Synthetic training data for endpoint detection models

Abstract

A computer-implemented method for generating synthetic data describing a sample may include: processing, by a system operatively coupled to a processor, sample information describing a set of original features of the sample, thereby producing processed model input information; and generating composite image data by analyzing a model and based on the processed model input information, the composite image data being usable to generate a composite image and describing at least a portion of the set of original features. The computer-implemented method may also include generating, by the system, a composite image of dummy samples based on the composite image data, the composite image having at least one dummy feature different from and based on the set of original features.

Description

Cross-reference to related applications

[0001] This application claims priority and benefit to U.S. Provisional Patent Application No. 63 / 701,475, filed September 30, 2024, entitled "Synthetic Data for Semiconductor Metrology, Imaging, and Microanalysis." The entire contents of the foregoing application are hereby incorporated by reference. Background Technology

[0002] Analytical models (such as machine learning models and / or artificial intelligence models) can be used to control imaging systems, sample preparation systems, production and / or manufacturing systems, etc. Preparing samples for training such analytical models can be a daunting task, involving the manual and timely preparation of dozens, hundreds, or even thousands of samples representing various aspects and / or parameters of the analytical model to be trained. Technical Field

[0003] Embodiments of this disclosure relate to charged particle microscopy systems and algorithms and methods for operating them. In particular, some embodiments relate to analytical models for enhancing sample preparation, such as machine learning models and / or artificial intelligence models. Summary of the Invention

[0004] The following summary is presented to provide a basic understanding of one or more exemplary embodiments described herein. This summary is not intended to identify key or essential elements and / or to depict the scope of a particular embodiment or the claims. Its sole purpose is to present concepts in a simplified form as a prelude to the more detailed description that follows. In one or more exemplary embodiments, the systems, computer-implemented methods, apparatuses, and / or computer program products described herein can provide systems and / or methods for generating synthetic samples and / or sample data for training analytical models, and / or for using such trained models to control imaging systems, sample preparation systems, production and / or manufacturing systems, etc.

[0005] According to one embodiment, a charged particle beam system may include: a charged particle source, a machine-actuated sample holder, and control circuitry operatively coupled to a memory storing computer-executable components; and a processor that executes the computer-executable components stored in the memory to perform operations including: generating image data of a sample disposed in the sample holder; inputting a portion of the image data into an analysis model trained based on a dataset of synthetic image data describing synthetic images corresponding to the image data of the sample; and generating control instructions via the analysis model configured to adjust the operation of the charged particle source or the sample holder in response to processing by the control circuitry.

[0006] According to another embodiment, a computer-implemented method for generating synthetic data describing samples may include: processing sample information of a set of original features describing the samples via a system operatively coupled to a processor to generate processed model input information; and generating synthetic image data by analyzing the model and based on the processed model input information, the synthetic image data being used to generate a synthetic image and describing at least a portion of the set of original features.

[0007] According to yet another embodiment, a computer program product facilitates a process for facilitating endpoint detection of an imaging device. The computer program product includes a computer-readable storage medium having program instructions embodied therein, which are executable by a processor to cause the processor to: process sample information describing a set of primitive features of a sample, thereby generating processed model input information; and generate synthetic image data by the processor and based on the processed model input information, the synthetic image data being used to generate a synthetic image and describing at least a portion of the set of primitive features.

[0008] According to another embodiment, a computer-implemented method includes: receiving microscope image data; detecting features in the microscope image data; receiving feature template data describing feature groups including the features; detecting the groups in the microscope image data based at least in part on the feature template data; generating template information describing the groups; and outputting the template information.

[0009] Detecting features in microscope image data may include: inputting at least a portion of the microscope image data into a model configured to detect the feature; and generating coordinate information describing the location of the feature in the microscope image data as the output of the model. The location of the feature may correspond to a set of coordinates relative to the centroid of the feature. The model may include a convolutional neural network trained to input a portion of the microscope image data and output coordinate information. The feature may be a first feature, the model may be a first model, the portion may be a first part, the coordinate information may be first coordinate information, and the location may be a first location. The microscope image data may include a second feature. The method may further include: inputting at least a second portion of the microscope image data into a second model configured to detect a second feature; and generating second coordinate information describing a second location of the second feature in the microscope image data as the output of the second model.

[0010] The feature template data can describe a sequence of multiple features including a first feature. Detecting this group can include: convolving the feature template data with coordinate information; and detecting instances of the group in the microscope image data based at least in part on the position of the feature relative to at least a subset of the multiple features in the sequence. Instances of detecting the group can include: determining a first order of the first feature in the sequence; and determining a first order of the first feature and a second order of the second feature in the sequence to match the feature template data.

[0011] Feature template data may include feature multiplicity information and feature order information. Detecting groupings in image data may include detecting instances of groupings with reversed feature order. Features may form at least a portion of a device in an integrated circuit. Microscope image data may include images generated by charged particle microscopy. Microscope image data may further include metadata mapping the pixels of the image data to locations on the sample.

[0012] Output template information may include sending template information to a charged particle microscope configured to generate image data at least in part based on the template information. The template information may include the positions of groups within the microscope image data. The positions of the groups may correspond to the vertices of the bounding box surrounding the groups.

[0013] According to another embodiment, one or more non-transitory machine-readable media store instructions that, when executed by a machine, cause the machine to perform the operations of the methods described above.

[0014] According to another embodiment, a system includes an analytical instrument configured to generate image data; and a computing device operatively coupled to the analytical instrument and configured to receive the image data from the analytical instrument. The computing device may be configured to include the medium and / or perform the methods described above. The analytical instrument may be or include a charged particle microscope. The computing device may be an instrument PC, a client computing device, or one or more servers. The computing device may be configured to receive the image data from the analytical instrument via one or more networks.

[0015] Embodiments of this disclosure may also include systems, components, and methods according to the foregoing aspects. The terminology and expressions used herein are descriptive and not restrictive only, and their use is not intended to exclude any equivalents of the shown and described features or portions thereof, but rather to facilitate the understanding that various modifications may be possible within the scope of the claimed subject matter. Therefore, it should be understood that although the claimed subject matter has been clearly disclosed through specific embodiments and optional features, modifications and variations of the concepts disclosed herein can be made by those skilled in the art, and such modifications and variations should be considered to fall within the scope of this disclosure as defined by the appended claims.

[0016] One or more exemplary embodiments described herein can be implemented within, combined with, and / or coupled to an imaging device, imaging system, scientific measurement device, and / or scientific measurement system.

[0017] One or more exemplary embodiments disclosed herein can be applied to generate synthetic sample data for training analytical models, train analytical models based on synthetic sample data, and / or use analytical models for sample preparation, sample imaging and / or control of imaging and / or scientific measurement devices and / or systems.

[0018] One or more exemplary embodiments described herein can generate synthetic sample data and / or train analytical models without preparing, manufacturing, and / or acquiring dozens, hundreds, or even thousands of samples as in existing frameworks. This can save power, bandwidth, device / system usage time, user physical time, cost, etc.

[0019] Furthermore, using one or more exemplary embodiments described herein, sample diversity can be provided that may not be achievable in existing frameworks that rely entirely on real-world samples. Similarly, using one or more exemplary embodiments described herein, imaging guidance can be provided for settings that cannot be generated otherwise using existing frameworks (such as the limitations of preparation bandwidth in existing frameworks and / or the reuse of less robust models due to the same limitations), based on synthetic image training and / or generation. Attached Figure Description

[0020] The various embodiments will be readily understood through the following detailed description taken in conjunction with the accompanying drawings. For ease of description, the same reference numerals indicate the same structural elements. The embodiments are shown in the figures by way of example rather than limitation. Not all instances of elements need to be labeled, in order to appropriately reduce confusion in the figures. The figures are not necessarily drawn to scale, but rather focus on illustrating the principles described.

[0021] Figure 1A schematic diagram of an example charged particle microscope system according to some embodiments of the present disclosure is shown.

[0022] Figure 2 A schematic diagram of an example analysis system for generating microscope image data and template information according to some embodiments of the present disclosure is shown.

[0023] Figure 3 A flowchart illustrating an example process for generating template information using image data according to some embodiments of the present disclosure is shown.

[0024] Figure 4 A block diagram illustrating an example object hierarchy structure describing template information according to some embodiments of this disclosure is shown.

[0025] Figure 5 A flowchart illustrating an example data flow involved in generating template information is shown according to some embodiments of this disclosure.

[0026] Figure 6 This is a schematic diagram illustrating an example convolution technique for generating template information according to some embodiments of the present disclosure.

[0027] Figure 7 A block diagram of an exemplary non-limiting system that facilitates a process for comparing data from a measuring device according to one or more exemplary embodiments described herein is shown.

[0028] Figure 8 A block diagram of an example imaging and / or scientific measurement system according to one or more exemplary embodiments described herein is shown.

[0029] Figure 9 A block diagram of an exemplary non-limiting dual-beam system including an electron microscope (EM) and a focused ion beam (FIB) device according to one or more exemplary embodiments described herein is shown.

[0030] Figure 10 This document illustrates one or more exemplary embodiments that can be provided by [the following]. Figure 1 The example sheet used in the non-restrictive system.

[0031] Figure 11 This document illustrates one or more exemplary embodiments that can be provided by [the following]. Figure 1 Example template layout of an integrated circuit (IC) device for non-restricted system execution.

[0032] Figure 12 This document illustrates one or more exemplary embodiments that can be provided by [the following]. Figure 1 A flowchart of one or more processes executed by a non-restricted system.

[0033] Figure 13 This document illustrates one or more exemplary embodiments that can be provided by [the following]. Figure 1 One or more processes executed by an unrestricted system. Figure 12 The continuation of the flowchart.

[0034] Figure 14 A block diagram is shown of an exemplary operating environment in which embodiments of the topics described herein can be incorporated.

[0035] Figure 15 An example schematic block diagram of a computing environment in which the topics described herein can be interacted with and / or at least partially implemented is shown. Detailed Implementation

[0036] Semiconductor manufacturing utilizes charged particle microscopy (such as transmission electron microscopy) as part of quality control. In an illustrative example, samples of semiconductor devices (e.g., integrated circuits) are extracted from wafers or wafer sections (e.g., diced wafers) and examined under a transmission electron microscope. Microscopic images of so-called “device lines” (referring to a linear arrangement of individual devices such as transistors, capacitors, etc.) can be used to assess manufacturing and / or design errors.

[0037] Therefore, one aspect of quality control for semiconductor devices includes determining whether the manufactured device conforms to the device design, in which individual devices exist in a desired number and sequence at a given location on the wafer and / or wafer portion.

[0038] Typically, semiconductor quality control is at least partly (if not entirely) manual. Sample preparation (including locating and extracting slices, generating microscopic image data, and analyzing the image data to determine if the manufactured device conforms to the device design, among other operations) is performed by skilled technicians. Efforts to automate all aspects of the quality control process, including image processing automation, face significant challenges. For example, defect detection relies on correctly identifying regions of interest (ROIs) in the sample, generating images of these ROIs, and processing the images via feature detection and identification, pattern matching, etc. Each of these operations is challenging for machine vision systems, which typically perform poorly in distinguishing IC devices from the background, are prone to errors when samples are reversed in the microscope, and / or are relatively inflexible in analyzing device line samples that deviate from a predefined sequence. Therefore, improved data processing techniques, methods, and / or algorithms are needed for quality control in semiconductor manufacturing.

[0039] Furthermore, acquiring sufficient images through microscopic examination (such as for training analytical models that drive workflows) is a time-consuming process. In existing frameworks, user entities need to invest significant time in data collection and model training.

[0040] Especially for thin films such as wafers and IC devices, collecting real-world images is very time-consuming, and due to differences in chip design, these images are usually not applicable to every area of ​​the same wafer.

[0041] To overcome one or more of these shortcomings, this paper describes one or more implementations capable of generating synthetic samples and / or sample data for training analytical models, and / or using such trained models to control imaging systems, sample preparation systems, production and / or manufacturing systems, etc. In one or more implementations, this can eliminate and / or reduce the microscopy time required to capture images of real-world samples. Instead, user entities can access a greater quantity, quality, and variety of synthetically generated images. This not only reduces preparation time, model training time, etc., but also enables the generation of more sophisticated automated workflows and computer vision models.

[0042] Although exemplary embodiments have been shown and described, it should be understood that various changes can be made thereto without departing from the spirit and scope of this disclosure. In the following paragraphs, embodiments of charged particle microscopy systems, components, and methods for device detection and identification in integrated circuit samples are described. For simplicity, embodiments of this disclosure focus on CMOS device samples imaged in transmission electron microscopy (TEM). Therefore, embodiments are not limited to such samples or instruments, but rather envision analytical instrument systems in which the analysis of microstructure and / or nanostructure features can benefit from robust automation (e.g., operation without human intervention) and / or pseudo-automation (e.g., operation with limited human intervention). In exemplary examples, the techniques of this disclosure can be applied to image data derived from microbial processes (e.g., gene sequencing output, fluorescence microscopy images, etc.), metastructural materials (e.g., quality control of hidden geometries used in manufacturing), and / or to large-scale imaging of artificial or natural structures (e.g., survey data, such as hyperspectral imaging). Similarly, while embodiments of this disclosure focus on TEM, additional and / or alternative systems are contemplated, including but not limited to scanning electron microscopy (SEM), scanning transmission electron microscopy (STEM), STEM within SEM, atomic force microscopy (AFM), scanning capacitance microscopy (SCM), ion microscopy (IM), optical microscopy, confocal microscopy, fluorescence microscopy, hyperspectral imaging, etc., wherein the instruments are used to generate image data representing structural or other features that at least partially conform to a pattern.

[0043] Embodiments of this disclosure may include systems, methods, algorithms, and non-transitory media storing computer-readable instructions for generating template information from image data. In an exemplary example, one method may include: receiving microscope image data; detecting features in the microscope image data; receiving feature template data describing feature groups including the features; detecting the groups in the microscope image data based at least in part on the feature template data; generating template information for the groups; and outputting the template information. As described with reference to the following embodiments, the hierarchical structure of the template data allows the systems of this disclosure to efficiently process microscope image data, detect features in an arrangement corresponding to a design or other characteristic pattern, determine regions of interest in semiconductor samples for imaging, and guide the system to generate image data including the regions of interest. In this way, analytical instrument systems can perform template-driven image generation with improved performance in terms of time and computational resource requirements with reduced human interaction, while also reducing the level of technical complexity required of human operators of the instrument system.

