journal article·2026-06-30Open access

Hardware‐Attentive Programmable Fourier Ptychography Enables Task‐Adaptive Label‐Free Virtual Staining

Tianyue He, Wenyi Jing, Le Zhang, Qican Zhang, Tingdong Kou, Xin He, Yan Qiu, Yang Lu, Jian Cui, Yongfu Wen, Zhenrong Zheng, Hongying Zhang, Dayong Jin, Junfei Shen

Abstract

ABSTRACT Virtual staining will enable fast and reagent‐free histological imaging toward accurate and consistent pathology diagnosis. However, most current developments rely on heuristic optical landmarks and blind reconstruction, which reduces interpretability, limits cross‐task adaptations, and prevents their ultimate clinical translations. Here, we introduce an interpretable Plain‐to‐Stain framework, “Task‐Adaptive Programmable Optics (TAPO)” that removes manual landmark selection by directly tying programmable optical control to task‐specific diagnostic objectives. The approach operates under specially modulated visible light, and the highly programmable imaging system decomposes each optical step to execute optics‐attention‐based reconstruction, leading to task‐adaptive multimodal optical encoding for virtual staining. We demonstrated that TAPO successfully passed rigorous validation across diverse tissue types (liver, lung), pathological states (normal, malignant), staining protocols (H&E, Masson's trichrome), magnifications (10×, 20×), and section‐thickness settings including routine 4 µm sections and moderately thicker 10 µm sections. Blinded assessments by a panel of board‐certified pathologists on multiple virtual slides showed that TAPO results had high clinical acceptance, especially in resolution, cytoplasmic clarity, and nuclear staining, and demonstrated considerable potential for clinical pathology practice.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Advanced X-ray Imaging Techniques · Digital Holography and Microscopy · Optical Coherence Tomography Applications

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

College of Electronics and Information Engineering Sichuan University Chengdu Sichuan China

Department of Pathology West China Hospital Sichuan University Chengdu Sichuan China

Institute For Biomedical Materials and Devices (IBMD) Faculty of Science University of Technology Sydney Ultimo New South Wales Australia

Jiangxi Gaorui Optoelectronics Co., Ltd Nanchang Jiangxi China

State Key Laboratory of Modern Optical Instrumentation College of Optical Science and Engineering Zhejiang University Hangzhou China

Funding

National Key Research and Development Program of China

References (52)

