had to take a series of snapshots, manually adjusting focus — tedious and slow.
Now, a short video (2–14 seconds) suffices, where the operator simply turns a knob. The software, like a diligent reader, flips through the frames and assembles a single image: each area is captured at its sharpest. Thus, from a mosaic of the best “pages,” a perfectly clear picture emerges. Then a neural network, trained on medical samples, quickly finds and identifies cell types. An unexpected bonus: hand tremors during manual focusing actually help, providing more angles for the algorithm.
Tests on 14 real samples showed accuracy just as good, and analysis many times faster. This brings automated microscopy closer to everyday hospitals, where every minute counts.
Original abstract
as written by the authors arXiv:2607.13601
Microscopic urinalysis is a routine diagnostic test at hospitals. Recent studies have demonstrated the effectiveness of deep learning methods to automate microscopic urinalysis. These methods rely on high-quality images of the urine samples in which each cell is clearly identifiable. However, in practice, the urine sample on a glass slide has a multi-layer structure; hence, all the cells are not clearly visible within the depth of field of a lens focused at a particular focal plane. It demands acquiring multiple images at different focal planes to correctly identify each cell in a given urine sample, which is a time-consuming task. In this paper, we propose to simplify the task by recording a video, in place of acquiring multiple images, while gradually changing the focus of the lens manually by hand. A typical length of the video is from 2 to 14 seconds. We reconstruct an all-in-focus image from the recorded video frames and apply a deep learning model to detect and classify urine sediments. As a proof of concept, we conduct experiments on 14 videos acquired by a trained lab technician in a usual diagnostic lab environment and show the effectiveness of the proposed automated urinalysis pipeline with our novel reconstruction algorithm.
Urine was used for diagnosis as early as Ancient Egypt: doctors watched how fast barley grains sank in it, a forerunner of modern test strips.
In science fiction stories, doctors diagnose from a single drop, like the medical tricorder from Star Trek. Now, that picture is becoming a bit more real.