[0044] As used in this article, the phrase “based on” should be understood to mean “at least partially based on”, unless otherwise specified.

[0045] As used herein, the term "compound" can refer to a single material, multiple materials, a composition, a sample, a solution, a product, etc.

[0046] As used in this article, the term "data" may include metadata.

[0047] As used herein, the terms “entity,” “requesting entity,” and “user entity” can refer to machines, devices, components, hardware, software, intelligent devices, parties, organizations, individuals, and / or humans.

[0048] One or more exemplary embodiments will now be described with reference to the accompanying drawings, wherein the same reference numerals are always used to refer to the same elements in the drawings. In the following description, numerous specific details are set forth for purposes of explanation in order to provide a more thorough understanding of the one or more exemplary embodiments. However, it will be apparent, however, that the one or more exemplary embodiments may be practiced without these specific details.

[0049] Furthermore, it should be understood that the embodiments depicted in one or more of the accompanying drawings are for illustrative purposes only, and therefore the architecture of the embodiments is not limited to the systems, apparatuses and / or components depicted therein, nor to any particular order, connection and / or coupling of the systems, apparatuses and / or components depicted therein.

[0050] First refer to Figure 1The illustration shows a schematic diagram of an example charged particle microscope system 100 according to some embodiments of the present disclosure. The example system 100 may include: one or more instrument systems 105, one or more instrument PCs (IPCs) 110, one or more client computing devices (client PCs) 115, and / or one or more servers.

[0051] 120. The various components of the example system 100 may communicate via one or more networks 125 and / or via direct connections (e.g., USB connections, Bluetooth, Wi-Fi, Ethernet, etc.). In some embodiments, one or more components of the example system 100 are omitted. For example, embodiments of this disclosure may omit the client PC 115 and / or server 120.

[0052] Instrument system 105 may include components for analyzing material samples according to one or more measurement modalities, facilitated by the configuration of instrument 105 and software, tools, etc., available on IPC 110, client PC 115, and / or server 120. For example, client PC 115 and / or server 120 may host software applications configured to perform one or more processing operations using data generated by instrument 105. In this way, the software applications may be hosted locally on a single device and / or a distributed computing system, and may guide the operation of instrument 105 at least in part based on template information generated from image data generated by instrument 105.

[0053] Client computing device 115 may be or include general-purpose computing devices (e.g., laptops, tablets, smartphones, desktops, etc.) and / or dedicated computing devices. Server 120 may be or include one or more locally and / or remotely network-connected machines, including processing, storage, and / or communication components. In an exemplary example, server 120 may be cooperatively located in a physical location (e.g., a building, campus, or other location) with instrument 105 and may be compatible with...

[0054] One or more components of instrument 105 communicate. Client PC 115 may be located at a first physical location different from the second physical location of instrument 105. To this end, components of example system 100 may be coordinated to store large datasets generated by instrument system 105 and to reduce data transmission latency during periods of relatively high network latency, or for example when the first physical location and the second physical location are physically far apart (e.g., on different continents or different coasts of the same continent).

[0055] IPC 110 may include general-purpose or special-purpose computing devices. For example, embodiments may include a PC configured for user interaction (e.g., having a display, user interaction peripherals, and a user interface), a PC dedicated to coordinating the operation of instrument 105 without direct user interaction (also referred to as a "dedicated" PC) without user interface components, and / or a computing board incorporated into or otherwise operatively coupled to instrument 105. The computing board may include components similar to those of a dedicated PC, wherein power circuitry and / or input / output components may be shared with instrument 105.

[0056] Figure 2 This is a schematic diagram illustrating an example analysis system 200 for generating microscope image data 220 and template information 240 according to some embodiments of the present disclosure. In the illustrated embodiment, the example analysis system 200 includes a TEM sample 205, as an example of a sample form used in the instrument 105 of the example system 100. In this way, the microscope image data 220 includes a microscope image formed by passing a beam of charged particles 210 through a sample 215 that is at least partially permeable to electrons.

[0057] Figure 2 Example analysis system 200 shows a TEM sample such that the charged particle beam 210 is an electron beam. In some embodiments, the charged particle beam 210 is an ion beam or includes an ion beam (e.g., extracted from an ion source such as a liquid metal ion source, a plasma-based ion source, etc.). Furthermore, the charged particle beam 210 is shown passing through a sample 215 such that image data 220 corresponds to an image constructed using detector data generated from primary charged particles (e.g., primary electrons in the case of a TEM system) of the charged particle beam 210. In some embodiments, the charged particle beam 210 is focused onto the sample 215 such that image data 220 may include backscattered electron, backscattered ion, secondary electron, and / or secondary ion detector data. In this case, the sample 215 may be almost entirely or completely impermeable to charged particles, such as a bulk material sample or a sample having a thickness that causes electron absorption and / or backscattering to exceed electron transmission.

[0058] Image data 220 shows a region of sample 215, which includes features 225 and 230 arranged in an arrangement. This arrangement can be linear and / or non-linear. In an example of a semiconductor device, features 225 and 230 may be arranged in a “device line” that includes multiple instances of features 225 and 230 formed during the CMOS manufacturing process. Features 225 and 230 may be or include at least a portion of various devices constituting part of an integrated circuit, such as transistors, capacitors, vias, etc. In one or more embodiments, the same device may be detected as more than one feature type, at least in part, based on variations in device characteristics. For example, size may be used to classify a device into one feature type within a set of feature types (e.g., small 227, medium 228, and large 229). Similarly, other characteristics such as material composition, sub-features, etc. (e.g., in one or more preprocessing operations) may be used to define multiple feature types.

[0059] Image data 220 may include metadata, including but not limited to sample information, system parameters, and / or spatial / coordinate information. Spatial / coordinate metadata maps pixels in image data 220 to a set of coordinates on the location of a position on sample 205. In one or more embodiments, the coordinates may reference a stage control scheme, such as a multi-axis sample holder (e.g., three spatial orientations and tilt). In this way, features 225 and 230 can be referenced by their positions on sample 205 and in image data 220. For example, a feature can be referenced by the location of its centroid in image data 220 and / or on sample 205. The extent, centroid, and other geometric properties of various features may be determined at least in part based on a segmentation process applied to image data 220. Additionally or alternatively, the size, extent, and / or centroid of various features may be determined at least in part based on the detection of one or more edges, vertices, or other aspects of the feature, with a predefined centroid referenced from one or more edges, vertices, or other aspects of the feature. For example, the centroid may be defined based on the design specifications of the given feature by referencing the vertex between the top and side edges of the given feature. (See reference...) Figure 3 In a more detailed description, the location of the centroid can be referenced to the bounding box used to define the region of interest (ROI) for further microscopic examination and / or microanalysis (e.g., by imaging or probing).

[0060] Therefore, the technology disclosed herein may include a process applied to image data 220, according to which the observed arrangement of features 225 and / or 230 can be compared with feature template data (e.g., Figure 4 and Figure 5 The characteristic template data 405 is compared with the microscopic examination and microanalysis method of the guide sample 205. Figure 2Features 225 and 230 shown are schematic in nature and do not represent the shape or scale of an actual semiconductor device. Instead, image data 220 is provided as an illustrative example of features arranged in sample 215, from which template information 240 can be generated. Furthermore, although image data 220 includes two types of features, the techniques of this disclosure can be applied to image data describing samples that include more or fewer types of features.

[0061] Template information 240 may include data on features 225 and 230 (including feature sequences), such as the number of instances of the first feature type 225 and the number of instances of the second feature type 230 in group 235. Therefore, template information 240 may include a sequence of features (e.g., in order of their respective positions in the arrangement), where group 235 corresponds to this sequence of features. Figure 2 In the example, the template corresponds to a sequence of features in the device line, for which group 235 includes a first instance 225-1 of the first feature, an instance of the second feature 230, and a second instance 225-2 of the first feature. Image data 220 may describe multiple instances of group 235, and not all features 225 and / or 230 may belong to a group instance (e.g., a third instance 225-3 of the first feature). See reference... Figure 3 In more detail, template information 240 can be generated by: using an algorithm to process image data 220 to detect features in image data 220; identifying the arrangement of features in groups associated with feature template data; and generating information describing the location and sequence of groups to be used for the study sample.

[0062] Figure 3 This is a flowchart of an example process 300 for generating template information using image data, according to some embodiments of this disclosure. One or more operations constituting example process 300 may be performed by a computer system and / or with analytical instruments (e.g., Figure 1 The components of the example instrument 105 are operatively coupled to other machines and / or additional systems or subsystems (including, but not limited to, characterization systems, network infrastructure, databases, controllers, relays, power systems, and / or user interface devices) to perform and / or initiate operations. Therefore, operations can be stored as machine-executable instructions in one or more machine-readable media, which, when executed by a computer system, cause the computer system to perform at least a portion of the constituent operations of process 300. The constituent operations of process 300 may occur before, between, and / or after operations omitted in this specification (such as sample and / or instrument preparation, operations occurring before operation 305, etc.), which form the basis for processing samples to generate, for example, […]. Figure 2At least a portion of the data analysis method shown. Therefore, in some implementations, the operations of example process 300 may be omitted, repeated, reordered, and / or replaced.

[0063] At operation 305, the example procedure includes receiving image data (e.g., Figure 2 Image data 220). Receiving image data may include various sub-operations associated with data storage and retrieval. For example, image data may be stored in a local storage system and / or a distributed storage system, such that a computing device (e.g., Figure 1 The IPC 110, client PC 115, server 120, etc., can request, retrieve, or otherwise access image data of a given sample. In some implementations, receiving image data includes generating image data, such as reference image data. Figure 2 To be described in more detail. For this purpose, example process 300 can be implemented simultaneously by one or more computing systems and imaging of a sample in a charged particle microscope, for example, as part of a semiconductor quality control scheme. In an exemplary example, the microscope image data (e.g., Figure 2 Image data 220 can be generated and obtained from charged particle microscopes (e.g., Figure 1 The instrument 105) transmits the data to a computing device or other machine that is implementing the operation of the example process 300.

[0064] At operation 310, the example process includes detecting one or more features in the image data. Feature detection may include, at least in part, based on features that allow detection and / or identification in the image data (e.g., Figure 2 Features 225 and 230) include one or more image processing and / or segmentation techniques. Detecting one or more features may include: inputting at least a portion of microscope image data into a model configured to detect the feature; and generating coordinate information describing the location of the feature in the microscope image data as the output of the model. (See reference...) Figure 4 and Figure 5 In more detail, the model may be or include at least a portion of the input microscope image data and output information describing the order, location, and / or size of given features, as well as information that can be used to detect groupings in the microscope image data (e.g., Figure 2 Various model structures for other information in group 235. Model structures may include rule-based models, feature detection algorithms (e.g., edge detection based on Sobel filters, texture analysis based on Gabor filters, etc.), neural network-based models (e.g., convolutional neural networks), pixel-based classification methods, patch-based image classification methods, etc.

[0065] In some implementations, multiple models are used to detect multiple features in the image data. The models can be configured to detect corresponding feature types, such that for a given number of features to be detected in the microscope image data, the same number of models are prepared. For example, two convolutional neural network models can be trained as part of the preparatory operation of example process 300, such that the first model detects a first feature type and the second model detects a second feature type. To this end, detecting one or more features in the image data may include: inputting at least a second portion of the microscope image data into a second model configured to detect the second feature; and generating second coordinate information describing the second feature's second location in the microscope image data as the output of the second model. In one or more implementations, the entire microscope image dataset is processed and input into multiple models. However, in one or more implementations, operation 310 may include sub-operations such as segmentation and preprocessing (e.g., feature agnostic) to divide the features into smaller datasets, thereby reducing the amount of data processed by the models. The smaller datasets may be labeled using a grid reference or other index as a method of tracking the order of features in a sequence, such as a reference... Figure 2 as well as Figure 5 and Figure 6 A more detailed description.

[0066] At operation 315, the example procedure includes receiving feature template data. (See reference...) Figure 2 as well as Figures 4 to 6 A more detailed description of the feature template data (e.g., Figure 4 Feature template data 405) can describe multiple features (e.g., Figure 2 The arrangement of features 225 and 230. For example, feature template data can describe the spatial arrangement of multiple features using relative coordinates that can be compared with features detected in microscope image data. In a simpler example, feature template data can describe a sequence of multiple features, where features are assigned sequential positions (e.g., ordered using integers). In this way, feature template data can describe a sample (e.g., Figure 2 The intended arrangement of features in sample 215 is used as part of microscopic examination, microanalysis, and / or quality control review of samples (such as integrated circuit samples). Feature template data may include metadata such as feature type, feature size, relative position of centroid, or other information that can be used to map the arrangement of features in microscopic image data to the feature template. In some embodiments, feature template data includes feature multiplicity information and feature order information. Feature multiplicity describes the number of instances of a given feature, while feature order information describes the relative ordering of features in a sequence. In some embodiments, the template may include multiple groupings (e.g., Figure 2 Group 235), as shown in the reference Figure 4 A more detailed description.

[0067] At operation 320, the example procedure includes detecting one or more packets. Packets (e.g., Figure 2 Grouping (235) may include multiple instances of features in the microscope image data. For example, in one arrangement, grouping may include one or more instances of a first feature, one or more instances of a second feature, and one or more instances of a third feature. Detection grouping may include one or more methods using the data generated at operation 310. For example, sorted data generated by feature detection may be convolved with feature template data, as referenced... Figure 6 A more detailed description.

[0068] Detecting one or more groups may include detecting instances of groups in microscope image data based at least in part on the position of features relative to at least a subset of a plurality of features in a sequence. In this way, detecting instances of groups in microscope image data may include determining a first order of a first feature in the sequence; and determining a first order of the first feature in the sequence and a second order of the second feature matching feature template data. For example, detecting groups may include finding a matching sequence of features in an arrangement (e.g., first feature, followed by second feature, followed by first feature (e.g., ...)). Figure 2 and Figure 6 (as shown) can be identified as a group.

[0069] Group detection can be based at least in part on feature multiplicity and / or feature order, as described in reference operation 315. For some analytical instrument systems (e.g., TEM systems, STEM systems, etc.), the sample (e.g., Figure 2 Sample 215) can be introduced into the sample holder in more than one orientation. For example, in a TEM holder, a sheet can define two broad faces, either of which can face the incident electron beam (e.g., Figure 2 The orientation of the charged particle beam 210. In this way, the feature template data can describe information that can be directly mapped to observed features detected in the microscope image data or mapped to the order of an inverted arrangement (e.g., mirror inversion) caused by the inversion of the sample in the analytical instrument system. Thus, operation 320 can include detecting instances of grouping based on the inverted feature order. In one example, in a linear arrangement, the inverted feature order of a template having two first features followed by a second feature would be a sequence of a second feature followed by two first features.

