Relating Human and AI-based Detection Limits in SEM Dimensional Metrology

Published

October 25, 2025

Author(s)

Peter Bajcsy, Pushkar Sathe, Andras Vladar

Abstract

Background: The nanoscale measurements of critical dimensions in semiconductor manufacturing rely on scanning electron microscopy (SEM) and SEM image analyses. The acquisition of SEM images requires a low primary electron beam current and a low dose of the SEM imaging microscope to avoid integrated circuit (IC) sample charging and inflicted damage to sensitive IC structures. These requirements inevitably result in \textitnoisy, low-contrast images}, which can make traditional SEM image analyses no longer viable. Aim: With the advancement in computational hardware and artificial intelligence (AI) models, IC structure detection via \textitSEM image segmentation based on AI models} can extend the viability of these measurements from noisy, low-contrast images. However, the use of AI models raises questions about the detection limits of extracted measurements and the confidence in reported measurements Approach: Our approach is to relate SEM image quality characteristics with AI-based object segmentation accuracy to establish detection limits of AI-based models and their relationships to human detection limits. Using SEM image simulation software, we create six image sets of quasi-circular objects on a substrate with varying noise and contrast characteristics. These sets of SEM images are characterized by 25 image quality metrics and then used to train and evaluate three AI models. The 25 SEM image quality characteristics and three AI model accuracy metrics per SEM image define the mapping between the quality of input SEM images and the performance of the trained AI models. Results: We used the mapping to establish the detection limits of trained AI models with respect to a required confidence and then to relate the human detection limits to the trained AI model detection limits. The human detection limit has been established by Rose as the minimal signal-to-noise ratio (SNR) of five to reliably delineate the shape and size of objects in an image. We matched the $SNR$ defined by Rose to image quality characteristics and demonstrated the upper and lower $SNR$ bounds for three AI models with respect to the human detection limit and for a specified confidence. Conclusions: This work establishes a method to determine the detection limits of AI-based SEM dimensional metrology. The work is relevant to semiconductor vendors and consumers of AI models since critical dimension measurements are derived from noisy and low-contrast SEM images using AI models with varying performance characteristics. Given a measured SEM with estimated noise and contrast characteristics, each AI model will be characterized by unique detection limits that can be trusted in semiconductor production. Our method enables improving the trust in critical dimensions while using advanced AI models.

Citation

Journal of Micro/Nanopatterning, Materials, and Metrology

Volume

24

Issue

4

Pub Type

Journals

Download Paper

https://doi.org/10.1117/1.JMM.24.4.044201

Local Download

Keywords

scanning electron microscopy, SEM, dimensional metrology, detection limits, AI model.

Citation

Bajcsy, P. , Sathe, P. and Vladar, A. (2025), Relating Human and AI-based Detection Limits in SEM Dimensional Metrology, Journal of Micro/Nanopatterning, Materials, and Metrology, [online], https://doi.org/10.1117/1.JMM.24.4.044201, https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=960148 (Accessed March 6, 2026)