# US 2023/0420308 A1 · Examination of a hole formed in a semiconductor specimen

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2023/0420308 A1
- Document ID: US20230420308A1
- Status: Published application
- Kind: A1
- Application number: 17/848,360
- Filed: 2022-06-23
- Published: 2023-12-28
- Earliest claimed: 2022-06-23
- Assignees: Applied Materials Israel Ltd.
- Applicants: Applied Materials Israel Ltd.
- Inventors: Rafael BISTRITZER; Vadim VERESCHAGIN; Grigory KLEBANOV; Roman KRIS; Ilan BEN-HARUSH; Omer KEREM; Asaf GOLOV; Elad SOMMER
- Web page: https://patentgrep.com/patent/US20230420308A1

## CPC

- H10P 74/203: {Structural properties, e.g. testing or measuring thicknesses, line widths, warpage, bond strengths or physical defects}
- G06T 7/0004: {Industrial image inspection}
- G06T 7/11: Region-based segmentation
- G06T 7/50: Depth or shape recovery
- G06T 7/66: of image moments or centre of gravity
- G06V 10/25: Determination of region of interest [ROI] or a volume of interest [VOI]
- G06V 10/255: {Detecting or recognising potential candidate objects based on visual cues, e.g. shapes}
- G06V 10/26: Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V 10/764: using classification, e.g. of video objects
- G06V 20/698: {Matching; Classification}
- G06T 2207/20021: Dividing image into blocks, subimages or windows
- G06T 2207/20081: Training; Learning
- G06T 2207/30148: Semiconductor; IC; Wafer
- H10P: GENERIC PROCESSES OR APPARATUS FOR THE MANUFACTURE OR TREATMENT OF DEVICES COVERED BY CLASS H10
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

A system of examination of a semiconductor specimen, comprising a processor and memory circuitry (PMC) configured to: obtain an image of a hole formed in the semiconductor specimen, wherein the hole exposes at least one layer of a plurality of layers of the semiconductor specimen, segment the image into a plurality of regions, generate at least one of: data Dpix_intensity informative of one or more pixel intensities of one or more regions of the plurality of regions, data Dgeometry informative of one or more geometrical properties of one or more regions of the plurality of regions, feed at least one of Dpix_intensity or Dgeometry to a trained classifier to obtain an output, wherein the output of the trained classifier is usable to determine whether the hole ends at a target layer of the plurality of layers.

## Claims

### Claim 1

A system of examination of a semiconductor specimen, the system comprising a processor and memory circuitry (PMC) configured to:
obtain an image of a hole formed in the semiconductor specimen, wherein the hole exposes at least one layer of a plurality of layers of the semiconductor specimen,
segment the image into a plurality of regions,
generate at least one of:
data Dpix_intensity informative of one or more pixel intensities of one or more regions of the plurality of regions, or
data Dgeometry informative of one or more geometrical properties of one or more regions of the plurality of regions,
feed at least one of Dpix_intensity or Dgeometry to a trained classifier to obtain an output, wherein the output of the trained classifier is usable to determine whether the hole ends at a target layer of the plurality of layers.

### Claim 2 (depends on 1)

The system of claim 1, wherein the output of the trained classifier is informative of a classification of the hole to a class out of different classes that represent different possible outcomes of a manufacturing process of the hole.

### Claim 3 (depends on 2)

The system of claim 2, wherein the different classes include at least one of:
(i) a properly etched hole,
(ii) an under-etched hole,
(iii) a first-degree over-etched hole,
(iv) a second-degree over-etched hole, wherein the second-degree over-etched hole is deeper than the first-degree over-etched hole.

### Claim 4 (depends on 1)

The system of claim 1, wherein at least one of (i) or (ii) or (iii) is met:
(i) the hole is a tilted hole, or
(ii) the image is not radially symmetric, or
(iii) the system is configured to segment the image into a plurality of segments, wherein a majority or all of an area of the image on which said segmentation is performed corresponds to an image of the hole.

### Claim 5 (depends on 1)

The system of claim 1, wherein the image is segmented into a plurality of N regions R1 to RN, wherein, for a manufacturing process of said hole, a predefined region Ri is informative of an over-etch, with i between 1 and N, wherein the system is configured to determine at least one of data Dgeometry or data Dpix_intensity informative of this predefined region Ri.

### Claim 6 (depends on 5)

The system of claim 5, wherein the predefined region Ri, informative of an over-etch, is selected based on its pixel intensity with respect to the pixel intensity of the other regions.