Show source-provided references
1. 10.1109/jstqe.2022.323352310.1109/jstqe.2022.3233523 ↗
2. 10.1186/s13000‐024‐01461‐w10.1186/s13000‐024‐01461‐w ↗
3. 10.1038/s41591‐019‐0508‐110.1038/s41591‐019‐0508‐1 ↗
4. 10.1038/s41591‐024‐03141‐010.1038/s41591‐024‐03141‐0 ↗
5. 10.1016/j.jpi.2025.10042310.1016/j.jpi.2025.100423 ↗
6. 10.1186/s12880‐024‐01498‐910.1186/s12880‐024‐01498‐9 ↗
7. 10.34133/2020/964716310.34133/2020/9647163 ↗
8. Deep Learning‐enabled Virtual Histological Staining of Biological samples10.1038/s41377-023-01104-7 ↗
9. 10.1038/s41551‐019‐0362‐y10.1038/s41551‐019‐0362‐y ↗
10. 10.1038/s41467‐021‐25221‐210.1038/s41467‐021‐25221‐2 ↗
11. 10.1038/s41377‐019‐0129‐y10.1038/s41377‐019‐0129‐y ↗
12. J. Y.Zhu T.Park P.Isola andA. A.Efros “Unpaired Image‐To‐Image Translation Using Cycle‐Consistent Adversarial Networks ” in2017 IEEE International Conference on Computer Vision (ICCV) Venice Italy(2017) 2242–2251.10.1109/ICCV.2017.244 ↗
13. 10.1038/s41467‐024‐46077‐210.1038/s41467‐024‐46077‐2 ↗
14. 10.1016/j.tibtech.2024.02.00910.1016/j.tibtech.2024.02.009 ↗
15. 10.1038/s41379‐020‐00718‐110.1038/s41379‐020‐00718‐1 ↗
16. 10.1002/ima.2316510.1002/ima.23165 ↗
17. 10.1016/j.ajpath.2022.09.01110.1016/j.ajpath.2022.09.011 ↗
18. 10.1021/acsphotonics.2c0093210.1021/acsphotonics.2c00932 ↗
19. 10.34133/2022/985360610.34133/2022/9853606 ↗
20. 10.1016/j.modpat.2025.10084210.1016/j.modpat.2025.100842 ↗
21. 10.1038/s41467‐023‐41574‐210.1038/s41467‐023‐41574‐2 ↗
22. 10.1177/000370281881985710.1177/0003702818819857 ↗
23. 10.1146/annurev‐anchem‐101422‐09095610.1146/annurev‐anchem‐101422‐090956 ↗
24. 10.1021/acsnano.1c1150710.1021/acsnano.1c11507 ↗
25. 10.1063/5.012296510.1063/5.0122965 ↗
26. 10.1038/s41467‐024‐52263‐z10.1038/s41467‐024‐52263‐z ↗
27. Generating Bright‐field Images of Stained Tissue Slices From Mueller Matrix Polarimetric Images With CycleGAN Using Unpaired Dataset10.1142/S1793545823430034 ↗
28. 10.1126/sciadv.adv074110.1126/sciadv.adv0741 ↗
29. 10.1016/j.pacs.2021.10030810.1016/j.pacs.2021.100308 ↗
30. 10.1038/s41377‐024‐01554‐710.1038/s41377‐024‐01554‐7 ↗
31. 10.1038/s41551‐022‐00940‐z10.1038/s41551‐022‐00940‐z ↗
32. 10.1038/s41377‐020‐0315‐y10.1038/s41377‐020‐0315‐y ↗
33. 10.1038/s41467‐018‐04470‐810.1038/s41467‐018‐04470‐8 ↗
34. 10.1038/s41591‐019‐0715‐910.1038/s41591‐019‐0715‐9 ↗
35. 10.1186/s43074‐023‐00113‐410.1186/s43074‐023‐00113‐4 ↗
36. 10.1016/j.media.2025.10386510.1016/j.media.2025.103865 ↗
37. L.Kreiss S.Jiang X.Li et al. “Digital Staining in Optical Microscopy Using Deep Learning – a Review ”PhotoniX4(2023):34 https://doi.org/10.1186/s43074‐023‐00113‐4.10.1186/s43074-023-00113-4 ↗
38. 10.1007/s00521‐013‐1368‐010.1007/s00521‐013‐1368‐0 ↗
39. Information Theoretic Methods for Variable Selection—A Review10.3390/e24081079 ↗
40. 10.1038/s41377‐023‐01104‐710.1038/s41377‐023‐01104‐7 ↗
41. 10.1038/s41551‐025‐01421‐910.1038/s41551‐025‐01421‐9 ↗
42. 10.1016/j.artmed.2022.10236810.1016/j.artmed.2022.102368 ↗
43. 10.1016/j.compbiomed.2019.10337510.1016/j.compbiomed.2019.103375 ↗
44. Gans trained by a two time‐scale update rule converge to a local nash equilibrium
45. 10.1371/journal.pone.025343910.1371/journal.pone.0253439 ↗
46. 10.1080/01478885.2019.170861110.1080/01478885.2019.1708611 ↗
47. 10.1016/j.patter.2023.10072510.1016/j.patter.2023.100725 ↗
48. 10.1007/s11307‐021‐01641‐w10.1007/s11307‐021‐01641‐w ↗
49. 10.1109/EMBC46164.2021.963002610.1109/EMBC46164.2021.9630026 ↗
50. 10.1038/s44303‐024‐00021‐710.1038/s44303‐024‐00021‐7 ↗
51. 10.1038/s41467‐020‐20062‐x10.1038/s41467‐020‐20062‐x ↗
52. 10.1038/s41377‐019‐0129‐y10.1038/s41377‐019‐0129‐y ↗