In a study led by Tampere University, researchers have developed a new lensless imaging method that produces precise quantitative data on living cells from a single image. The compact system can be placed inside a standard cell-culture incubator, allowing living cells to be monitored continuously for hours or even days without staining or other labels.
Researchers have developed a new lensless quantitative phase imaging method, called SF-PULSE, which combines an AI-based neural network with physics-informed image reconstruction.
The method is designed for use in a compact imaging system that can operate directly inside a standard cell-culture incubator. This allows cells to be monitored continuously for hours or even days without the need for staining or repeated removal from the incubator for imaging.
Quantitative phase imaging is a technique that enables the observation of living, transparent cells without staining. In addition to producing images of cells, it provides quantitative information about features such as cell growth, size and changes in biomass.
The researchers set out to address two major limitations of quantitative phase imaging. Conventional quantitative phase imaging methods typically rely on large and complex microscope systems that are not well suited for long-term monitoring inside a cell-culture incubator. In addition, recovering phase information in lensless systems is a challenging computational problem that has traditionally required multiple images or additional optical components.
“Our SF-PULSE method can reconstruct quantitative phase information from a single measurement image without the need for complex optical hardware. The method reduced computational errors, improved reconstruction stability and enabled accurate long-term tracking of individual cells,” says Igor Shevkunov , the study’s first author from the Faculty of Information Technology and Communication Sciences at Tampere University.
The result is important because it enables long-term, uninterrupted and label-free monitoring of large numbers of cells. The method produces quantitative information about the behaviour of individual cells, which is often far more informative than analysing only the average behaviour of a cell population.
“Importantly, researchers can follow not only how a cell population changes, but also how individual cells grow, move, divide, and gain or lose biomass over time. This is often more informative than examining the average behaviour of a cell population alone,” says Meenakshisundaram Kandhavelu , University Lecturer in the Faculty of Medicine and Health Technology at Tampere University and head of the Molecular Signaling research group.
Rather than simply providing another imaging modality, SF-PULSE has the potential to enable entirely new types of biological experiments. The method could support applications such as drug-response studies, toxicity screening and investigations of cell-death mechanisms.
Because the system is compact, lensless and capable of monitoring hundreds or even thousands of cells simultaneously across a wide field of view, it could also be used for automated biological analytics and the development of new biomedical instrumentation in the future.
Applied Physics Letters
Single-frame lensless phase retrieval using learned sensor plane initialization
21-Sep-2026