[0070] At operation 325, the example procedure includes generating template information. The template information may include metadata derived from the microscope image data, at least in part, based on the grouping detected at operation 320. For example, the template information derived from a given group may include the coordinates of the group, which may, without limitation, include the group's location in the microscope image data and / or within the sample. The location of the group can be described using the group's centroid or other substantially centered position, the group's extent (e.g., a set of quadrangular coordinates, a bounding box, etc.), vertex or other peripheral coordinates and / or the origin of the bounding box surrounding the group, contour data, etc. Advantageously, defining the group's location using the centroid or other substantially centered position allows for the generation of instructions for the analysis instrument to produce new image data for which the region of interest is centered, substantially centered, or includes the group. In this way, the group can be detected in the microscope image data at a relatively low magnification and analyzed in the new microscope image data at a relatively high magnification using an automatic or pseudo-automatic method.

[0071] At operation 330, the example process includes outputting template information. Operation 330 may include sending the template information to a charged particle microscope configured to generate image data based at least in part on the template information, as described with reference to operation 325. In some embodiments, operation 330 includes storing the template information, which may include communication between computing devices (e.g., via...). Figure 1 Network 125) transmits template information.

[0072] Operation 330 may also include generating visualization data based at least in part on the template information. The visualization data may include data configured to modify a display or other device to render the template information as a computing device (e.g., ...). Figure 1 The instructions are part of a user environment (e.g., a browser or application environment on a display) on the IPC 110 and / or client PC 115. In an exemplary example, visualization data may be generated to modify the display to overlay bounding boxes onto regions of microscopic image data, where the bounding boxes represent regions of interest substantially centered on one or more groups. In some embodiments, operation 330 includes outputting feature and / or grouping information, such that the visualization data may include feature ordering, feature identifiers, feature centroids, group centroids, number of group instances, and / or template order information, as well as other types of information. Therefore, operation 330 may include outputting information from multiple hierarchical levels of features, groups, and templates, which allows for systematic and efficient querying of samples through automated and / or pseudo-automated techniques.

[0073] Figure 4This is a block diagram of an example object hierarchy structure 400 describing template information according to some embodiments of this disclosure. The example hierarchy structure 400 includes a top-level object associated with feature template data 405, which includes data from multiple clusters 410, which in turn includes one or more features 415. The example hierarchy structure 400 includes image data (e.g., Figure 2 The image data 220 describes three object levels, but template information may include more or fewer object levels. For example, grouping (e.g., Figure 2 Group 235) can represent a template or cluster 410.

[0074] Feature 415 may have one or more types, as referenced Figure 2 A more detailed description follows. Therefore, each feature type 415 can be associated with a model configured to detect feature types 415 in image data. The model can generate metadata for detecting clusters 410 and / or templates 405 in the image data, as referenced... Figure 3 as well as Figure 5 and Figure 6 In a more detailed description, cluster 410 may represent a combination of features and / or composite features described in device design, intended arrangement, etc., making the detection of cluster 410 computationally simpler than the detection of constituent features 415. In an exemplary example, in addition to detecting or instead of detecting the individual features constituting the cluster, the device line may include a group of continuous features, such that the outer boundary of the cluster is suitable for detecting the cluster. Thus, one or more models may be configured to detect cluster 410 in image data.

[0075] Figure 5 This is a flowchart of an example data processing workflow 500 involved in generating template information according to some embodiments of this disclosure. The data processing workflow 500 includes applications applied to analytical instruments 501 (e.g., Figure 1 The example workflow 500 is shown as one or more processing operations of data 505 generated by instrument 105 of the example system 100. The operations of the example workflow 500 are shown as a series of operations unrelated to a specific instrument, computing device, or machine, as an example of how multiple data types and / or data structures are generated at various points in the example workflow 500. Furthermore, the example workflow 500 includes at least, for example, distributing operations across multiple computing devices (e.g., Figure 1 A subset of processing operations implemented in parallel on server 120 and / or by processing data 505 on a multi-core processor.

[0076] Data 505 may be or include image data (e.g., Figure 2 Microscopic image data 220), but may also include descriptions of the sample (e.g., Figure 2Other data for sample 215. For example, the data may be optical image data generated using an optical microscope and / or camera, spectral mapping image data generated using spatially resolved spectroscopy, force microscopy data mapping the electronic properties of the sample surface in two or more dimensions, etc.

[0077] Data 505 may be distributed, in whole or in part, to one or more models 510, which are configured to detect features in the data 505 (e.g., Figure 2 Features 225 and 230 and Figure 4 Feature 415) and / or grouping of features (e.g., Figure 4 Cluster 410). See reference Figure 3 In more detail, data 505 can be segmented through one or more preprocessing operations as a method to improve parallelization, and model 510 can be or includes various types of image processing models and / or algorithms (e.g., CNN-type machine learning models, image patch-based processing algorithms, etc.). In this way, the output from model 510 can be or includes data 515 describing feature information (such as ordering, position in image data, and / or position in samples). Data 515 output from model 510 can be combined to generate aggregate data 520 and provided to template detection subprocess 530. See reference... Figure 6 In more detail, one or more template detection subprocesses 530 may be configured to map feature template data 405 to output data 515 and / or aggregated data 520. In one or more embodiments, the template detection subprocess 530 may be implemented as an algorithm configured to generate template information 535, as described in reference [reference needed]. Figure 3 A more detailed description.

[0078] Template information 535 may include template location, ROI data, feature sequence data (such as feature multiplicity and order information observed in the sample), template instance information, or information that can be obtained by an analysis system (e.g., Figure 1 The template information 535 can then be provided as input to an output subprocess 540, which may be or include one or more algorithms for generating visualization data, sample positioning instructions, beam orientation instructions, detector operation instructions, instrument operation parameters, etc. In an exemplary example, the output subprocess 540 may generate instruction data 545 to guide the instrument 501 to generate additional data, based at least in part on the template information 535 generated using data 505.

[0079] Figure 6This is a schematic diagram illustrating an example convolutional technique 600 for generating template information according to some embodiments of the present disclosure. Example technique 600 includes mapping feature template data 405 to output data 515 and / or aggregated data 520 describing feature ordering and identity information of device line samples. In example technique 600, feature template data 405 describes the following groupings (e.g., Figure 2 Grouping 235), the grouping includes a first instance of a first feature, followed by a first instance of a second feature, followed by a second instance of the first feature. The convolutional method includes mapping feature template data 405 onto a sequence of features in aggregate data 520 to determine whether a feature matches the template. If a feature does not match the template, the template is then incremented by one level, or if the feature does match the template, the template is then incremented by a template length. For one or more templates in the detected templates (e.g., each template or fewer templates in the templates), a number of instances can be assigned, along with various location / position data of the relative position of the reference template in the image data and / or on the samples. Figure 6 In this data, the centroid position of the XY coordinates in the reference image or on the sample is included.

[0080] In some implementations, additional and / or alternative techniques are used to map the feature template data 405 to the aggregated data 520 as part of the feature information 535 of the generated samples. For example, techniques for measuring the error or distance (e.g., mean squared error) between the template and the measured features can be used to generate the feature information 535. Similarly, template matching methods may include outlier removal (e.g., random sample consensus techniques) to improve matching in noisy data. Advantageously, template matching methods can be extended to higher dimensions. Implementations of this disclosure include two-dimensional convolution (e.g., along a second axis in the array of features).

[0081] Now for reference Figure 7 The illustration shows a non-limiting system 700, which may include an imaging device endpoint detection system 702, a scientific imaging system 732, and a library data repository (DS) 740. For brevity, repeated descriptions of similar elements and / or processes employed in corresponding embodiments are omitted. Regarding... Figure 7 The description of the implementation scheme is applicable to Figure 8 The implementation plan. Similarly, regarding... Figure 8 The description of the implementation scheme is applicable to Figure 7 The implementation plan.

[0082] In one or more embodiments, the scientific imaging system 732 (such as a dual-beam system, a focused ion beam (FIB) system, or an electron microscope (EM) system device) may be decoupled from the non-limiting system 700, but communicatively coupled to the non-limiting system. In one or more other embodiments, the scientific imaging system 732 may include an imaging device endpoint detection system 702.

[0083] In one or more embodiments, one or more additional scientific imaging systems may also be communicatively coupled to and / or included in the non-limiting system 700.

[0084] In one or more embodiments, the library data repository 740 may be separate from the non-restrictive system 700, but communicatively coupled to the non-restrictive system.

[0085] Generally, the imaging device endpoint detection system 702 can facilitate the generation of synthetic image data 740, which is used to train the analysis model 712 and / or generate instructions 750 for controlling the operation of the scientific imaging system 732 or other scientific imaging systems.

[0086] One or more communications between one or more components of the non-limiting system 700 may be provided via wired and / or wireless means, including but not limited to cellular networks, wide area networks (WANs) (e.g., the Internet), and / or local area networks (LANs). Suitable wired or wireless technologies for supporting communications may include (but are not limited to) Wi-Fi, Global System for Mobile Communications (GSM), Universal Mobile Telecommunications System (UMTS), Global Microwave Access Interoperability (WiMAX), Enhanced General Packet Radio Service (Enhanced GPRS), 3GPP Long Term Evolution (LTE), 3GPP2 Ultra Mobile Broadband (UMB), High Speed ​​Packet Access (HSPA), Zigbee and other 802.XX wireless technologies and / or traditional telecommunications technologies. Session Initiation Protocol (SIP) RF4CE protocol, WirelessHART protocol, 6LoWPAN (IPv6 on low power wireless local area network), Z-Wave, advanced and / or adaptive networking technology (ANT), ultra-wideband (UWB) standard protocol and / or other proprietary and / or non-proprietary communication protocols.

[0087] The imaging device endpoint detection system 702 can be integrated with cloud computing environments (such as...) Figure 14 The cloud computing environment 1400 is associated with (such as being accessible via the cloud computing environment).

[0088] The imaging device endpoint detection system 702 may include multiple components. These components may include a memory 704, a processor 706, a bus 705, an information processing component 710, an analysis model 712, a training component 714, a data generation component 716, an image generation component 718, and / or an output component 720. Using these components, the imaging device endpoint detection system 702 can facilitate the generation of synthetic image data 740, which is used to train the analysis model 712 and / or generate instructions 750 for controlling the operation of the scientific imaging system 732 or other scientific imaging systems.

[0089] The processor 706, memory 704, and bus 705 of the imaging device endpoint detection system 702 will be discussed next. For example, in one or more exemplary embodiments, the imaging device endpoint detection system 702 may include a processor 706 (e.g., a computer processing unit, microprocessor, classical processor, quantum processor, and / or similar processor). In one or more exemplary embodiments, components associated with the imaging device endpoint detection system 702 (as described herein with or without reference to one or more figures of one or more exemplary embodiments) may include one or more computer and / or machine-readable, writable, and / or executable components and / or instructions that can be executed by the processor 706 to perform one or more processes defined by such components and / or instructions. In one or more exemplary embodiments, the processor 706 may include an information processing component 710, an analysis model 712, a training component 714, a data generation component 716, an image generation component 718, and / or an output component 720.

[0090] In one or more exemplary embodiments, the imaging device endpoint detection system 702 may include a computer-readable storage 704 operatively connected to a processor 706. The storage 704 may store computer-executable instructions that, when executed by the processor 706, cause the processor 706 and / or one or more other components of the imaging device endpoint detection system 702 (e.g., information processing component 710, analysis model 712, training component 714, data generation component 716, image generation component 718, and / or output component 720) to perform one or more actions. In one or more exemplary embodiments, the storage 704 may store computer-executable components (e.g., information processing component 710, analysis model 712, training component 714, data generation component 716, image generation component 718, and / or output component 720).

[0091] As described herein, the imaging apparatus endpoint detection system 702 and / or its components may be coupled to each other via bus 705 in a communicative, electrical, operational, optical, and / or other manner. Bus 705 may include one or more of a memory bus, memory controller, peripheral bus, external bus, local bus, quantum bus, and / or another type of bus that may employ one or more of the following bus architectures. One or more of these examples of bus 705 may be employed.

[0092] In one or more exemplary embodiments, the imaging device endpoint detection system 702 may be coupled (e.g., communicatively, electrically, operablely, optically, and / or similarly) to one or more external systems (e.g., an electrical output production system not shown, one or more output targets and / or output target controllers), sources, and / or devices (e.g., classical and / or quantum computing devices, communication devices, and / or similar devices), such coupling being performed via a network. In one or more exemplary embodiments, one or more components of the imaging device endpoint detection system 702 and / or the non-limiting system 700 may reside in the cloud and / or may reside locally in a local computing environment (e.g., at a designated location).

[0093] In addition to the processor 706 and / or memory 704 described above, the imaging device endpoint detection system 702 may also include one or more computer and / or machine-readable, writable and / or executable components and / or instructions that, when executed by the processor 706, enable the execution of one or more operations defined by such components and / or instructions.

[0094] The other components of the imaging device endpoint detection system 702 (e.g., information processing component 710, analysis model 712, training component 714, data generation component 716, image generation component 718 and / or output component 720) will be discussed next.

[0095] The process performed by the imaging device endpoint detection system 702 can generally be divided into multiple sets of processes, including but not limited to a first set of processes for generating synthetic images based on original sample information and / or images, a second set of processes for training an analysis model using synthetic images, and a third set of processes for operating the scientific imaging system using the trained analysis model and / or using one or more synthetic images generated by the system described herein.

[0096] First, it should be noted that in one or more exemplary embodiments, the information processing component 710, the analysis model 712, the training component 714, the data generation component 716, the image generation component 718, and / or the output component 720 can be implemented independently without requiring one or more of the other components of the information processing component 710, the analysis model 712, the training component 714, the data generation component 716, the image generation component 718, and / or the output component 720. Additionally and / or alternatively, the information processing component 710, analysis model 712, training component 714, data generation component 716, image generation component 718, and / or output component 720 may be included in the advanced analysis component 703. One or more of the following functions of the information processing component 710, analysis model 712, training component 714, data generation component 716, image generation component 718, and / or output component 720 may be performed by the advanced analysis component 703, and / or the information processing component 710, analysis model 712, training component 714, data generation component 716, image generation component 718, and / or output component 720 may be omitted, and one or more of the following functions of the information processing component 710, analysis model 712, training component 714, data generation component 716, image generation component 718, and / or output component 720 may be performed by the advanced analysis component 703.

