Self-supervised image quality assessment for X-ray tomographic images of Li-ion battery

Image perception plays a fundamental role in the tomography-based approaches for microstructure characterization and has a deep impact on all subsequent stages of image processing,such as segmentation and 3D analysis.The enhancement of image perception,however,frequently involves observer-dependence,which reflects user-to-user dispersion and uncertainties in the calculated parameters.This work presents an objective quantitative method,which uses convolutional neural networks (CNN) for the quality assessment of the X-ray tomographic images.With only dozens of annotations,our method allows to evaluate directly and precisely the quality of tomographic images.Different metrics were employed to evaluate the correlation between our predicted scores and subjective human annotations.The evaluation results demonstrate that our method can be a direct tool to guide the enhancement process in order to produce reliable segmentation results.The processing of the tomographic image can thus evolve into a robust observer-independent procedure and advance towards the development of an efficient self-supervised approach.

Artificial neural network approach for multiphase segmentation of battery electrode nano-CT images

The segmentation of tomographic images of the battery electrode is a crucial processing step,which will have an additional impact on the results of material characterization and electrochemical simulation.However,manually labeling X-ray CT images(XCT)is time-consuming,and these XCT images are generally difficult to segment with histographical methods.We propose a deep learning approach with an asymmetrical depth encode-decoder convolutional neural network(CNN)for real-world battery material datasets.This network achieves high accuracy while requiring small amounts of labeled data and predicts a volume of billions voxel within few minutes.While applying supervised machine learning for segmenting real-world data,the ground truth is often absent.The results of segmentation are usually qualitatively justified by visual judgement.We try to unravel this fuzzy definition of segmentation quality by identifying the uncertainty due to the human bias diluted in the training data.Further CNN trainings using synthetic data show quantitative impact of such uncertainty on the determination of material’s properties.Nano-XCT datasets of various battery materials have been successfully segmented by training this neural network from scratch.We will also show that applying the transfer learning,which consists of reusing a well-trained network,can improve the accuracy of a similar dataset.