公开(公告)号：US20240280522A1

公开(公告)日：2024-08-22

申请号：US18171541

申请日：2023-02-20

Applicant: FEI COMPANY

Inventor： Hans Vanrompay ,  Maurice Peemen

IPC: G01N23/2252 ,  G06N3/0455

CPC classification number: G01N23/2252 ,  G06N3/0455

Abstract: Disclosed herein are scientific instrument support systems, as well as related methods, apparatus, computing devices, and computer-readable media. Some embodiments provide a scientific instrument including detectors supporting one or more spectroscopic modalities and an imaging modality and further including an electronic controller configured to process streams of measurements received from the detectors. The electronic controller operates to generate a base image of the sample based on the measurements corresponding to the imaging modality and further operates to generate an anomaly map of the sample based on the base image and further based on differences between measured and autoencoder-reconstructed spectra corresponding to different pixels of the base image. In at least some instances, the anomaly map can beneficially be used in a quality-control procedure to identify, within seconds, specific problem spots in the sample for more-detailed inspection and/or analyses.

公开(公告)号：US20240281650A1

公开(公告)日：2024-08-22

申请号：US18171543

申请日：2023-02-20

Applicant: FEI Company

Inventor： Hans Vanrompay ,  Maurice Peemen

IPC: G06N3/08

CPC classification number: G06N3/08

Abstract: Disclosed herein are scientific instrument support systems, as well as related methods, apparatus, computing devices, and computer-readable media. Some embodiments provide a scientific instrument including detectors supporting two or more spectroscopic modalities and an imaging modality and further including an electronic controller configured to process streams of measurements received from the detectors. The electronic controller operates to generate a base image of the sample based on the measurements corresponding to the imaging modality and further operates to generate a cluster-mapped image of the sample based on the base image and further based on mappings of the measured spectra corresponding to different pixels of the base image to various clusters in the latent space of a variational autoencoder. In at least some instances, the cluster-mapped image can beneficially be used to identify, within seconds, chemically similar areas within the sample even when the measured spectra have relatively low signal-to-noise-ratio values.