[0097] As described above, the first group of one or more processes may include generating a synthetic image based on the original sample information and / or the image. It should be noted that this first group of one or more processes at least partially encompasses the above-mentioned references. Figures 1 to 6 The topic of discussion.

[0098] First, the information processing component 710 is invoked, which typically acquires (e.g., obtains, downloads, uploads, requests, transmits, etc.) the sample information 730 output by the scientific imaging system 732. The information processing component 710 may, for example, temporarily and / or more permanently store the sample information 730 in any suitable format at a library data repository 740. The sample information 730 may include data and / or metadata in any suitable format.

[0099] The information processing component 710 can process the sample information 730 into processed model input information 738, which describes a set of original features 736 of the sample 734. This processing may include any suitable procedures such as transposition, transformation, conversion, addition, deletion, noise cancellation, noise removal, etc.

[0100] In one exemplary embodiment, the processed model input information 738 may describe a sequence 832 of IC devices 830 including a specified relationship between features of IC devices 830 relative to one or more groups (e.g., cluster 410) of integrated circuit (IC) devices 830 arranged with each other.

[0101] refer to Figure 8 At the same time, still refer to Figure 7 Sample 734 may include any suitable scientific sample, such as integrated circuit (IC) device 830, sequence 832 of IC device 830, sheet 834 (whether biological sheet, sheet of IC device 830, etc.), template layout 836 for workflow images for operating scientific imaging system 732, complementary metal oxide semiconductor (CMOS) device 838, dynamic random access memory (DRAM) device 837 and / or NAND device 839.

[0102] For example, refer to Figure 10 The diagram shows a pair of sheets 1002 (e.g., sheets 1002-A and 1002-B). Each sheet 1002 has a cut surface 1006 disposed at a plane 1008 of the sheet.

[0103] For example, refer to Figure 11 The figure illustrates an example template layout 836. Template layout 836 includes a CMOS device 838 and represents a set of workflow processes for identifying and imaging one or more regions of interest 820. In one or more other embodiments, template layout 836 may include a sequence 832 of IC devices 830. As shown in the left figure, a template 1102 is generated based on a nearby semiconductor device, such as the CMOS device 838, and superimposed on this sequence. Each colored box 1104 of template layout 836 may represent a step in the workflow set of the process.

[0104] Therefore, return Figure 7 and Figure 8 Sample information 730 may include various types of information.

[0105] For example, sample information 730 may include image data 802 describing an integrated circuit (IC), wherein a set of raw features 736 includes one or more IC devices 830 of the integrated circuit, and wherein composite image data 740 includes one or more physical characteristics 760 of the one or more IC devices 830. Physical characteristics 760 may include, but are not limited to, shape, position, orientation, surface height, size, etc.

[0106] In another example, sample information 730 may include computer-aided drawing (CAD) data 804 describing the set of original features 736 and associated noise data 806 in image format.

[0107] In yet another example, sample information 730 may include Graphical Data System Formatted Data (GDS or GDSII) or Open Layout Systems Exchange Standard Formatted Data (OASIS).

[0108] Still referencing Figure 7 and Figure 8 The data generation component 716 can generate synthetic image data 740 that describes at least a portion of the original features 736 based on the processed model input information 738.

[0109] One or more synthetic image datasets 740 can be generated based on any set of sample information 730 corresponding to a single sample 734.

[0110] In one or more embodiments, the synthetic image data 740 may describe at least one pseudo-feature that differs from the original feature 736 but is based on the original feature. In this way, using one or more exemplary embodiments described herein, sample diversity can be provided that may not be achievable in existing frameworks that use only real-world samples (e.g., sample 734).

[0111] In one or more examples, sample information 730 and synthetic image data 740 may each describe the region of interest 820 described by reference to computer-aided drawing (CAD) data 804, GDS data 808 and / or other image data 802, which describes only a portion of sample 734.

[0112] Image generation component 718 can typically generate a synthetic image 742 of pseudo-sample 744 based on synthetic image data 740. The synthetic image has at least one pseudo-feature 746 that is different from and based on the set of original features 736.

[0113] In one or more embodiments, the composite image 742 may include a composite transmission electron microscope (TEM) image 840 defined by composite image data 740.

[0114] Let's briefly review again Figure 10 In one or more embodiments, the synthesized image 742 may include a virtual three-dimensional (3D) image 842. Components of the output component 720 and / or the scientific imaging system 732 may virtually slice the virtual three-dimensional image 842 at a virtual plane 1008. Furthermore, the output component 720 may identify the region of interest 820 of the slice based on the difference between the region of interest 820 of the resulting slice of the 3D image 842 and the surrounding slice surface 1006.

[0115] like Figure 10As shown, compared to existing frameworks, using CAD data 804 and / or other synthetic image data 740 can produce synthetic cut surface 1006 and / or slice images with a clearer region of interest 820 characterized by less noise data 806. This can be attributed at least in part to virtual slices of the virtual 3D image 842.

[0116] In one or more embodiments, the output component 720 may output the synthesized image 742 to the scientific imaging system 732 and / or to a display, screen, graphical user interface, etc., communicatively coupled to the imaging device endpoint detection system 702.

[0117] In one or more embodiments, the output component 720 may output the synthetic image 742 and associated synthetic image data 740 to the training component 714 and / or the analysis model 712.

[0118] Referring now to one or more of the processes described in the second group, which may include training an analytical model using synthetic images.

[0119] For example, dozens, hundreds, or even thousands of synthetic images 742 can be generated for training the analysis model 712 using the training component 714. Compared to existing frameworks that use real-world samples 734, these synthetic images 742 can be generated with reduced power, bandwidth, time, and manual work.

[0120] Analysis model 712 may include artificial intelligence models, machine learning models, language models, imaging models, neural network (NN) models, convolutional neural network (CNN) models, etc.

[0121] In one or more embodiments, the analysis model 712 may include an adversarial component, a generative adversarial network (GAN), a diffusion model, a neural network model, or a convolutional neural network model, which is trained using a training dataset of synthetically generated images 742 containing integrated circuit device 830, cut surface 1006 of sheet 834, or transmission electron microscope workflow images (e.g., included in template layout 836).

[0122] Based on the training of the analysis model 712, and using the data generation component 716, the analysis model 712 can perform virtual slicing of the virtual 3D image 842 at the virtual plane 1008. Furthermore, the output component 720 can identify the region of interest 820 of the slice based on the difference between the region of interest 820 of the obtained slice of the 3D image 842 and the surrounding slice surface 1006.

[0123] As described above, the use of CAD data 804 and / or other synthetic image data 740, relative to the image preparation used to train the analysis model 712, can also produce synthetic cut surface 1006 and / or slice images with a clearer region of interest 820 characterized by less noise data 806 when using the analysis model 712. This can be attributed at least in part to the virtual slicing of the virtual 3D image 842.

[0124] Also based on the training of the analysis model 712, during operation, the analysis model 712 can receive / acquire sample images and / or sample data (e.g., sample information 730) from the scientific imaging system 732 (e.g., using the information processing component 710). Based on the training of the analysis model 712, the analysis model can identify the region of interest 820 of the sample 734 for operation by the scientific imaging system 732.

[0125] In one or more embodiments, when generating synthetic image data 740 and / or when analyzing sample information 730 / processed model input information 738, the analysis model 712 may refer to the degree of originality 748. The degree of originality 748 may describe the variability relative to the sample information 730 or relative to the dataset used to train the analysis model 712.

[0126] The third group of processes described above will be discussed next. This third group may include the use of trained analytical models and / or the use of the systems described herein (e.g., Figure 7 The non-restricted system 100 generates one or more synthetic images to operate the scientific imaging system.

[0127] That is, based on further training of the analysis model 712, during operation, the analysis model 712 can generate one or more control commands 790 to cause one or more logic circuits 876 of the scientific imaging system 732 (e.g., the logic circuits of the control circuit 814) to perform one or more operations.

[0128] For example, control instructions 790 may include data and / or metadata in any suitable format, including information guiding operation. That is, with this information, control instructions 790 may be configured to generally adjust the scientific imaging system 732 (such as...) in response to processing via control circuitry 814. Figure 9 The operation of charged particle sources or sample holders in the scientific imaging system 900.

[0129] In one or more embodiments, control instructions 790 may include endpoint detection instructions configured to regulate the operation of the FIB subsystem and the SEM subsystem to delay sample 734 and expose one or more CMOS devices 838 of sample 734.

[0130] In one or more embodiments, the control instructions 790 may include metering information based at least in part on image data 729 describing one or more CMOS devices 838, dynamic random access memory (DRAM) devices 837, or NAND devices 839.

[0131] In one or more embodiments, control command 790 and / or endpoint detection command may include instructions to generate a sample (e.g., a thin section) via a scientific imaging system (e.g., a FIB / SEM microscope), which may be used by the scientific imaging system or another scientific imaging system including TEM to generate one or more images of the sample.

[0132] In one or more embodiments, the analysis model 712 can be used to assist in generating synthetic image data 740 and generating control commands 790. The same analysis model 712 for both control command generation and synthetic image data generation can be trained using the same and / or different training data (e.g., simulated training data based on synthetic image data 740), and / or different analysis models for either control command generation or synthetic image data generation, or both.

[0133] In one or more embodiments, the synthesized image data 740 and control commands 790 may correspond to the same set of operations on the same sample 734 to be operated at the scientific imaging system 732. In one or more embodiments, the synthesized image data 740 and control commands 790 may correspond to different sets of operations on different samples 734 to be operated at the scientific imaging system 732.

[0134] In one or more embodiments, raw image data 729 may be acquired from the same scientific imaging system 732 that receives and / or acquires control commands 790. In one or more embodiments, raw image data 729 may be acquired from a first scientific imaging system 732, and a second scientific imaging system 732, distinct from the first scientific imaging system 732, may receive and / or acquire control commands 790.

[0135] In one or more embodiments, based on input of computer-aided drawing (CAD) data (e.g., processed model input information 738) from a set of analysis models 712, the set of analysis models 712, which includes one or more distinct analysis models 712 and has been trained to generate endpoint detection instructions (e.g., control instructions 790) based on CAD input to the set of analysis models. These operations may include generating endpoint detection instructions for a scientific imaging system, including one or more focused ion beam (FIB) subsystems or scanning electron microscope (SEM) subsystems, via the set of analysis models 712. These operations may include generating a set of composite images 742 of a sample 734 via the set of analysis models 712, based on the CAD input and endpoint detection instructions, as a function of the imaging depth of the sample 734 (e.g., its z-slice). These operations may include generating additional composite image data 740 via the set of analysis models 712 based on at least one of the composite images 742, the additional composite image data including template information describing a sequence of integrated circuit (IC) devices. These operations may include: generating metrological information, including a region of interest (ROI) specification applicable to the sample to be imaged, through a set of analysis models 712, based on additional synthetic image data 740 and the combined synthetic image 742. This sample may differ from sample 734. These operations may also include: generating control instructions 790, based on the metrological information, through the set of analysis models 712 for a scientific imaging system 732 that includes a transmission electron microscope (TEM) subsystem or another scientific imaging system 732. In one or more cases, this other scientific imaging system 732 may differ from the scientific imaging system 732 and / or may include a transmission electron microscope (TEM) subsystem.

[0136] The following is a brief introduction. Figure 8 The illustration shows a scientific imaging system 732 that can be controlled and / or operated using instructions 750 generated by a trained analysis model 712. Specifically, such instructions can be used to identify a region of interest (ROI) 820, capture an image, identify a portion of a sample image of a sample 734 described by sample information 730, and so on.

[0137] As shown in the figure, the scientific imaging system 732 may include multiple components, including but not limited to: control circuitry 814, logic circuitry 876, charged particle source 810, machine-actuated sample holder 812, focused ion beam apparatus (FIB) 870, scanning electron microscope (SEM) 872 and / or transmission electron microscope (TEM) 874.

[0138] The following is a brief introduction. Figure 9An exemplary dual-beam system 900 is shown, for which output component 720 may provide instructions (e.g., instructions 750 for controlling the operation of dual-beam system 900).

[0139] Next discussion Figure 7 This relates to a description of an exemplary dual-beam system 700 that can be used as part of a non-limiting system 600. It should be understood that in one or more embodiments, dual-beam system 700 may be used instead of dual-beam system 501, and the description of dual-beam system 700 may also be applied to dual-beam system 501.

[0140] Figure 9 Typical beam systems are illustrated, such as a dual-beam system 900 with a SEM column and a focused ion beam (FIB) column. While examples of suitable hardware are provided below, the implementations described herein are not limited to implementations in any particular type of hardware.

[0141] A scanning electron microscope (SEM) 941, along with a power supply and control unit 945, is provided with a dual-beam system 900. An electron beam 943 is emitted from the cathode 952 by applying a voltage between the cathode 952 and the anode 954. The electron beam 943 is focused into a fine point by a converging lens 956 and an objective lens 958. The electron beam 943 performs a two-dimensional scan on the sample by means of a deflection coil 960. The operation of the converging lens 956, the objective lens 958, and the deflection coil 960 is controlled by the power supply and control unit 945.

[0142] An electron beam 943 can be focused onto a substrate 922, which is located on a movable XY stage 925 within a lower cavity 926. When electrons in the electron beam strike the substrate 922, secondary charged particles are emitted. These secondary charged particles are detected by a secondary electron detector 940, as discussed below. A STEM detector 962, located below the TEM sample holder 924 and the stage 925, can collect electrons and / or ions passing through the sample mounted on the TEM sample holder, as discussed above.

[0143] The dual-beam system 900 also includes a focused ion beam (FIB) system 911, which includes a vacuum chamber with an upper neck portion 912 in which an ion source 914 and a focusing column 916 including extraction electrodes and an electrostatic optical system are placed. The axis of the focusing column 916 is tilted 52 degrees relative to the axis of the electron column. The neck portion, such as the ion column 912, may include the ion source 914, extraction electrodes 915, focusing elements 917, deflection elements 920, and / or a focused ion beam 918. The focused ion beam 918 passes from the ion source 914 through the focusing column 916 and toward a substrate 922 between electrostatic deflection tools schematically indicated by 920, the substrate including semiconductor devices, for example, on a movable XY stage 925 located within a lower chamber 926.