### Claim 7 (depends on 1)

The system of claim 1, wherein at least one of (i) or (ii) or (iii) is met:
(i) at least one of data Dpix_intensity or data Dgeometry comprises data usable to determine data informative of a depth of the hole;
(ii) at least one of data Dpix_intensity or data Dgeometry comprise data informative of one or more physical attributes of a manufacturing process of the hole;
(iii) at least one of data Dpix_intensity or data Dgeometry comprise data informative of one or more physical attributes of a manufacturing process of the hole in a NAND memory unit.

### Claim 8 (depends on 1)

The system of claim 1, wherein data Dgeometry comprises data informative of a ratio between:
first data informative of an average radius of pixels located within a given region of the plurality of regions, and
second data informative of an average radius of pixels located within a second region of the plurality of regions, wherein the second region is different from the given region.

### Claim 9 (depends on 1)

The system of claim 1, wherein data Dpix_intensity comprises data informative of an average pixel intensity of a given region of the plurality of regions.

### Claim 10 (depends on 1)

The system of claim 1, wherein Dgeometry comprises data informative of a ratio between an area of the given region of the plurality of regions and a bounding area.

### Claim 11 (depends on 1)

The system of claim 1, wherein Dgeometry comprises data informative of a distance between a centre of gravity of a given region of the plurality of regions and a pixel of the given region which is the closest to the centre of gravity.

### Claim 12 (depends on 1)

The system of claim 1, wherein Dpix_intensity comprises data informative of a contrast between a given region of the plurality of regions and one or more regions different from the given region.

### Claim 13 (depends on 1)

The system of claim 1, wherein a given region of the plurality of regions includes a darkest area and a brightest area, wherein Dpix_intensity comprises data informative of a contrast between the darkest area and the brightest area.

### Claim 14 (depends on 1)

The system of claim 1, wherein Dpix_intensity comprises data informative of a contrast at a border between a given region of the plurality of regions, and a second region of the plurality of regions, different from the given region.

### Claim 15 (depends on 1)

The system of claim 1, wherein Dgeometry comprises data informative of a ratio between:
a distance between a centre of gravity of a given region of the plurality of regions, and a pixel of the given region, which is closest to the centre of gravity, and
a distance between the centre of gravity of the given region of the plurality of regions, and a pixel of the given region, which is farthest from the centre of gravity.

### Claim 16 (depends on 1)

The system of claim 1, wherein Dgeometry determined for a given region is informative of whether the given region has, at least partially, an annular shape.

### Claim 17 (depends on 1)

The system of claim 1, wherein at least one of (i) or (ii) is met: (i) Dgeometry comprises data informative of a number of pixels in a predefined zone of a region of the plurality of regions, wherein the region is associated with a pixel intensity above a threshold, or (ii) Dgeometry comprises data informative of a side over-etch generated by a etch process of the hole.

### Claim 18 (depends on 1)

The system of claim 1, wherein at least one of (i) or (ii) is met:
(i) the hole exhibits a high aspect ratio and has a width of a nanometric scale, wherein the hole exposes at least one layer of one or more sets of layers, wherein each set of layers comprises layers that differ from each other by their electron yield, wherein the specimen is an intermediate product manufactured by one or more manufacturing stages of a manufacturing process of a three-dimensional NAND memory unit;
(ii) the hole has a depth between 50 nm and 10.000 nm.

### Claim 19

A method of examination of a semiconductor specimen, the method comprising, by a processor and memory circuitry (PMC):
obtaining an image of a hole formed in the semiconductor specimen, wherein the hole exposes at least one layer of a plurality of layers of the semiconductor specimen,
segmenting the image into a plurality of regions,
generating at least one of:
data Dpix_intensity informative of one or more pixel intensities of one or more regions of the plurality of regions, or
data Dgeometry informative of one or more geometrical properties of one or more regions of the plurality of regions,
feeding at least one of Dpix_intensity or Dgeometry to a trained classifier to obtain an output, wherein the output of the trained classifier is usable to determine whether the hole ends at a target layer of the plurality of layers.

### Claim 20

A non-transitory computer readable medium comprising instructions that, when executed by a processor and memory circuitry (PMC), cause the PMC to perform operations comprising:
obtaining an image of a hole formed in the semiconductor specimen, wherein the hole exposes at least one layer of a plurality of layers of the semiconductor specimen,
segmenting the image into a plurality of regions,
generating at least one of:
data Dpix_intensity informative of one or more pixel intensities of one or more regions of the plurality of regions, or
data Dgeometry informative of one or more geometrical properties of one or more regions of the plurality of regions,
feeding at least one of Dpix_intensity or Dgeometry to a trained classifier to obtain an output, wherein the output of the trained classifier is usable to determine whether the hole ends at a target layer of the plurality of layers.
