Fourier ptychographic microscopy image enhancement with bi-modal deep learning
Biomedical Optics Express · 01.07.2023 · 14 (7) · 3172
DOI: 10.1364/boe.489776 ↗Kurz gefasst
Fachartikel in der Zeitschrift Biomedical Optics Express, online erschienen am 07.06.2023. Verfasst von Lyes Bouchama und 4 weiteren Autor:innen. Beteiligte Einrichtung: Samovar, Télécom SudParis, Institut Polytechnique de Paris, 91120 Palaiseau, France. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 30 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.
Abstract (Originalsprache)
Digital pathology based on a whole slide imaging system is about to permit a major breakthrough in automated diagnosis for rapid and highly sensitive disease detection. High-resolution FPM (Fourier ptychographic microscopy) slide scanners delivering rich information on biological samples are becoming available. They allow new effective data exploitation for efficient automated diagnosis. However, when the sample thickness becomes comparable to or greater than the microscope depth of field, we report an observation of undesirable contrast change of sub-cellular compartments in phase images around the optimal focal plane, reducing their usability. In this article, a bi-modal U-Net artificial neural network (i.e., a two channels U-Net fed with intensity and phase images) is trained to reinforce specifically targeted sub-cellular compartments contrast for both intensity and phase images. The procedure used to construct a reference database is detailed. It is obtained by exploiting the FPM reconstruction algorithm to explore images around the optimal focal plane with virtual Z-stacking calculations and selecting those with adequate contrast and focus. By construction and once trained, the U-Net is able to simultaneously reinforce targeted cell compartment visibility and compensate for any focus imprecision. It is efficient over a large field of view at high resolution. The interest of the approach is illustrated considering the use-case of Plasmodium falciparum detection in blood smear where improvement in the detection sensitivity is demonstrated without degradation of the specificity. Post-reconstruction FPM image processing with such U-Net and its training procedure is general and applicable to demanding biological screening applications.
Autor:innen und Institutionen
- Samovar, Télécom SudParis, Institut Polytechnique de Paris, 91120 Palaiseau, France.
- TRIBVN/T-life, 92800 Puteaux, France.
- Sorbonne Université, INSERM, Institut Pierre Louis d'Epidémiologie et de Santé Publique, AP-HP, Hôpital Pitié-Salpêtrière, 75013 Paris, France.
ORCID-Profile: Lyes Bouchama, Yaneck Gottesman
Zitieren
APA
Bouchama, L., Dorizzi, B., Thellier, M., Klossa, J., & Gottesman, Y. (2023). Fourier ptychographic microscopy image enhancement with bi-modal deep learning. Biomedical Optics Express, 14(7), 3172. https://doi.org/10.1364/boe.489776
Vancouver
Bouchama L, Dorizzi B, Thellier M, Klossa J, Gottesman Y. Fourier ptychographic microscopy image enhancement with bi-modal deep learning. Biomedical Optics Express. 2023;14(7):3172. doi:10.1364/boe.489776
BibTeX
@article{Bouchama2023,
author = {Bouchama, Lyes and Dorizzi, Bernadette and Thellier, Marc and Klossa, Jacques and Gottesman, Yaneck},
title = {Fourier ptychographic microscopy image enhancement with bi-modal deep learning},
journal = {Biomedical Optics Express},
year = {2023},
volume = {14},
number = {7},
pages = {3172},
doi = {10.1364/boe.489776}
}
EUVIMED