Blind-structured illumination microscopy (blind-SIM) enhances the optical resolution without the requirement of nonlinear effects or pre-defined illumination patterns. It is thus advantageous in experimental conditions where toxicity or biological fluctuations are an issue. In this work, we introduce a custom convolutional neural network architecture for blind-SIM: BS-CNN. We show that BS-CNN outperforms other blind-SIM deconvolution algorithms providing a resolution improvement of 2.17 together with a very high Fidelity (artifacts reduction). Furthermore, BS-CNN proves to be robust in cross-database variability: it is trained on synthetically augmented open-source data and evaluated on experiments. This approach paves the way to the employment of CNN-based deconvolution in all scenarios in which a statistical model for the illumination is available while the specific realizations are unknown or noisy.
Deep learning for blind structured illumination microscopy / Xypakis, Emmanouil; Gosti, Giorgio; Giordani, Taira; Santagati, Raffaele; Ruocco, Giancarlo; Leonetti, Marco. - In: SCIENTIFIC REPORTS. - ISSN 2045-2322. - 12:1(2022), p. 8623. [10.1038/s41598-022-12571-0]
Deep learning for blind structured illumination microscopy
Gosti, Giorgio;Giordani, Taira;Ruocco, Giancarlo;Leonetti, Marco
2022
Abstract
Blind-structured illumination microscopy (blind-SIM) enhances the optical resolution without the requirement of nonlinear effects or pre-defined illumination patterns. It is thus advantageous in experimental conditions where toxicity or biological fluctuations are an issue. In this work, we introduce a custom convolutional neural network architecture for blind-SIM: BS-CNN. We show that BS-CNN outperforms other blind-SIM deconvolution algorithms providing a resolution improvement of 2.17 together with a very high Fidelity (artifacts reduction). Furthermore, BS-CNN proves to be robust in cross-database variability: it is trained on synthetically augmented open-source data and evaluated on experiments. This approach paves the way to the employment of CNN-based deconvolution in all scenarios in which a statistical model for the illumination is available while the specific realizations are unknown or noisy.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.