# US 2026/0228865 A1 · Generative Adversarial Autoencoder for Noise Reduction in X-ray Images

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

- Number: US 2026/0228865 A1
- Document ID: US20260228865A1
- Status: Published application
- Kind: A1
- Application number: 19/460,452
- Filed: 2026-01-27
- Published: 2026-08-06
- Earliest claimed: 2025-02-04
- Assignees: Bruker Technologies Ltd.
- Applicants: Bruker Technologies Ltd.
- Inventors: Andrei Baranovskiy; Yehonatan Amasay
- Web page: https://patentgrep.com/patent/US20260228865A1

## CPC

- G06T 5/70: Denoising; Smoothing
- G01T 1/247: {Detector read-out circuitry (for processing gain or off-set correction H04N)}
- G06T 5/50: using two or more images, e.g. averaging or subtraction
- G06T 5/60: using machine learning, e.g. neural networks
- G06T 2207/10116: X-ray image
- G06T 2207/20081: Training; Learning
- G06T 2207/20084: Artificial neural networks [ANN]
- G06T 2207/30148: Semiconductor; IC; Wafer
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G01T: MEASUREMENT OF NUCLEAR OR X-RADIATION (radiation analysis of materials, mass spectrometry G01N23/00; tubes for determining the presence, intensity, density or energy of radiation or particles H01J47/00)

## Abstract

A method for reducing noise in an X-ray image, the method includes receiving a plurality of X-ray images acquired at a predefined location on a semiconductor substrate. A plurality of pairs is selected from the plurality of X-ray images, each pair including either (i) two copies of a same X-ray image or (ii) two different X-ray images. A generator is applied to reduce noise in the X-ray images of each pair, and the generator is trained to deceive a discriminator of a Generative Adversarial Network (GAN) into determining whether each pair includes (i) the two copies of a same X-ray image or (ii) the two different X-ray images. Upon the generator successfully trained to deceive the discriminator, the trained generator is applied to reduce noise in at least one additional X-ray image acquired at a selected location on the semiconductor substrate.

## Claims

### Claim 1

A method for reducing noise in an X-ray image, the method comprising:
receiving a plurality of X-ray images acquired at a predefined location on a semiconductor substrate;
selecting, from the plurality of X-ray images, a plurality of pairs, each pair comprising either (i) two copies of a same X-ray image or (ii) two different X-ray images;
applying a generator to reduce noise in the X-ray images of each pair, wherein the generator is trained to deceive a discriminator of a Generative Adversarial Network (GAN) into determining whether each pair comprises (i) the two copies of a same X-ray image or (ii) the two different X-ray images; and
upon the generator successfully trained to deceive the discriminator, applying the trained generator to reduce noise in at least one additional X-ray image acquired at a selected location on the semiconductor substrate.

### Claim 2 (depends on 1)

The method according to claim 1, wherein the generator and the discriminator together form a Generative Adversarial Autoencoder (GAAE) that combines a Variational Autoencoder (VAE) architecture with the GAN.

### Claim 3 (depends on 2)

The method according to claim 2, wherein the generator comprises an encoder and a decoder, wherein the encoder is configured to compress each X-ray image into a latent representation, and wherein the decoder is configured to reconstruct a denoised X-ray image from the latent representation.

### Claim 4 (depends on 3)

The method according to claim 3, wherein the discriminator is configured to receive pairs of latent representations produced by the encoder, and wherein the encoder is trained so that the discriminator cannot distinguish whether the pairs of the latent representations originate from the two copies of the same X-ray image or from the two different X-ray images.

### Claim 5 (depends on 3)

The method according to claim 3, wherein the discriminator is configured to receive pairs of denoised X-ray images produced by the decoder, and wherein the decoder is trained so that the discriminator cannot distinguish whether the pairs of the denoised X-ray images originate from the two copies of the same X-ray image or from the two different X-ray images.

### Claim 6 (depends on 3)

The method according to claim 3, wherein the GAAE is trained using a weighted combination of (a) an intershot loss configured to measure a difference between denoised X-ray images produced from the two different X-ray images of a pair, combined with (b) one or more loss functions selected from a list of loss functions consisting of:
(i) a reconstruction loss configured to ensure the denoised X-ray image remains similar to a corresponding one of the X-ray images;
(ii) a Kullback-Leibler (KL) divergence loss configured to regularize the latent representation to approximate a standard normal distribution;
(iii) a generator loss configured to measure how successfully the encoder deceives the discriminator; and
(iv) a discriminator loss configured to measure an ability of the discriminator to distinguish whether the pairs originate from the two copies of the same X-ray image or from the two different X-ray images.

