Enhancing 3D Reconstruction Accuracy of FIB Tomography Data Using Multi‑voltage Images and Multimodal Machine Learning

作     者：Trushal Sardhara Alexander Shkurmanov Yong Li Lukas Riedel Shan Shi Christian J.Cyron Roland C.Aydin Martin Ritter Trushal Sardhara;Alexander Shkurmanov;Yong Li;Lukas Riedel;Shan Shi;Christian J.Cyron;Roland C.Aydin;Martin Ritter

作者机构：Institute for Continuum and Material MechanicsHamburg University of TechnologyHamburgGermany Electron Microscopy UnitHamburg University of TechnologyHamburgGermany Institute of Materials Physics and TechnologyHamburg University of TechnologyHamburgGermany Institute of Materials MechanicsHelmholtz-Zentrum HereonGeesthachtGermany Research Group of Integrated Metallic Nanomaterials SystemsHamburg University of TechnologyHamburgGermany Institute of Material Systems ModelingHelmholtz-Zentrum HereonGeesthachtGermany 

出 版 物：《Nanomanufacturing and Metrology》 (纳米制造与计量（英文）)

年 卷 期：2024年第7卷第1期

页      面：48-60页

核心收录：

学科分类：08[工学] 081104[工学-模式识别与智能系统] 080203[工学-机械设计及理论] 0802[工学-机械工程] 0811[工学-控制科学与工程] 

基　　金：funded by the Deutsche Forschungsgemein-schaft(DFG German Research Foundation)-SFB 986-Project number 192346071. 

主　　题：Multimodal machine learning Multi-voltage images FIB-SEM Overdeterministic systems 3D reconstruction FIB tomography 

摘      要：FIB-SEM tomography is a powerful technique that integrates a focused ion beam(FIB)and a scanning electron microscope(SEM)to capture high-resolution imaging data of nanostructures.This approach involves collecting in-plane SEM imagesand using FIB to remove material layers for imaging subsequent planes,thereby producing image stacks.However,theseimage stacks in FIB-SEM tomography are subject to the shine-through effect,which makes structures visible from theposterior regions of the current plane.This artifact introduces an ambiguity between image intensity and structures in thecurrent plane,making conventional segmentation methods such as thresholding or the k-means algorithm insufficient.Inthis study,we propose a multimodal machine learning approach that combines intensity information obtained at differentelectron beam accelerating voltages to improve the three-dimensional(3D)reconstruction of nanostructures.By treatingthe increased shine-through effect at higher accelerating voltages as a form of additional information,the proposed methodsignificantly improves segmentation accuracy and leads to more precise 3D reconstructions for real FIB tomography data.