阅读说明：本技术 用于机器学习的相关切片和视图图像注释 (Related slice and view image annotation for machine learning ) 是由 D·希金斯 B·拉尔森 于 2021-05-28 设计创作，主要内容包括：公开了用于允许用户操作者快速且容易地进行以下操作的方法和系统：(i)检查机器学习算法的产品以评估其准确性,(ii)对此类产品进行校正,以及(iii)编译反馈以用于重新训练算法。示例方法包含：采集样品的多个相关图像；确定所述多个相关图像中的每一图像中的一个或多个特征；并且接着确定所述多个相关图像中的第一图像中的至少第一特征与所述多个图像中的第二图像中的至少第二特征之间的关系。接着,在确定关于所述第一特征的特性信息时,所述特性信息基于所述关系而与所述第一图像中的所述第一特征和所述第二图像中的所述第二特征两者相关联。(Methods and systems are disclosed for allowing a user operator to quickly and easily: (i) checking products of the machine learning algorithm to assess their accuracy, (ii) making corrections to such products, and (iii) compiling feedback for retraining the algorithm. An example method includes: acquiring a plurality of related images of a sample; determining one or more features in each of the plurality of related images; and then determining a relationship between at least a first feature in a first image of the plurality of related images and at least a second feature in a second image of the plurality of images. Then, when determining characteristic information about the first feature, the characteristic information is associated with both the first feature in the first image and the second feature in the second image based on the relationship.)

1. A method for labeling a plurality of related images of a sample, comprising:

obtaining a plurality of related images of the sample acquired with a charged particle microscope system;

determining one or more features in one or more of the plurality of related images;

determining a relationship between a first feature in a first image of the plurality of related images and a second feature in a second image of the plurality of images, wherein the relationship indicates that the first feature and the second feature correspond to the same component of the sample;

determining characteristic information associated with the first feature; and

associating the second feature in the second image with the characteristic information based on the relationship.

2. The method of claim 1, wherein the sample is a thin slice formed of a semiconductor chip, wherein each image of the plurality of related images is acquired using an electron microscope, and wherein between the acquisitions of each image, a portion of the sample is removed with a focused ion beam.

3. The method of claim 1, further comprising:

presenting a Graphical User Interface (GUI) on a display, the GUI including selectable elements that allow a user to input edits to the property information associated with the first feature;

receiving, via the selectable element, an edit comprising a change to the property information associated with the first feature; and

associating the second feature in the second image with the change to the characteristic information based on the relationship.

4. The method of claim 3, wherein at least one of the determinations is performed by one or more machine learning algorithms, and wherein based at least in part on receiving the edits, an updated training data set is generated based on the edits and the set of related images for training of the one or more machine learning algorithms.

5. The method of claim 1, wherein the set of related images corresponds to a plurality of sequential related images of the sample, and wherein determining the relationship comprises determining one or more relationships between features in sequential images.

6. The method of claim 1, wherein determining the relationship further comprises determining an additional relationship between a third feature in the first image and a fourth feature in the second image, and wherein determining the additional relationship comprises determining that the third feature in the first image and the fourth feature in the second image depict additional identical components of the sample.

7. The method of claim 1, wherein determining the characteristic information associated with the first feature comprises:

presenting a GUI that graphically displays the first feature in the first image;

receiving a selection of the first feature via the GUI; and

receiving a selection of the characteristic information associated with the first feature.

8. The method of claim 1, wherein the determining of the characteristic information associated with the first feature is performed at least in part by an algorithm that accesses a data structure describing one or more components of the sample and characteristic information of the one or more components of the sample.

9. The method of claim 1, further comprising:

receiving an edit comprising a change to the relationship; and

associating a third feature in a third image of the plurality of related images with the characteristic information based on the change to the relationship.

10. The method of claim 1, further comprising:

receiving an edit comprising a change to the property information associated with the first feature; and

associating the second feature in the second image with the change to the characteristic information based on the relationship.

11. The method of claim 10, wherein based at least in part on receiving the edits, an updated training data set is generated for training a machine learning algorithm based on the edits and a set of related images.

12. The method of claim 1, wherein receiving the edit comprises presenting a Graphical User Interface (GUI) on a display, the GUI including selectable elements that allow a user to enter the edit to the characteristic information associated with the first feature.

13. The method of claim 1, wherein the GUI is configured to:

displaying a smaller graphical representation of at least the first image and the second image; and

in response to receiving a user input selection of the first image, displaying a larger graphical representation of the first image.

14. The method of claim 13, wherein the smaller graphical representation of at least the first and second images is a cropped version of the first and second images that includes the first and second features, and wherein the smaller graphical representation of at least the first and second images is positioned in the GUI such that the first feature is aligned with the second feature.

15. A non-transitory computer-readable medium containing instructions that, when executed by one or more processors, cause a computing system to perform the method of any of claims 1-14.