### Claim 7 (depends on 6)

The method according to claim 6, wherein training of the GAAE stops when at least the intershot loss reaches saturation and ceases to improve.

### Claim 8 (depends on 2)

The method according to claim 2, wherein the GAAE is trained to remove both Poisson noise from photon-counting processes and hardware-induced noise comprising at least one of electronic interference, detector imperfections, or mechanical vibrations.

### Claim 9 (depends on 2)

The method according to claim 2, wherein upon the generator being successfully trained to deceive the discriminator, the discriminator is discarded and only the generator is applied to reduce noise in the at least one additional X-ray image.

### Claim 10 (depends on 1)

The method according to claim 1, wherein the plurality of X-ray images comprises a repeatability set of images acquired from successive shots at the predefined location on the semiconductor substrate.

### Claim 11 (depends on 1)

The method according to claim 1, further comprising, calculating a discriminator loss for at least one of the pairs; comparing the discriminator loss to a predefined threshold; and in response to the discriminator loss exceeding the predefined threshold, generating an indication of an anomaly in the plurality of X-ray images.

### Claim 12

A system for reducing noise in an X-ray image, the system comprising:
an interface configured to receive a plurality of X-ray images acquired at a predefined location on a semiconductor substrate; and
a processor configured to:
select, from the plurality of X-ray images, a plurality of pairs, each pair comprising either (i) two copies of a same X-ray image or (ii) two different X-ray images;
apply a generator to reduce noise in the X-ray images of each pair, wherein the generator is trained to deceive a discriminator of a Generative Adversarial Network (GAN) into determining whether each pair comprises (i) the two copies of a same X-ray image or (ii) the two different X-ray images; and
upon the generator successfully trained to deceive the discriminator, apply the trained generator to reduce noise in at least one additional X-ray image acquired at a selected location on the semiconductor substrate.

### Claim 13 (depends on 12)

The system according to claim 12, wherein the generator and the discriminator together form a Generative Adversarial Autoencoder (GAAE) that combines a Variational Autoencoder (VAE) architecture with the GAN.

### Claim 14 (depends on 13)

The system according to claim 13, wherein the generator comprises an encoder and a decoder, wherein the encoder is configured to compress each X-ray image into a latent representation, and wherein the decoder is configured to reconstruct a denoised X-ray image from the latent representation.

### Claim 15 (depends on 14)

The system according to claim 14, wherein the discriminator is configured to receive pairs of latent representations produced by the encoder, and wherein the encoder is trained so that the discriminator cannot distinguish whether the pairs of the latent representations originate from the two copies of the same X-ray image or from the two different X-ray images.

### Claim 16 (depends on 14)

The system according to claim 14, wherein the discriminator is configured to receive pairs of denoised X-ray images produced by the decoder, and wherein the decoder is trained so that the discriminator cannot distinguish whether the pairs of the denoised X-ray images originate from the two copies of the same X-ray image or from the two different X-ray images.

### Claim 17 (depends on 14)

The system according to claim 14, wherein the GAAE is trained using a weighted combination of (a) an intershot loss configured to measure a difference between denoised X-ray images produced from the two different X-ray images of a pair, combined with (b) one or more loss functions selected from a list of loss functions consisting of:
(i) a reconstruction loss configured to ensure the denoised X-ray image remains similar to a corresponding one of the X-ray images;
(ii) a Kullback-Leibler (KL) divergence loss configured to regularize the latent representation to approximate a standard normal distribution;
(iii) a generator loss configured to measure how successfully the encoder deceives the discriminator; and
(iv) a discriminator loss configured to measure an ability of the discriminator to distinguish whether the pairs originate from the two copies of the same X-ray image or from the two different X-ray images.

### Claim 18 (depends on 17)

The system according to claim 17, wherein training of the GAAE stops when at least the intershot loss reaches saturation and ceases to improve.

### Claim 19 (depends on 13)

The system according to claim 13, wherein the GAAE is trained to remove both Poisson noise from photon-counting processes and hardware-induced noise comprising at least one of electronic interference, detector imperfections, or mechanical vibrations.

### Claim 20 (depends on 13)

The system according to claim 13, wherein upon the generator being successfully trained to deceive the discriminator, the discriminator is discarded and only the generator is applied to reduce noise in the at least one additional X-ray image.

### Claim 21 (depends on 12)

The system according to claim 12, wherein the plurality of X-ray images comprises a repeatability set of images acquired from successive shots at the predefined location on the semiconductor substrate.

### Claim 22 (depends on 12)

The system according to claim 12, wherein the processor is further configured to calculate a discriminator loss for at least one of the pairs, compare the discriminator loss to a predefined threshold, and, in response to the discriminator loss exceeding the predefined threshold, generate an indication of an anomaly in the plurality of X-ray images.
