EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Machine Learning Approach to 3×4 Mueller Polarimetry for Complete Reconstruction of Diagnostic Polarimetric Images of Biological Tissues

Sooyong Chae, Tongyu Huang, Omar Rodriguez-Nunez, Theotim Lucas, Jean-Charles Vanel, Jeremy Vizet, Angelo Pierangelo, Gennadii Piavchenko, Tsanislava Genova, Ajmal Ajmal, Jessica C Ramella-Roman, Alexander Doronin und 2 weitere

IEEE Transactions on Medical Imaging · 2025-09 · 44 (9) · 3820-3831

DOI: 10.1109/tmi.2025.3567570 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Medical Imaging, 2025-09. Verfasst von Sooyong Chae und 13 weiteren Autor:innen. Hauptthemen laut MEDLINE: Machine Learning, Image Processing, Computer-Assisted. Die Arbeit wurde bisher 19-mal zitiert (Crossref) und nennt 65 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Funds from Swiss National Science Foundation under HORAO, Campus France Partenariat Hubert Curien (PHC) “Dumont D’Urville” under POLANNs, Royal Society Te Apārangi.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The translation of imaging Mueller polarimetry to clinical practice is often hindered by large footprint and relatively slow acquisition speed of the existing instruments. Using polarization-sensitive camera as a detector may reduce instrument dimensions and allow data streaming at video rate. However, only the first three rows of a complete ${4}\times {4}$ Mueller matrix can be measured. To overcome this hurdle we developed a machine learning approach using sequential neural network algorithm for the reconstruction of missing elements of a Mueller matrix from the measured elements of the first three rows. The algorithm was trained and tested on the dataset of polarimetric images of various excised human tissues (uterine cervix, colon, skin, brain) acquired with two different imaging Mueller polarimeters operating in either reflection (wide-field imaging system) or transmission (microscope) configurations at different wavelengths of 550 nm and 385 nm, respectively. Reconstruction performance was evaluated using various error metrics, all of which confirmed low error values. The reconstruction of full images of the fourth row of Mueller matrix with GPU parallelization and increasing batch size took less than 50 milliseconds. It suggests that a machine learning approach with parallel processing of all image pixels combined with the partial Mueller polarimeter operating at video rate can effectively substitute for the complete Mueller polarimeter and produce accurate maps of depolarization, linear retardance and orientation of the optical axis of biological tissues, which can be used for medical diagnosis in clinical settings.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningImage Processing, Computer-AssistedHumansAlgorithmsBrainFemaleColonCervix UteriSkinMicroscopy, Polarization

Förderung

  • Funds from Swiss National Science Foundation under HORAO
  • Campus France Partenariat Hubert Curien (PHC) “Dumont D’Urville” under POLANNs
  • Royal Society Te Apārangi
  • Campus France PHC “Rila” under AURORA
  • Campus France PHC “Osmose” under PHAETHON
  • European Cooperation in Science and Technology (COST) Action PhoBioS
  • Institut National du Cancer and Cancéropóle, France
  • NSF under STROBE

Zitieren

APA

Chae, S., Huang, T., Rodriguez-Nunez, O., Lucas, T., Vanel, J. C., Vizet, J., Pierangelo, A., Piavchenko, G., Genova, T., Ajmal, A., Ramella-Roman, J. C., Doronin, A., Ma, H., & Novikova, T. (2025). Machine Learning Approach to 3×4 Mueller Polarimetry for Complete Reconstruction of Diagnostic Polarimetric Images of Biological Tissues. IEEE Transactions on Medical Imaging, 44(9), 3820-3831. https://doi.org/10.1109/tmi.2025.3567570

Vancouver

Chae S, Huang T, Rodriguez-Nunez O, Lucas T, Vanel JC, Vizet J, et al. Machine Learning Approach to 3×4 Mueller Polarimetry for Complete Reconstruction of Diagnostic Polarimetric Images of Biological Tissues. IEEE Transactions on Medical Imaging. 2025;44(9):3820-3831. doi:10.1109/tmi.2025.3567570

BibTeX
@article{Chae2025,
  author = {Chae, Sooyong and Huang, Tongyu and Rodriguez-Nunez, Omar and Lucas, Theotim and Vanel, Jean-Charles and Vizet, Jeremy and Pierangelo, Angelo and Piavchenko, Gennadii and Genova, Tsanislava and Ajmal, Ajmal and Ramella-Roman, Jessica C and Doronin, Alexander and Ma, Hui and Novikova, Tatiana},
  title = {Machine Learning Approach to 3×4 Mueller Polarimetry for Complete Reconstruction of Diagnostic Polarimetric Images of Biological Tissues},
  journal = {IEEE Transactions on Medical Imaging},
  year = {2025},
  volume = {44},
  number = {9},
  pages = {3820--3831},
  doi = {10.1109/tmi.2025.3567570}
}
Kostenlos starten →