[0144] The stage 925 is preferably movable in the horizontal plane (X and Y axes) and the vertical plane (Z axis). The stage 925 can also tilt approximately sixty (60) degrees and rotate about the Z axis. In some embodiments, a separate TEM sample stage (not shown) may be used. Such a TEM sample stage will also preferably be movable in the X, Y, and Z axes. The door 961 is opened for inserting the substrate 922 onto the XY stage 925 and, if used, for maintaining the internal gas supply reservoir. The door is interlocked so that it cannot be opened if the system is under vacuum.

[0145] An ion pump 968 is used to evacuate the neck section 912. Under the control of a vacuum controller 932, a turbomolecular and mechanical suction system 930 is used to evacuate the chamber 926. The vacuum system provides a vacuum within the chamber 926 between approximately 1 × 10⁻⁷ Torr and 5 × 10⁻⁴ Torr. If an etching assist gas, etching delay gas, or deposition precursor gas is used, the chamber background pressure can be increased, typically to approximately 1 × 10⁻⁵ Torr.

[0146] A high-voltage power supply provides an appropriate accelerating voltage to the electrodes in the focusing column 916 to excite and focus the ion beam 918. When it strikes the substrate 922, material is sputtered, i.e., physically ejected from the sample. Alternatively, the ion beam 918 may decompose a precursor gas to deposit material.

[0147] A high-voltage power supply 934 is connected to the liquid metal ion source 914 and appropriate electrodes in the ion beam focusing column 916 to form an ion beam 918 of approximately 1 keV to 60 keV and guide it toward the sample. A deflection controller and amplifier 936, operating according to a pattern generator 938, are coupled to a deflection plate 920, thereby allowing manual or automatic control of the ion beam 918 to trace a corresponding pattern on the upper surface of the substrate 922. As is well known in the art, in some systems, the deflection plate is placed before the final lens. When a blanking controller (not shown) applies a blanking voltage to the blanking electrode, the beam blanking electrode (not shown) within the ion beam focusing column 916 causes the ion beam 918 to strike the blanking aperture (not shown) instead of the substrate 922.

[0148] The liquid metal ion source 914 typically provides a beam of gallium metal ions. This source is typically able to focus a beam of sub-one-tenth of a micrometer wide at the substrate 922 for modifying the substrate 922 by ion milling, enhanced etching, material deposition, or for imaging the substrate 922.

[0149] A charged particle detector 940, such as an Everhart Thornley detector or a multichannel board, for detecting secondary ion or electron emissions, is connected to video circuitry 942, which supplies drive signals to video monitor 944 and receives deflection signals from system controller 919. The position of the charged particle detector 940 within the lower chamber 926 can vary in different embodiments. For example, the charged particle detector 940 may be coaxial with the ion beam and include apertures for allowing the ion beam to pass through. In other embodiments, secondary particles may be collected via a final lens of the SEM and then deflected off-axis for collection.

[0150] The micromanipulator 947 can precisely move an object within a vacuum chamber. The micromanipulator 947 may include a precision electric motor 948 located outside the vacuum chamber to provide X, Y, Z, and θ control of a portion 949 located within the vacuum chamber. The micromanipulator 947 may be equipped with different end effectors for manipulating small objects. In the embodiment described herein, the end effector is a fine probe 950.

[0151] A gas delivery system 946 extends into the lower chamber 926 for introducing and guiding gaseous vapors to the substrate 922. For example, iodine may be delivered to enhance etching, or a metal-organic compound may be delivered to deposit metal.

[0152] System controller 919 controls the operation of various parts of dual-beam system 900. Through system controller 919, a user can input commands into a conventional user interface (not shown) to cause ion beam 918 or electron beam 943 to scan in a desired manner. Alternatively, system controller 919 can control dual-beam system 900 according to programming instructions stored in memory 921. In some embodiments, dual-beam system 900 incorporates image recognition software to automatically identify regions of interest, and the system can then extract samples manually or automatically according to this application. For example, the system can automatically locate similar features on a semiconductor wafer comprising multiple devices and sample these features on different (or identical) devices.

[0153] Back to Figure 7 and Figure 8 And now refer to it again Figure 4Instruction 750 may include indications for identifying regions of interest 820 of sample 734, as described above. For example, analysis model 712 may execute and / or send instruction 750 instructing one or more logic circuits 876 of scientific imaging system 732 to identify a first group of groups (e.g., clusters 410-1, 410-2, 410-3) of IC devices, and subsequently identify a specific group (e.g., cluster 410-1) of the first group of groups based on a first identifier of one aspect and a second identifier of another aspect: the number of IC devices included in each group of IC devices, or shape-based features or other physical features (e.g., features 415-1, 415-2) of at least one IC device in the group of IC devices.

[0154] As another example, instruction 750 may include instructions for generating image data of a sample disposed in a sample holder; inputting a portion of the image data (e.g., sample information 730) into an analysis model 712, which is trained based on a dataset of synthetic image data 740 describing a synthetic image 742 corresponding to the image data of sample 734; and / or generating control instructions 750 by the analysis model 712, which are configured to adjust the operation of the charged particle source 810 or the sample holder 812 in response to processing by control circuitry 814.

[0155] In one or more implementations, such as Figure 9 As shown, the scientific imaging system 732 may include a focused ion beam (FIB) subsystem and a scanning electron microscope (SEM) subsystem. Relatedly, the sample 734 may include one or more complementary metal-oxide-semiconductor (CMOS) devices 838, dynamic random access memory (DRAM) devices 837, and / or NAND devices 839, and control instructions 750 may include endpoint detection instructions configured to adjust the operation of the FIB and SEM subsystems to delay the sample 734 and expose one or more CMOS devices 838.

[0156] In one or more embodiments, the scientific imaging system 732 may include a transmission electron microscope (TEM) system. Relatedly, the sample may include one or more complementary metal-oxide-semiconductor (CMOS) devices 838, dynamic random-access memory (DRAM) devices 837, and / or NAND devices 839, and control instructions 740 may include metrological information (e.g., sample information 730) based at least in part on image data 729 describing one or more CMOS devices 838, DRAM devices 837, and / or NAND devices 839.

[0157] As a summary of the components and / or their functions mentioned above, please refer to the following... Figure 12 and Figure 13 The document illustrates one or more exemplary embodiments (such as those described herein) Figure 7 A flowchart of an exemplary non-limiting method 1200 for facilitating the process of comparing and / or evaluating the output of a measuring device (non-limiting system 700). Although relative to... Figure 7 The non-limiting system 700 describes the non-limiting method 1200, but the non-limiting method 1200 can also be applied to other systems described herein, such as Figure 8 Non-limiting system 800. For the sake of brevity, repeated descriptions of similar elements and / or processes used in the corresponding embodiments are omitted.

[0158] At 1202, the non-limiting method 1200 may include: processing sample information (e.g., sample information 730) describing a set of original features (e.g., original features 736) of a sample (e.g., sample 734) by a system (e.g., information processing component 710) operatively coupled to a processor (e.g., processor 706) to generate processed model input information (e.g., processed model input information 738).

[0159] At 1204, the non-limiting method 1200 may include: generating synthetic image data (e.g., synthetic image data 740) by analyzing a model (e.g., analyzing model 712 and optionally using data generation component 716) and based on processed model input information, which can be used to generate a synthetic image (e.g., synthetic image 742) and describe at least a portion of the original set of features.

[0160] At 1206, the non-limiting method 1200 may include: generating, via a system (e.g., image generation component 718), a synthetic image (e.g., synthetic image 742) based on synthetic image data, of which a pseudo-sample (e.g., pseudo-sample 744) has at least one pseudo-feature (e.g., pseudo-feature 746) that is different from and based on the set of original features.

[0161] At 1208, the non-limiting method 1200 may include a first group of groups (e.g., group 410) of groups of IC devices (e.g., IC device 830) identified by a system (e.g., analysis model 712), and subsequently a particular group of the first group of groups is identified based on a first identifier of one aspect and a second identifier of another aspect: the number of IC devices included in the group of IC devices, or a shape-based feature of at least one IC device in the group of IC devices.

[0162] At 1210, the non-limiting method 1200 may include: virtually slicing the virtual three-dimensional image at a virtual plane (e.g., virtual plane 1008) of the virtual three-dimensional image (e.g., virtual 3D image 842) by means of a system (e.g., analysis model 712 and / or scientific imaging system 732).

[0163] At 1212, the non-limiting method 1200 may include: identifying the region of interest (ROI 820) of the slice based on the difference between the region of interest of the resulting slice from the virtual 3D image and the surrounding slice surface (e.g., slice surface 1006) by a system (e.g., analysis model 712).

[0164] At 1214, the non-limiting method 1200 may include: referencing a degree of originality (e.g., degree of originality 748) when generating synthetic image data by a system (e.g., analysis model 712 and / or data generation component 716), the degree of originality describing variability relative to sample information or relative to the dataset used to train the analysis model.

[0165] At 1216, the non-limiting method 1200 may include: generating one or more instructions (e.g., instruction 750) via the system, the one or more instructions being configured to cause one or more logic circuits (e.g., logic circuit 876) of the scientific imaging apparatus to perform one or more operations on a sample thereon.

[0166] At 1218, the non-restrictive method 1200 may include: training an analytical model by employing multiple synthetic image datasets through the system. Additional Invention Content

[0167] For the sake of simplicity, the computer-implemented and non-computer-implemented methods provided herein are depicted and / or described as a series of actions. It should be understood that the invention is not limited to the actions and / or the order of actions shown; for example, actions may occur in one or more orders and / or simultaneously, and together with other actions not presented and described herein. Furthermore, not all actions shown can be used to implement the computer-implemented and non-computer-implemented methods according to the subject matter. Additionally, the computer-implemented and non-computer-implemented methods may alternatively be represented as a series of interrelated states via state diagrams or events. Furthermore, the computer-implemented methods described below and throughout this specification can be stored in an article of manufacture for transmission or transfer to a computer. As used herein, the term "article of manufacture" is intended to cover a computer program accessible from any computer-readable device or storage medium.

[0168] This document has described (and / or will further describe) systems and / or apparatuses with respect to the interaction between one or more components. Such systems and / or components may include those components or sub-components specified herein, one or more of the specified components and / or sub-components, and / or additional components. Sub-components may be implemented as components communicatively coupled to other components rather than being included within a parent component. One or more components and / or sub-components may be combined into a single component that provides aggregate functionality. These components may interact with one or more other components not specifically described herein for brevity but known to those skilled in the art.

[0169] In summary, the systems, computer program products, and / or computer-implemented methods provided and / or described herein relate to the generation and use of synthetic image data. A computer-implemented method for generating synthetic data describing a sample may include: processing sample information of a set of original features describing the sample via a system operatively coupled to a processor, thereby generating processed model input information; and generating synthetic image data by analyzing the model and based on the processed model input information, the synthetic image data being usable for generating a synthetic image and describing at least a portion of the set of original features. The computer-implemented method may further include: generating a synthetic image of a pseudo-sample based on the synthetic image data via a system, the synthetic image having at least one pseudo-feature that is different from and based on the set of original features.

[0170] One or more exemplary embodiments described herein can be implemented within, combined with, and / or coupled to an imaging device, imaging system, scientific measurement device, and / or scientific measurement system.

[0171] In practice, given the one or more exemplary embodiments described herein, the practical applications of the one or more systems, computer-implemented methods, and / or computer program products described herein can be the ability to generate synthetic sample data for training analytical models, train analytical models based on synthetic sample data, and / or use analytical models for sample preparation, sample imaging, and / or control imaging and / or scientific measurement devices and / or systems. These are useful and practical applications of computers, thus providing enhanced (e.g., improved and / or optimized) analytical model training, sample preparation, and / or imaging system usage. In general, such computerized tools can constitute concrete and tangible technological improvements in the field of materials analysis, and particularly in the use of scientific imaging systems, such as, but not limited to, electron microscopy.

[0172] Furthermore, based on the disclosed teachings, one or more exemplary embodiments described herein can be employed in real-world systems. For example, one or more exemplary embodiments described herein can generate synthetic sample data and / or train analytical models without the need to prepare, manufacture, and / or acquire dozens, hundreds, or even thousands of samples as in existing frameworks. This can save power, bandwidth, device / system usage time, user physical time, costs, etc. These can be useful processes for various industries employing materials analysis, product manufacturing and / or production, quality control, etc. Therefore, the embodiments disclosed herein can provide improvements to scientific instrumentation technology (e.g., improvements to the computer technology supporting such scientific instruments, and others).

[0173] Furthermore, one or more exemplary embodiments described herein can achieve an operational-scale level. For example, sample information corresponding to two or more samples can be processed and used for training, at least partially in parallel with each other. Additionally and / or alternatively, synthetic image data corresponding to two or more operations can be used to operate one or more scientific imaging systems, at least partially in parallel with each other.

[0174] This document has described (and / or will further describe) systems and / or apparatuses with respect to the interaction between one or more components. Such systems and / or components may include those components or sub-components specified herein, one or more of the specified components and / or sub-components, and / or additional components. Sub-components may be implemented as components communicatively coupled to other components rather than being included within a parent component. One or more components and / or sub-components may be combined into a single component that provides aggregate functionality. These components may interact with one or more other components not specifically described herein for brevity but known to those skilled in the art.

[0175] One or more exemplary embodiments described herein are inherently and / or inextricably linked to computer technology and cannot be implemented outside of a computing environment. For example, one or more processes performed by one or more exemplary embodiments described herein can more efficiently and even more practically achieve program and / or program instruction execution, such as with respect to the generation of synthetic sample data, compared to existing systems and / or technologies. Systems, computer-implemented methods, and / or computer program products capable of performing these processes have great practical value in the field of materials analysis and cannot be reasonably and practically implemented outside of a computing environment.

[0176] One or more exemplary embodiments described herein can employ hardware and / or software to solve highly technical, non-abstract problems that cannot be performed by humans through a set of mental behaviors. For example, one or even thousands of people cannot efficiently, accurately, and / or effectively analyze computer data / metadata (e.g., synthetic image data and / or sample information data) describing original sample images, CAD images, synthetic images, etc., while one or more exemplary embodiments described herein can achieve this process. Furthermore, the human brain or humans with only pen and paper cannot perform any one or more of these processes as described in one or more exemplary embodiments herein.

