Hot Paper - Holotomography-driven learning unlocks in-silico staining of single cells in flow cytometry by avoiding fluorescence co-registration

Holotomography-driven learning unlocks in-silico staining of single cells in flow cytometry by avoiding fluorescence co-registration

全息成像驱动的学习通过避免荧光共定位，实现了流式细胞术中的单细胞计算机模拟染色
ホロトモグラフィー駆動学習は、蛍光共登録を回避することでフローサイトメトリーにおけるシングルセルのインシリコ染色を可能にする
홀로토모그래피 기반 학습은 형광 공동 등록을 피함으로써 유세포 분석에서 단일 세포의 시뮬레이션 염색을 가능하게 한다
El aprendizaje impulsado por holotomografía desbloquea el tinción in silico de células individuales en citometría de flujo al evitar la co-registración de fluorescencia
L'apprentissage guidé par holotomographie permet la coloration in silico des cellules individuelles en cytométrie en flux en évitant la co-échantillonnage par fluorescence
Обучение на основе голотомографии позволяет проводить in silico окрашивание отдельных клеток в проточной цитометрии, избегая совместной регистрации флуоресценции

Daniele Pirone ¹, Giusy Giugliano ¹ ², Michela Schiavo ¹ ² ³ ⁴, Annalaura Montella ⁵ ⁶, Martina Mugnano ⁷, Vincenza Cerbone ⁵, Maddalena Raia ⁵, Giulia Scalia ⁵, Ivana Kurelac ⁸ ⁹, Diego Luis Medina ³ ¹⁰, Lisa Miccio ¹, Mario Capasso ⁵ ⁶, Achille Iolascon ⁵ ⁶, Pasquale Memmolo ¹, Pietro Ferraro ¹

¹ CNR-ISASI, Institute of Applied Sciences and Intelligent Systems "E. Caianiello", Via Campi Flegrei 34, 80078 Pozzuoli, Napoli, Italy
² Department of Mathematics and Physics, University of Campania "Luigi Vanvitelli", Viale Abramo Lincoln 5, 81100 Caserta, Italy
³ TIGEM, Telethon Institute of Genetics and Medicine, Via Campi Flegrei 34, 80078 Pozzuoli, Napoli, Italy
⁴ Department of Advanced Biomedical Science, University of Naples "Federico II", Via Sergio Pansini 5, 80131 Napoli, Italy
⁵ CEINGE - Advanced Biotechnologies, Via Gaetano Salvatore 486, 80131 Napoli, Italy
⁶ DMMBM, Department of Molecular Medicine and Medical Biotechnology, University of Naples "Federico II", Via Pansini 5, 80131 Napoli, Italy
⁷ DICMaPI, Department of Chemical, Materials and Production Engineering, University of Naples "Federico II", Piazzale Tecchio 80, 80125 Napoli, Italy
⁸ DIMEC, Department of Medical and Surgical Sciences, Alma Mater Studiorum-University of Bologna, Via Irnerio 49, 40126 Bologna, Italy
⁹ IRCCS Azienda Ospedaliero-Universitaria di Bologna, 40138 Bologna, Italy
¹⁰ Medical Genetics Unit, Department of Medical and Translational Science, University of Naples "Federico II", Via Sergio Pansini 5, 80131 Napoli, Italy

https://doi.org/10.29026/oes.2026.260003

https://www.oejournal.org/oes/article/doi/10.29026/oes.2026.260003

Opto-Electronic Science, 25 February 2026

Abstract

Virtual staining is the current state-of-the-art computational technique to cleverly enhance intracellular specificity in unstained biological samples by using convolutional neural networks (CNNs) trained on co-registered pairs of unstained/stained images. While effective, this approach suffers from unpredictable biases inherent to fluorescence microscopy and encounters challenges when applied to flow cytometry data as it would require accurate co-registration on a huge number of images.

Here, we present a novel method that exploits for the first time a Holotomography-driven learning to completely eliminate the need for co-registration. We demonstrate that training a CNN on a stain-free dataset of 3D refractive index tomograms of flowing cells unlocks stain-free intracellular specificity for the first time in quantitative phase imaging flow cytometry.

This self-supervised solution, by circumventing the critical obstacle of fluorescence co-registration, opens unprecedented perspectives for label-free, high-throughput imaging flow cytometry, offering a powerful new paradigm for advanced 2D and 3D single-cell analysis.

Reviews and Discussions