Reducing image artefacts in electron microscopy

A method (100) for training an artificial neural network (ANN) to reduce noise and/or artefacts in an electron microscopy image is disciosed. A plurality of training image pairs is generated (101 ). For each pair, an undistorted synthetic specimen image is created (102) and a distorted image is created (103) by simulating additional noise and/or artefact features. The ANN is trained, in which the distorted images are used as input and the corresponding undistorted images as output. An adversarial training strategy is used in which the ANN is trained, as a generator network, in conjunction with concomitantly training a further ANN, as a discriminator network, to differentiate output produced by the generator network from synthetic images in the training set. In said training (109), parameters of the ANN and further ANN are optimized using a generator loss function and a discriminator loss function, in which a dependency exists between said toss functions to train the networks in an adversarial manner.

Patent Publication Number: WO2023111772

Year filing: 2022

Year approval: 2024

Year publication: 2023

Status: Requested

Technology domains: Computer technology

Validated for IOF-key: Yes

Attributed to: Associatie Universiteit & Hogescholen Antwerpen