[0177] In one or more exemplary embodiments, one or more processes described herein may be executed by one or more dedicated computers (e.g., dedicated processing units, dedicated classical computers, dedicated quantum computers, dedicated hybrid classical / quantum systems, and / or another type of dedicated computer) to perform the defined tasks associated with one or more of the aforementioned technologies. One or more exemplary embodiments described herein and / or components thereof may be used to address new problems arising from advances in the aforementioned technologies, quantum computing systems, cloud computing systems, computer architectures, and / or other technologies.

[0178] One or more exemplary embodiments described herein can be used entirely to perform one or more other functions (e.g., full power-on, full execution, and / or another function) while also performing one or more of the operations described herein.

[0179] To provide additional details about the invention, a list of embodiments and their features is provided below.

[0180] A computer-implemented method for generating synthetic data describing samples may include: processing sample information of a set of original features describing the samples via a system operatively coupled to a processor to generate processed model input information; and generating synthetic image data by analyzing the model and based on the processed model input information, the synthetic image data being used to generate a synthetic image and describing at least a portion of the set of original features.

[0181] The computer-implemented method according to the preceding paragraph further includes: generating a synthetic image of a pseudo-sample based on synthetic image data through the system, the synthetic image having at least one pseudo-feature that is different from and based on the set of original features.

[0182] According to the computer-implemented method described in any of the preceding paragraphs, the sample information includes image data describing an integrated circuit (IC), wherein the set of original features includes one or more IC devices of the integrated circuit, and wherein the synthesized image data includes one or more physical characteristics of the one or more IC devices.

[0183] According to the computer-implemented method described in any of the preceding paragraphs, the sample information includes computer-aided drawing (CAD) data describing the set of raw features and associated noise data in image format.

[0184] According to the computer-implemented method described in any of the preceding paragraphs, the sample information includes Graphics Data System Formatted Data (GDS or GDSII) or Open Layout Systems Exchange Standard Formatted Data (OASIS).

[0185] According to the computer-implemented method described in any of the preceding paragraphs, the sample information and the synthetic image data each describe the region of interest described by reference computer-aided drawing (CAD) data, which describes only a portion of the sample.

[0186] According to any of the preceding paragraphs, the computer-implemented method wherein the processed model input information describes a sequence of integrated circuit (IC) devices, the sequence of IC devices comprising one or more groups of IC devices arranged relative to each other by a specified relationship between IC device features.

[0187] The computer-implemented method according to any of the preceding paragraphs further includes: identifying a first group of groups in the group of IC devices through the system, and subsequently identifying a specific group in the first group of groups based on a first identifier of one aspect and a second identifier of another aspect: the number of IC devices respectively included in the group of IC devices, or a shape-based feature of at least one IC device in the group of IC devices.

[0188] According to the computer-implemented method described in any of the preceding paragraphs, the synthesized image includes a synthesized transmission electron microscope (TEM) image defined by synthesized image data.

[0189] According to any of the preceding paragraphs, the computer-implemented method, wherein the synthesized image includes a virtual three-dimensional image, and wherein the computer-implemented method further includes: virtually slicing the virtual three-dimensional image at a virtual plane of the virtual three-dimensional image; and identifying the region of interest of the slice based on the difference between the region of interest of the resulting slice of the three-dimensional image and the surrounding slice surface of the slice.

[0190] According to any of the preceding paragraphs, the computer-implemented method wherein the analysis model includes an adversarial component, a generative adversarial network (GAN), a diffusion model, a neural network model, or a convolutional neural network model, which is trained using a training dataset of synthetically generated images containing images of integrated circuit devices, sheet cut surfaces, or transmission electron microscope workflow images.

[0191] According to the computer-implemented method described in any of the preceding paragraphs, the analytical model is further configured to reference a degree of originality when generating synthetic image data, which describes the variability relative to sample information or relative to the dataset used to train the analytical model.

[0192] One or more machine systems include one or more logic circuits and one or more computer-readable storage media storing instructions that, when executed by the one or more machine systems, cause the one or more logic circuits to perform one or more operations of a computer-implemented method according to any of the preceding paragraphs.

[0193] The computer-implemented method according to any of the preceding paragraphs further includes: inputting computer-aided drawing (CAD) data into a set of analysis models, the set of analysis models including the analysis model and other analysis models different from the analysis model, which have been trained to generate endpoint detection instructions based on the CAD input of the set of analysis models; generating endpoint detection instructions for a scientific imaging system, including one or more of a focused ion beam (FIB) subsystem or a scanning electron microscope (SEM) subsystem, through the set of analysis models; generating additional synthetic image data, the additional synthetic image data including template information describing a sequence of integrated circuit (IC) devices, through the set of analysis models based on the additional synthetic image data and the combined synthetic image; generating metrological information, including a region of interest (ROI) specification applicable to the sample to be imaged, through the set of analysis models based on the metrological information; and generating control instructions for a scientific imaging system including a transmission electron microscope (TEM) subsystem or another scientific imaging system, through the set of analysis models based on the metrological information.

[0194] The computer-implemented method according to any of the preceding paragraphs further includes: inputting computer-aided drawing (CAD) data into a set of analytical models, the set of analytical models including the analytical model and other analytical models different from the analytical model, which have been trained to generate endpoint detection instructions based on the CAD input of the set of analytical models; generating endpoint detection instructions for a scientific imaging system, including one or more of a focused ion beam (FIB) subsystem or a scanning electron microscope (SEM) subsystem, using the set of analytical models based on the CAD input and endpoint detection instructions; and generating a composite image of the sample, including the composite image, using the set of analytical models. A set of composite images, as a function of the imaging depth of the sample; based on at least one composite image in the composite images, additional composite image data is generated by the set of analytical models, the additional composite image data including template information describing the sequence of integrated circuit (IC) devices; based on the additional composite image data and the composite images, metrological information is generated by the set of analytical models, the metrological information including a region of interest (ROI) specification applicable to the sample to be imaged; and based on the metrological information, control instructions for a scientific imaging system including a transmission electron microscope (TEM) subsystem or another scientific imaging system are generated by the set of analytical models.

[0195] According to any of the preceding paragraphs, the computer-implemented method wherein the synthetic image data description includes a sequence of integrated circuit (IC) devices, the sequence of IC devices comprising one or more groups of IC devices arranged relative to each other by a specified relationship between IC device features.

[0196] The computer-implemented method according to any of the preceding paragraphs further includes: identifying a first group of IC devices in the grouping of the synthetic image based on the synthetic image data, and subsequently identifying a specific group in the first grouping based on a first identifier of one aspect and a second identifier of another aspect: the number of IC devices respectively included in the grouping of the IC devices, or a shape-based feature of at least one IC device in the grouping of the IC devices.

[0197] The computer-implemented method according to any of the preceding paragraphs further includes: identifying a first group of IC devices in the group of IC devices that synthesize the image through the system, and subsequently identifying a specific group in the first group of groups based on a first identifier of one aspect and a second identifier of another aspect: the number of IC devices respectively included in the group of IC devices, or a shape-based feature of at least one IC device in the group of IC devices.

[0198] The computer-implemented method according to any of the preceding paragraphs, wherein the analysis model includes an adversarial component, a diffusion model, a neural network model, or a convolutional neural network model, is trained using a training dataset of synthetically generated images containing images of integrated circuit devices, sheet cut surfaces, or transmission electron microscope workflow images.

[0199] A charged particle beam system may include: a charged particle source, a machine-actuated sample holder, and control circuitry operatively coupled to: a memory storing computer-executable components; and a processor executing the computer-executable components stored in the memory to perform operations including: generating image data of a sample disposed in the sample holder; inputting a portion of the image data into an analysis model trained based on a dataset of synthetic image data describing synthetic images corresponding to the image data of the sample; and generating control instructions via the analysis model configured to adjust the operation of the charged particle source or the sample holder in response to processing by the control circuitry.

[0200] The charged particle beam system described in the preceding paragraph further includes: a focused ion beam (FIB) subsystem; and a scanning electron microscope (SEM) subsystem, wherein the sample comprises one or more complementary metal-oxide-semiconductor (CMOS) devices, dynamic random access memory (DRAM) devices, or NAND devices, and wherein control instructions include endpoint detection instructions configured to adjust the operation of the FIB subsystem and the SEM subsystem to delay the sample and expose one or more CMOS devices.

[0201] The charged particle beam system according to any of the preceding paragraphs further includes: a transmission electron microscope (TEM) system, wherein the sample comprises one or more complementary metal-oxide-semiconductor (CMOS) devices, dynamic random access memory (DRAM) devices, or NAND devices, and wherein the control instructions include metrological information based at least in part on image data describing one or more CMOS devices.

[0202] A computer program product facilitating a process for endpoint detection in an imaging apparatus may include a computer-readable storage medium having program instructions embodied therein, the program instructions being executable by a processor to cause the processor to: process sample information describing a set of primitive features of a sample to generate processed model input information; and generate synthetic image data by the processor and based on the processed model input information, the synthetic image data being usable for generating a synthetic image and describing at least a portion of the set of primitive features.

[0203] According to any of the preceding paragraphs, the computer program product wherein the program instructions may be further executed by a processor to cause the processor to: generate a synthetic image of a pseudo-sample based on synthetic image data, the synthetic image having at least one pseudo-feature that is different from and based on the set of original features.

[0204] According to any of the preceding paragraphs, the computer program product wherein the synthesized image includes a virtual three-dimensional image, and wherein program instructions are further executable by a processor to cause the processor to: virtually slice the virtual three-dimensional image at a virtual plane of the virtual three-dimensional image; and, by the processor, identify the region of interest of the slice based on the difference between the region of interest of the resulting slice of the three-dimensional image and the surrounding slice surface of the slice.

[0205] The computer program product according to any of the preceding paragraphs, wherein the sample information includes image data describing an integrated circuit (IC), wherein the set of original features includes one or more IC devices of the integrated circuit, and wherein the synthesized image data includes one or more physical characteristics of the one or more IC devices.

[0206] A computer-implemented method may include: receiving microscope image data; detecting features in the microscope image data; receiving feature template data describing feature groups including the features; detecting the groups in the microscope image data based at least in part on the feature template data; generating template information describing the groups; and outputting the template information.

[0207] According to the computer-implemented method described in the preceding paragraph, detecting a feature in microscope image data includes: inputting at least a portion of the microscope image data into a model configured to detect the feature; and generating coordinate information describing the location of the feature in the microscope image data as the output of the model.

[0208] According to the computer-implemented method described in any of the preceding paragraphs, the position of the feature corresponds to a set of coordinates of the centroid of the feature.

[0209] The computer-implemented method according to any of the preceding paragraphs, wherein the model includes a convolutional neural network trained to take into account a portion of microscope image data and output coordinate information.

[0210] According to the computer-implemented method described in any of the preceding paragraphs, wherein the feature is a first feature, the model is a first model, the part is a first part, the coordinate information is first coordinate information, and the position is a first position, and wherein the microscope image data includes a second feature, the method further includes: inputting at least a second part of the microscope image data into a second model, the second model being configured to detect the second feature; and generating second coordinate information describing the second position of the second feature in the microscope image data as the output of the second model.

[0211] The computer-implemented method according to any of the preceding paragraphs, wherein the feature is a first feature, wherein the feature template data describes a sequence of multiple features including the first feature, and wherein detecting the group comprises: convolving the feature template data with coordinate information; and detecting instances of the group in the microscope image data based at least in part on the position of the feature relative to at least a subset of the multiple features in the sequence.

[0212] According to the computer-implemented method described in any of the preceding paragraphs, an example of detecting groups includes: determining a first order of a first feature in the sequence; and determining a first order of the first feature in the sequence and a second order of a second feature to match feature template data.

[0213] According to the computer-implemented method described in any of the preceding paragraphs, the feature template data includes feature multiplicity information and feature order information.

[0214] According to the computer-implemented method described in any of the preceding paragraphs, detecting groups in image data includes detecting instances of groups having a reversed feature order.

[0215] The computer-implemented method according to any of the preceding paragraphs, wherein the feature forms at least a portion of a device in an integrated circuit.

[0216] The computer-implemented method according to any of the preceding paragraphs includes microscopic image data comprising images generated by a charged particle microscope.

[0217] According to the computer-implemented method described in any of the preceding paragraphs, the microscope image data further includes coordinate metadata that maps the pixels of the image data to the locations on the sample.

[0218] According to the computer-implemented method described in any of the preceding paragraphs, outputting the template information includes sending the template information to a charged particle microscope configured to generate image data at least in part based on the template information.

[0219] According to the computer-implemented method described in any of the preceding paragraphs, the template information includes the position of the group in the microscope image data.

[0220] According to the computer-implemented method described in any of the preceding paragraphs, the position of the group corresponds to the vertex of the bounding box surrounding the group.

[0221] One or more non-transitory machine-readable media storing instructions that, when executed by a machine, cause the machine to perform operations including: receiving microscope image data; detecting features in the microscope image data; receiving feature template data describing feature groups including the features; detecting groups in the microscope image data based at least in part on the feature template data; generating template information describing the groups; and outputting the template information.

[0222] According to the medium described in the preceding paragraph, detecting a feature in microscope image data includes: inputting at least a portion of the microscope image data into a model configured to detect the feature; and generating coordinate information describing the location of the feature in the microscope image data as the output of the model.

[0223] According to any of the preceding paragraphs, wherein the feature is a first feature, the model is a first model, the portion is a first portion, the coordinate information is first coordinate information, and the position is a first position, and wherein the microscope image data includes a second feature, the operation further includes: inputting at least a second portion of the microscope image data into a second model, the second model being configured to detect the second feature; and generating second coordinate information describing the second position of the second feature in the microscope image data as the output of the second model.

[0224] According to any of the preceding paragraphs, outputting the template information includes sending the template information to a charged particle microscope configured to generate image data at least in part based on the template information.

[0225] According to any of the preceding paragraphs, the feature is a first feature, the feature template data describes a sequence of multiple features including the first feature, and the detection of the grouping includes: convolving the feature template data with coordinate information; and detecting instances of the grouping in the microscope image data based at least in part on the position of the feature relative to at least a subset of the multiple features in the sequence. Exemplary operating environment

[0226] Figure 14This is a schematic block diagram of an operating environment 1400 with which the subject can interact. The operating environment 1400 includes one or more remote components 1410. Remote components 1410 can be hardware and / or software (e.g., threads, processes, computing devices). In one or more exemplary embodiments, remote component 1410 can be a distributed computer system, a program connected to a local auto-extension component via a communication framework 1440, and / or using the resources of the distributed computer system. The communication framework 1440 can include wired network devices, wireless network devices, mobile devices, wearable devices, radio access network devices, gateway devices, femtocell devices, servers, etc.

