Physics Maths Engineering
Baekcheon Seong,
Woovin Kim,
Younghun Kim,
Jong-Seok Lee,
Jeonghoon Yoo,
Chulim Joo
Peer Reviewed
Abstract Several image-based biomedical diagnoses require high-resolution imaging capabilities at large spatial scales. However, conventional microscopes exhibit an inherent trade-off between depth-of-field (DoF) and spatial resolution, and thus require objects to be refocused at each lateral location, which is time-consuming. Here, we present a computational imaging platform, termed E2E-BPF microscope, which enables large-area, high-resolution imaging of large-scale objects without serial refocusing. This method involves a physics-incorporated, deep-learned design of binary phase filter (BPF) and jointly optimized deconvolution neural network, which altogether produces high-resolution, high-contrast images over extended depth ranges. We demonstrate the method through numerical simulations and experiments with fluorescently labeled beads, cells and tissue section, and present high-resolution imaging capability over a 15.5-fold larger DoF than the conventional microscope. Our method provides highly effective and scalable strategy for DoF-extended optical imaging system, and is expected to find numerous applications in rapid image-based diagnosis, optical vision, and metrology.
The E2E-BPF microscope is a computational imaging platform designed to overcome the trade-off between depth-of-field (DoF) and spatial resolution in conventional microscopes. It enables high-resolution imaging over large areas without the need for time-consuming refocusing.
High-resolution imaging at large scales is crucial for biomedical diagnoses, such as analyzing tissue samples or cells. It allows researchers and clinicians to observe fine details over wide areas, improving accuracy and efficiency in diagnostics.
Conventional microscopes struggle with a trade-off between depth-of-field (DoF) and spatial resolution. To image large objects, they require serial refocusing at each lateral location, which is slow and impractical for large-scale imaging.
The E2E-BPF microscope uses a physics-incorporated, deep-learned binary phase filter (BPF) and a jointly optimized deconvolution neural network. This combination extends the depth-of-field by 15.5 times compared to conventional microscopes, enabling high-resolution imaging without refocusing.
A binary phase filter (BPF) is an optical component that modifies the phase of light passing through it. In the E2E-BPF microscope, the BPF is designed using deep learning to optimize imaging performance over extended depth ranges.
Deep learning is used to design the BPF and optimize the deconvolution neural network. This ensures high-resolution, high-contrast images over large areas, even at extended depths, by learning and compensating for optical aberrations.
The E2E-BPF microscope:
The microscope was tested through numerical simulations and experiments with fluorescently labeled beads, cells, and tissue sections. Results demonstrated its ability to maintain high resolution and contrast over extended depths.
The E2E-BPF microscope is ideal for:
Traditional methods require constant refocusing and struggle with depth-of-field limitations. The E2E-BPF microscope overcomes these challenges, offering faster, more efficient, and higher-quality imaging over large areas.
Future research could focus on:
Show by month | Manuscript | Video Summary |
---|---|---|
2025 April | 3 | 3 |
2025 March | 67 | 67 |
2025 February | 55 | 55 |
2025 January | 60 | 60 |
2024 December | 56 | 56 |
2024 November | 63 | 63 |
2024 October | 46 | 46 |
2024 September | 64 | 64 |
2024 August | 36 | 36 |
2024 July | 46 | 46 |
2024 June | 30 | 30 |
2024 May | 43 | 43 |
2024 April | 44 | 44 |
2024 March | 10 | 10 |
Total | 623 | 623 |
Show by month | Manuscript | Video Summary |
---|---|---|
2025 April | 3 | 3 |
2025 March | 67 | 67 |
2025 February | 55 | 55 |
2025 January | 60 | 60 |
2024 December | 56 | 56 |
2024 November | 63 | 63 |
2024 October | 46 | 46 |
2024 September | 64 | 64 |
2024 August | 36 | 36 |
2024 July | 46 | 46 |
2024 June | 30 | 30 |
2024 May | 43 | 43 |
2024 April | 44 | 44 |
2024 March | 10 | 10 |
Total | 623 | 623 |