[0227] The operating environment 1400 also includes one or more local components 1420. Local components 1420 may be hardware and / or software (e.g., threads, processes, computing devices). In one or more exemplary embodiments, local components 1420 may include auto-expansion components and / or programs that communicate with / use remote resources such as remote resources 1410 and 1420 connected to a remote distributed computing system via communication framework 1440.

[0228] One possible communication between the remote component 1410 and the local component 1420 may be in the form of data packets suitable for transmission between two or more computer processes. Another possible communication between the remote component 1410 and the local component 1420 may be in the form of circuit-switched data suitable for transmission between two or more computer processes in a radio time slot. The operating environment 1400 includes a communication framework 1440 that can be used to facilitate communication between the remote component 1410 and the local component 1420, and may include an air interface, such as a UMTS network interface via an LTE network. The remote component 1410 may be operatively connected to one or more remote data repositories 1450, such as hard disk drives, solid-state drives, Subscriber Identity Module (SIM) cards, electronic SIMs (eSIMs), device memory, etc., which can be used to store information on the remote component 1410 side of the communication framework 1440. Similarly, the local component 1420 may be operatively connected to one or more local data repositories 1430 that can be used to store information on the local component 1420 side of the communication framework 1440. Exemplary computing environment

[0229] To provide additional context for the various implementation schemes described herein, Figure 15The following discussion is intended to provide a brief, general description of suitable computing environments 1500 for various implementations of the embodiments described herein. While the embodiments have been described above in the general context of computer-executable instructions that can run on one or more computers, those skilled in the art will recognize that the embodiments may also be implemented in combination with other program modules and / or as a combination of hardware and software.

[0230] Generally speaking, program modules include routines, programs, components, data structures, etc., that perform tasks or implement abstract data types. Furthermore, these methods can be practiced with other computer system configurations, including single-processor or multi-processor computer systems, minicomputers, mainframes, Internet of Things (IoT) devices, distributed computing systems, and personal computers, handheld computing devices, microprocessor-based or programmable consumer electronics, each of which is operatively coupled to one or more associated devices.

[0231] The implementation schemes illustrated in this paper can also be practiced in distributed computing environments, where some tasks are performed by remote processing devices connected via a communication network. In a distributed computing environment, program modules can reside in both local and remote memory storage devices.

[0232] Computing devices typically include a variety of media, which may include computer-readable storage media, machine-readable storage media, and / or communication media. These two terms are used interchangeably herein, as follows. A computer-readable storage media or a machine-readable storage media can be any available storage medium accessible by a computer and includes volatile and non-volatile media, removable and non-removable media. By way of example and not limitation, a computer-readable storage media or a machine-readable storage media can be implemented in conjunction with any method or technology used for storing information, such as computer-readable or machine-readable instructions, program modules, structured data, or unstructured data.

[0233] Computer-readable storage media may include, but is not limited to, random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compressed optical disc read-only memory (CD-ROM), digital versatile optical disc (DVD), Blu-ray disc (BD) or other optical disc storage devices, magnetic tape cassettes, magnetic tape, disk storage devices or other magnetic storage devices, solid-state drives or other solid-state storage devices, or other tangible and / or non-transitory media that can be used to store desired information. In this regard, the terms “tangible” or “non-transitory” used herein to describe storage devices, memories, or computer-readable media exclude only the propagation of transient signals themselves as a modifier, and do not waive the rights of all standard storage devices, memories, or computer-readable media that do not merely propagate transient signals themselves.

[0234] Computer-readable storage media can be accessed by one or more local or remote computing devices, for example via access requests, queries or other data retrieval protocols, for various operations concerning the information stored on the media.

[0235] Communication media typically contain computer-readable instructions, data structures, program modules, or other structured or unstructured data in data signals (such as modulated data signals, such as carrier waves or other transmission mechanisms), and include any information transmission or delivery medium. The term "modulated data signal" or signal refers to a signal whose one or more characteristics are set or altered to encode information in one or more signals. By way of example (but not limited to), communication media include wired media (such as wired networks or direct wired connections) and wireless media (such as acoustic, RF, infrared, and other wireless media).

[0236] Still referencing Figure 15 An exemplary computing environment 1500, which can implement one or more exemplary embodiments described herein, includes a computer 1502, which includes a processing unit 1504, a system memory 1506, and a system bus 1508. The system bus 1508 couples system components, including but not limited to the system memory 1506, to the processing unit 1504. The processing unit 1504 can be any of a variety of commercially available processors. A dual-microprocessor or other multiprocessor architecture may also be used as the processing unit 1504.

[0237] System bus 1508 can be any of several types of bus architectures, and can further interconnect with memory buses (with or without memory controllers), peripheral buses, and local buses using any of a variety of commercially available bus architectures. System memory 1506 includes ROM 1510 and RAM 1512. The Basic Input / Output System (BIOS) can be stored in non-volatile memory (such as ROM, erasable programmable read-only memory (EPROM), EEPROM), containing basic routines such as those that facilitate the transfer of information between components within computer 1502 during startup. RAM 1512 may also include high-speed RAM, such as static RAM for caching data.

[0238] Computer 1502 also includes an internal hard disk drive (HDD) 1514 (e.g., EIDE, SATA) and may include one or more external storage devices 1516 (e.g., floppy disk drive (FDD) 1516, memory stick or flash drive reader, memory card reader, etc.). Although the internal HDD 1514 is shown as being located within computer 1502, the internal HDD 1514 may also be configured for external use in a suitable chassis (not shown). Additionally, although not shown in computing environment 1500, a solid-state drive (SSD) may be used to supplement or replace the HDD 1514.

[0239] Other internal or external storage devices may include at least one other storage device 1520 having storage medium 1522 (e.g., solid-state storage device, non-volatile memory device, and / or optical disc drive that can read from or write to removable media such as CD-ROM, DVD, BD, etc.). External storage device 1516 may be facilitated by a network virtual machine. HDD 1514, external storage device 1516, and storage device (e.g., drive) 1520 may be connected to system bus 1508 via HDD interface 1524, external storage interface 1526, and drive interface 1528, respectively.

[0240] The drive and its associated computer-readable storage medium provide non-volatile storage of data, data structures, computer-executable instructions, etc. For computer 1502, the drive and storage medium may support the storage of any data in a suitable digital format. Although the description of computer-readable storage media above refers to a corresponding type of storage device, other types of computer-readable storage media (whether currently existing or developed in the future) may also be used in the exemplary operating environment, and further, any such storage medium may contain computer-executable instructions for performing the methods described herein.

[0241] The driver and RAM 1512 can store multiple program modules, including an operating system 1530, one or more application programs 1532, other program modules 1534, and program data 1536. All or part of the operating system, applications, modules, and / or data can also be cached in RAM 1512. The systems and methods described herein can be implemented using various commercially available operating systems or combinations of operating systems.

[0242] Computer 1502 may optionally include emulation technology. For example, a hypervisor (not shown) or other intermediary may emulate the hardware environment used for operating system 1530, and the emulated hardware may optionally be different from... Figure 15 The hardware shown is illustrated. In such implementations, the operating system 1530 may include one of a plurality of virtual machines (VMs) hosted at the computer 1502. Furthermore, the operating system 1530 may provide a runtime environment for the application 1532, such as the Java Runtime Environment or the .NET Framework. A runtime environment is a consistent execution environment that allows the application 1532 to run on any operating system that includes a runtime environment. Similarly, the operating system 1530 may support containers, and the application 1532 may be in the form of a container, which is a lightweight, standalone, executable software package that includes, for example, the application's code, runtime environment, system tools, system libraries, and settings.

[0243] Furthermore, computer 1502 may be equipped with a security module, such as a Trusted Processing Module (TPM). For example, using a TPM, the boot component hashes the next boot component over time and waits for the result to match a security value before loading the next boot component. This process can occur at any layer of the computer 1502's code execution stack, for example, at the application execution level or the operating system (OS) kernel level, thereby achieving security at any level of code execution.

[0244] User entities can input commands and information into computer 1502 through one or more wired / wireless input devices (e.g., keyboard 1538, touchscreen 1540, and pointing devices such as mouse 1542). Other input devices (not shown) may include microphones, infrared (IR) remote controls, radio frequency (RF) remote controls or other remote controls, joysticks, virtual reality controllers and / or virtual reality headsets, game controllers, styluses, image input devices (e.g., cameras), gesture sensor input devices, visual motion sensor input devices, emotion or face detection devices, biometric input devices (e.g., fingerprint or iris scanners), etc. These and other input devices are typically connected to processing unit 1504 via input device interface 1544, which can be coupled to system bus 1508, but may also be connected via other interfaces such as parallel ports, IEEE 1394 serial ports, game ports, USB ports, IR interfaces, etc. Interfaces, etc.

[0245] Monitor 1546 or other types of display devices may also be connected to system bus 1508 via an interface such as video adapter 1548. In addition to monitor 1546, the computer typically includes other peripheral output devices (not shown), such as speakers, printers, etc.

[0246] Computer 1502 can operate in a networked environment, using logical connections to one or more remote computers (such as remote computer 1550) via wired and / or wireless communications. Remote computer 1550 can be a workstation, server computer, router, personal computer, portable computer, microprocessor-based entertainment device, peer-to-peer device, or other common network node, and typically includes many or all of the elements described relative to computer 1502, but for brevity only memory / storage device 1552 is shown. The depicted logical connections include wired / wireless connections to a local area network (LAN) 1554 and / or a larger network (e.g., a wide area network (WAN) 1556). Such LAN and WAN networking environments are common in offices and companies and facilitate the establishment of enterprise-wide computer networks (such as intranets), all of which can connect to global communications networks (such as the Internet).

[0247] When used in a LAN networking environment, computer 1502 can connect to local network 1554 via a wired and / or wireless communication network interface or adapter 1558. Adapter 1558 can facilitate wired or wireless communication with LAN 1554, which may also include a wireless access point (AP) configured thereon for communicating with adapter 1558 in wireless mode.

[0248] When used in a WAN networking environment, computer 1502 may include modem 1560 or a communication server that can be otherwise connected to WAN 1556 to establish communication via WAN 1556, such as via the Internet. Modem 1560 may be built-in or external, wired or wireless, and may be connected to system bus 1508 via input device interface 1544. In a networking environment, program modules depicted relative to computer 1502 or parts thereof may be stored in remote memory / storage device 1552. The network connections shown are merely examples, and other methods may be used to establish communication links between computers.

[0249] When used in a LAN or WAN networking environment, computer 1502 can access cloud storage systems or other network-based storage systems, in addition to or as an alternative to external storage device 1516 as described above. Generally, the connection between computer 1502 and the cloud storage system can be established via LAN 1554 or WAN 1556, for example, via adapter 1558 or modem 1560, respectively. When computer 1502 is connected to an associated cloud storage system, external storage interface 1526 can manage the storage provided by the cloud storage system with the help of adapter 1558 and / or modem 1560, just as it would manage other types of external storage. For example, external storage interface 1526 can be configured to provide access to cloud storage sources as if those sources were physically connected to computer 1502.

[0250] Computer 1502 is operable to communicate with any wirelessly configured device or entity (e.g., printer, scanner, desktop and / or laptop computer, portable data assistant, communications satellite, any device or location associated with a wirelessly detectable tag (e.g., kiosk, newsstand, store shelf, etc.) and telephone). This may include Wi-Fi and Wireless technology. Therefore, communication can be structured in the same way as existing networks, or simply self-organizing communication between at least two devices. Additional Information

[0251] The embodiments described herein can be applied to one or more systems, methods, apparatuses, and / or computer program products at any possible level of technical detail integration. A computer program product may include a computer-readable storage medium having computer-readable program instructions thereon for causing a processor to perform aspects of one or more exemplary embodiments described herein. A computer-readable storage medium may be a tangible means capable of retaining and storing instructions for use by an instruction execution apparatus. A computer-readable storage medium may be, for example, but not limited to, electronic storage devices, magnetic storage devices, optical storage devices, electromagnetic storage devices, superconducting storage devices, and / or any suitable combination of the foregoing. A non-exhaustive list of more specific examples of computer-readable storage media may also include: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static random access memory (SRAM), portable optical disc read-only memory (CD-ROM), digital multifunction disc (DVD), memory sticks, floppy disks, mechanical encoding devices (such as punched cards or raised structures in grooves on which instructions are recorded), and any suitable combination of the foregoing. As used herein, computer-readable storage media should not be construed as transient signals themselves, such as radio waves and / or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides and / or other transmission media (e.g., optical pulses transmitted through fiber optic cables) and / or electrical signals transmitted through wires.

[0252] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to a corresponding computing / processing device and / or via a network (e.g., the Internet, a local area network, a wide area network, and / or a wireless network) to an external computer or external storage device. This network may include copper transmission cables, optical fiber transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards them to a computer-readable storage medium within the corresponding computing / processing device. The computer-readable program instructions used to perform the operations of one or more exemplary embodiments described herein may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, status setting data, configuration data for integrated circuits, and / or source code and / or object code written in any combination of one or more programming languages ​​(including object-oriented programming languages ​​such as Smalltalk, C++, etc.) and / or procedural programming languages ​​(such as the "C" programming language and / or similar programming languages). Computer-readable program instructions may be executed entirely on a computer, partially on a computer, as a standalone software package, partially on a computer and / or partially on a remote computer, or entirely on a remote computer and / or a server. In the latter case, the remote computer may be connected to the computer via any type of network (including local area network (LAN) and / or wide area network (WAN)) and / or may be connected to an external computer (e.g., via the Internet using an Internet service provider). In one or more exemplary embodiments, electronic circuitry (including, for example, programmable logic circuitry, field-programmable gate arrays (FPGAs), and / or programmable logic arrays (PLAs)) may execute computer-readable program instructions by utilizing state information of the computer-readable program instructions to personalize the electronic circuitry in order to perform aspects of one or more exemplary embodiments described herein.

[0253] The aspects of one or more exemplary embodiments described herein are described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to one or more exemplary embodiments described herein. It should be understood that each block in the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions. These computer-readable program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, and / or other programmable data processing apparatus to produce a machine, such that the instructions, executable via the processor of the computer or other programmable data processing apparatus, can create means for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium that can direct a computer, programmable data processing apparatus, and / or other means to operate in a particular manner. The computer-readable storage medium storing the instructions may include an article of writing comprising instructions that can implement aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram. Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus and / or other device to perform a series of operations on the computer, other programmable apparatus and / or other device, thereby producing a computer-implemented process, such that the instructions, which execute on the computer, other programmable apparatus and / or other device, perform the functions / actions specified in one or more boxes of a flowchart and / or block diagram.

[0254] The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and / or operation of possible implementations of a system, computer-implementable method, and / or computer program product according to one or more exemplary embodiments described herein. In this regard, each box in a flowchart or block diagram may represent a module, segment, and / or portion of instructions, including one or more executable instructions for implementing a specified logical function. In one or more alternative embodiments, the functions marked in the boxes may occur in a non-conforming order as shown in the figures. For example, two consecutively displayed boxes may execute substantially simultaneously, and / or sometimes in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and / or combinations of blocks in the block diagrams and / or flowcharts, may be implemented by a dedicated hardware system capable of performing the specified functions and / or actions, and / or executing one or more combinations of dedicated hardware and / or computer instructions.

[0255] Although the subject matter has been described above in the general context of computer-executable instructions for a computer program product running on one or more computers, those skilled in the art will recognize that one or more exemplary embodiments described herein can also be implemented, at least in part, in parallel with one or more other program modules. Generally, program modules include routines, programs, components, and / or data structures that perform a specific task and / or implement a specific abstract data type. Furthermore, the aforementioned computer-implemented methods can be practiced with other computer system configurations, including single-processor and / or multi-processor computer systems, small computing devices, mainframe computers, and computers, handheld computing devices (e.g., PDAs, telephones), and / or microprocessor-based or programmable consumer and / or industrial electronic devices. The aspects shown can also be practiced in a distributed computing environment, where tasks are performed by remote processing devices connected via a communication network. However, one or more (if not all) aspects of one or more exemplary embodiments described herein can be practiced on a standalone computer. In a distributed computing environment, program modules can reside in both local memory storage devices and remote memory storage devices.

[0256] As used herein, the terms “component,” “system,” “platform,” and / or “interface” may refer to and / or include computer-related entities or entities associated with an operating machine having one or more specific functions. Entities described herein may be hardware, a combination of hardware and software, software, or software in execution. For example, a component may be, but is not limited to, a process, processor, object, executable program, execution thread, program, and / or computer running on a processor. As an example, an application running on a server and the server itself can both be components. One or more components may reside within a process and / or execution thread, and components may reside on a single computer and / or be distributed across two or more computers. In another example, a corresponding component may be executable from various computer-readable media on which various data structures are stored. These components may communicate, for example, via local and / or remote processes based on signals having one or more data packets (e.g., data from one component interacts with another component in a local system, a distributed system, and / or with other systems via a network such as the Internet). As another example, a component may be a device having specific functionality provided by mechanical parts operated by electrical or electronic circuitry, which is operated by software and / or firmware applications executed by a processor. In this scenario, the processor can be internal and / or external to the device and can execute at least a portion of the software and / or firmware applications. As another example, the component can be a device that provides specific functionality through electronic components without mechanical parts, wherein the electronic components may include a processor and / or other means for executing software and / or firmware that at least partially endow the electronic components with functionality. In one aspect, the component can be emulated via a virtual machine, for example, within a cloud computing system.

[0257] Furthermore, the term “or” is intended to mean inclusive “or” rather than exclusive “or.” That is, unless otherwise specified or clearly apparent from the context, “X adopts A or B” is intended to mean any natural inclusive permutation. In other words, if X adopts A; X adopts B; or X adopts both A and B, then “X adopts A or B” is satisfied in any of the foregoing instances. Furthermore, unless otherwise specified or clearly apparent from the context involving the singular form, the article “a” as used in the subject matter specification and accompanying drawings should generally be interpreted as meaning “one or more.” As used herein, the terms “example” and / or “exemplary” are used to indicate as an example, instance, or illustration. For the avoidance of doubt, the subject matter described herein is not limited to such examples. Moreover, any aspect or design described herein as “example” and / or “exemplary” is not necessarily to be construed as preferred or advantageous over other aspects or designs, nor does it exclude equivalent exemplary structures and techniques known to those skilled in the art.

[0258] As used in this subject matter specification, the term "processor" can substantially refer to any computing processing unit and / or device, including but not limited to a single-core processor; a single processor with software multithreading capabilities; a multi-core processor; a multi-core processor with software multithreading capabilities; a multi-core processor with hardware multithreading technology; a parallel platform; and / or a parallel platform with distributed shared memory. Additionally, a processor can refer to an integrated circuit, application-specific integrated circuit (ASIC), digital signal processor (DSP), field-programmable gate array (FPGA), programmable logic controller (PLC), complex programmable logic device (CPLD), discrete gate or transistor logic components, discrete hardware components, and / or any combination thereof designed to perform the functions described herein. Furthermore, processors can utilize nanoscale architectures, such as, but not limited to, molecular and quantum dot-based transistors, switches, and / or gates, to optimize space utilization and / or enhance the performance of associated equipment. A processor can be implemented as a combination of computing processing units.

[0259] In this document, terms such as “repository,” “storage device,” “data repository,” “data storage device,” “database,” and virtually any other information storage component relating to the operation and functionality of a component are used to refer to a “memory component,” an entity embodied in “memory,” or a component that includes memory. The memory and / or memory components described herein can be volatile or non-volatile memory, or may include both. By way of illustration and not limitation, non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable ROM (EEPROM), flash memory, and / or non-volatile random access memory (RAM) (e.g., ferroelectric RAM (FeRAM)). Volatile memory may include RAM, which may, for example, act as external cache memory. By way of example and not limitation, RAM can take many forms, such as synchronous RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous linked DRAM (SLDRAM), direct Rambus RAM (DRRAM), direct Rambus dynamic RAM (DRDRAM), and / or Rambus dynamic RAM (RDRAM). Furthermore, the memory components of the systems described herein and / or the computer-implemented methods are intended to include, but are not limited to, these and / or any other suitable types of memory.

[0260] The foregoing only includes examples of systems and computer-implemented methods. Of course, in order to describe one or more exemplary embodiments, it is impossible to describe all conceivable combinations of components and / or computer-implemented methods, but those skilled in the art will recognize that many further combinations and / or arrangements of one or more exemplary embodiments are possible. Furthermore, with regard to the use of the terms "comprising," "having," "possessing," etc., in the detailed description, claims, appendices, and / or drawings, these terms are intended to be inclusive in a manner similar to how the term "comprising" is interpreted when used as a transitional word in the claims.

[0261] Descriptions of various implementation schemes may use the phrases “implementation scheme,” “various implementation schemes,” “one or more exemplary implementation schemes,” and / or “some implementation schemes,” each of which may refer to one or more identical or different implementation schemes.

[0262] Various embodiments have been described for illustrative purposes, but these descriptions are not intended to be exhaustive or limited to the embodiments described herein. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein has been chosen to best explain the principles, practical applications, and / or technical improvements relative to market technology of the embodiments, and / or to enable others skilled in the art to understand the embodiments described herein.

Claims

1. A computer-implemented method for generating synthetic data descriptive of a specimen, the method comprising: processing, by a system operatively coupled to a processor, specimen information descriptive of a set of original features of a specimen, resulting in processed model input information; and generating, by an analysis model and based on the processed model input information, synthetic image data usable for generating a synthetic image and descriptive of at least a portion of the set of original features.

2. The computer-implemented method of claim 1, further comprising: generating, by the system, a synthetic image of a pseudo-specimen based on the synthetic image data, the synthetic image having at least one pseudo-feature different from the set of original features and based on the set of original features.

3. The computer-implemented method of claim 1, wherein the specimen information comprises image data descriptive of an integrated circuit (IC), wherein the set of original features comprises one or more IC devices of the integrated circuit, and wherein the synthetic image data comprises one or more physical characteristics of the one or more IC devices.

4. The computer-implemented method of claim 1, wherein the specimen information comprises computer-aided drawing (CAD) data descriptive of the set of original features and associated noise data in an image format.

5. The computer-implemented method of claim 1, wherein the specimen information comprises graphic data system formatted data (GDS or GDSII) or open artwork system interchange standard formatted data (OASIS).

6. The computer-implemented method of claim 1, wherein the specimen information and the synthetic image data each describe a region of interest described with reference to computer-aided drawing (CAD) data, which describes only a portion of the specimen.

7. The computer-implemented method of claim 4, wherein the synthetic image data describes a sequence of integrated circuit (IC) devices, the sequence of IC devices comprising one or more groupings of the IC devices arranged relative to one another by specified relationships between features of the IC devices.

8. The computer-implemented method of claim 7, further comprising: identifying, by the system, a first grouping of the groupings of IC devices of the synthetic image, and subsequently identifying a particular grouping of the first grouping based on a first identification of one of the following aspects and a second identification of another of the following aspects: a number of IC devices respectively included by groupings of the groupings of IC devices; or a shape-based feature of at least one IC device in a grouping of the groupings of IC devices.

9. The computer-implemented method of claim 7, further comprising: identifying, by the system, a first grouping of the groupings of IC devices of the synthetic image based on the synthetic image data, and subsequently identifying a particular grouping of the first grouping based on a first identification of one of the following aspects and a second identification of another of the following aspects: a number of IC devices included in a grouping of the groupings of IC devices; or a shape-based feature of at least one IC device in a grouping of the groupings of IC devices.

10. The computer-implemented method of claim 2, wherein the synthetic image comprises a synthetic transmission electron microscope (TEM) image defined by the synthetic image data.

11. The computer-implemented method of claim 2, wherein the synthetic image comprises a virtual three-dimensional image, and wherein the computer-implemented method further comprises: virtually slicing the virtual three-dimensional image at a virtual plane of the virtual three-dimensional image; and identifying a region of interest of the slice based on a difference between the region of interest of the slice and a surrounding slice surface of the slice.

12. The computer-implemented method of claim 1, wherein the analysis model comprises a generative adversarial component, a diffusion model, a neural network model, or a convolutional neural network model trained using a training dataset containing synthetic generated images of integrated circuit devices, wafer slice faces, or transmission electron microscope workflow images.

13. The computer-implemented method of claim 1, wherein the analysis model is further configured to reference a degree of originality describing a variability relative to the sample information or relative to a dataset used to train the analysis model when generating the synthetic image data.

14. The computer-implemented method of claim 1, further comprising: inputting, by the system, computer-aided drafting (CAD) data to a set of analysis models, the set of analysis models comprising the analysis model and other analysis models different from the analysis model that have been trained to generate end-point detection instructions based on CAD input to the set of analysis models; generating, by the set of analysis models, end-point detection instructions for a scientific imaging system, the scientific imaging system comprising one or more of a focused ion beam (FIB) subsystem or a scanning electron microscope (SEM) subsystem; generating, by the set of analysis models, additional synthetic image data, the additional synthetic image data comprising template information describing a sequence of integrated circuit (IC) devices; generating, by the set of analysis models, metrology information based on the additional synthetic image data and the set of synthetic images, the metrology information comprising region of interest (ROI) specifications applicable to a sample to be imaged; and generating, by the set of analysis models, control instructions based on the metrology information, the control instructions for the scientific imaging system comprising a transmission electron microscope (TEM) subsystem or another scientific imaging system.

15. The computer-implemented method of claim 1, further comprising: inputting, by the system, computer-aided drafting (CAD) data to a set of analysis models, the set of analysis models comprising the analysis model and other analysis models different from the analysis model that have been trained to generate end-point detection instructions based on CAD input to the set of analysis models; generating, by the set of analytical models, end-point detection instructions for a scientific imaging system including one or more of a focused ion beam (FIB) subsystem or a scanning electron microscope (SEM) subsystem; generating, by the set of analytical models, a set of synthetic images of the sample including the synthetic images as a function of an imaging depth of the sample based on the CAD input and the end-point detection instructions; generating, by the set of analytical models, additional synthetic image data including template information describing a sequence of integrated circuit (IC) devices based on at least one synthetic image of the set of synthetic images; generating, by the set of analytical models, metrology information including region of interest (ROI) specifications applicable to a sample to be imaged based on the additional synthetic image data and the set of synthetic images; and and generating, by the set of analytical models, control instructions for the scientific imaging system including a transmission electron microscope (TEM) subsystem or another scientific imaging system based on the metrology information.

16. A charged particle beam system comprising: a charged particle source, a machine-actuated sample holder, and control circuitry operatively coupled to: a memory, the memory storing computer-executable components; and a processor, the processor executing the computer-executable components stored in the memory to cause the processor to perform operations including: generating image data of a sample disposed in the sample holder; inputting a portion of the image data to an analytical model trained based on a dataset of synthetic image data describing synthetic images corresponding to the image data of the sample; and generating, by the analytical model, control instructions configured to adjust operation of the charged particle source or the sample holder in response to processing by the control circuitry.

17. The charged particle beam system of claim 16, further comprising: a focused ion beam (FIB) subsystem; and a scanning electron microscope (SEM) subsystem, wherein the sample includes one or more complementary metal-oxide-semiconductor (CMOS) devices, dynamic random-access memory (DRAM) devices, or not-and (NAND) devices, and wherein control instructions include end-point detection instructions configured to adjust operation of the FIB subsystem and the SEM subsystem to delay the sample and reveal the one or more CMOS devices.

18. The charged particle beam system of claim 16, further comprising: a transmission electron microscope (TEM) system, wherein the sample includes one or more complementary metal-oxide-semiconductor (CMOS) devices, dynamic random-access memory (DRAM) devices, or not-and (NAND) devices, and wherein the control instructions include metrology information describing image data of the one or more CMOS devices, dynamic random access memory (DRAM) devices, or NAND devices based at least in part.

19. A computer program product facilitating a process for imaging device endpoint detection, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to: process, by the processor, sample information describing a set of raw features of a sample, resulting in processed model input information; and generate, by the processor and based on the processed model input information, synthetic image data, the synthetic image data usable to generate a synthetic image and describing at least a portion of the set of raw features.

20. The computer program product of claim 19, wherein the synthetic image comprises a virtual three-dimensional image, and wherein the program instructions are further executable by the processor to cause the processor to: virtually slice, by the processor, the virtual three-dimensional image at a virtual plane of the virtual three-dimensional image; and identify, by the processor, a region of interest of a resulting slice of the three-dimensional image based on a difference between the region of interest of the slice and a surrounding slice surface of the slice.

Images