# US 2025/0095141 A1 · Method and system of detecting and classifying an object in real-time medical imaging

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

- Number: US 2025/0095141 A1
- Document ID: US20250095141A1
- Status: Published application
- Kind: A1
- Application number: 18/387,483
- Filed: 2023-11-07
- Published: 2025-03-20
- Earliest claimed: 2023-09-14
- Assignees: L&T Technology Services Limited
- Applicants: L&T Technology Services Limited
- Inventors: SREERAG HAREENDRANATH; AKSHAYA BABU; ANUSREE KAREEPARAMBATH
- Web page: https://patentgrep.com/patent/US20250095141A1

## CPC

- G06T 7/0012: {Biomedical image inspection}
- G06T 5/70: Denoising; Smoothing
- G06T 5/92: based on global image properties
- G06T 7/11: Region-based segmentation
- G06V 10/25: Determination of region of interest [ROI] or a volume of interest [VOI]
- G06V 10/54: relating to texture
- G06V 10/56: relating to colour
- G06V 10/764: using classification, e.g. of video objects
- G06T 2207/10024: Color image
- G06T 2207/10081: Computed x-ray tomography [CT]
- G06T 2207/20081: Training; Learning
- G06T 2207/20084: Artificial neural networks [ANN]
- G06T 2207/30096: Tumor; Lesion
- G06V 2201/03: Recognition of patterns in medical or anatomical images
- G06V 2201/07: Target detection
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

A method for detecting and classifying an object is disclosed. The method includes receiving imaging data captured by imaging device. Further, the method includes generating a pre-processed image frame by correcting one or more pixels corresponding to reflections in corresponding image frame using autoencoder based DL model. Further the corrected image is split into R channel image, G channel image, and B channel image. Further, texture enhancement of G channel image and denoising the B channel image using wiener filter is performed to generate a color enhanced image frame. Further, regions of interest are determined corresponding to at least one object in the pre-processed image frame using SSD model. Further, the at least one object is classified as one of: cancerous type, pre-cancerous type or non-cancerous type using a CNN model.

## Claims

### Claim 1

A method of detecting and classifying an object in real-time medical imaging, the method comprising:
receiving, by an image processing device, real-time imaging data captured by an imaging device,
wherein the imaging data comprises a set of image frames;
for each of the set of image frames:
generating, by the image processing device, a pre-processed image frame by:
correcting, by the image processing device, one or more pixels corresponding to one or more reflections in a corresponding image frame using an autoencoder based deep learning (DL) model;
splitting, by the image processing device, the corrected image frame into a R channel image, a G channel image, and a B channel image;
performing, by the image processing device, texture enhancement of the G channel image;
denoising, by the image processing device, the B channel image using a Wiener filter; and
generating, by the image processing device, a color enhanced image frame from the R channel image, the texture enhanced G channel image and the denoised B channel image;
determining, by the image processing device, at least one region of interest corresponding to at least one object in the pre-processed image frame using a Single Shot Detection (SSD) model,
wherein the SSD model is pre-trained to detect the at least one object by extracting one or more features from the pre-processed image frame corresponding to the at least one object; and
classifying, by the image processing device, the at least one object as one of: a cancerous type, a pre-cancerous type or a non-cancerous type using a Convolution Neural Network (CNN) model.

### Claim 2 (depends on 1)

The method of claim 1, wherein the generation of the pre-processed image frame comprises:
enhancing, by the image processing device, a contrast level of the corresponding image frame using a gamma correction technique based on a first predefined gamma correction parameter.

### Claim 3 (depends on 1)

The method of claim 1, wherein the autoencoder based DL model is trained to correct one or more pixels corresponding to the one or more reflections based on the corresponding input image frame.

### Claim 4 (depends on 1)

The method of claim 1, wherein the generation of the color enhanced image frame comprises:
normalizing, by the image processing device, the R channel image, the texture enhanced G channel image, and the denoised B channel image based on a predefined normalization threshold range; and
determining, by the image processing device, a modified RGB image frame based on a predefined modification factor and performing a gamma correction based on a second predefined gamma correction parameter.

### Claim 5 (depends on 4)

The method of claim 4, wherein the determination of the modified RGB image frame comprises:
generating, by the image processing device, a normalized RGB image by combining the normalized R channel image, the texture enhanced G channel image, and the denoised B channel image;
segregating, by the image processing device, each of a plurality of pixels of the normalized RGB image into one of a first cluster or a second cluster based on a pre-defined clustering threshold; and
generating, by the image processing device, an enhanced image frame by scaling each of the plurality of pixels of the first cluster and the second cluster based on a first scaling factor and a second first scaling factor respectively.

### Claim 6 (depends on 1)

The method of claim 1, wherein the SSD model comprises a backbone model and an SSD head, wherein the backbone model is a pre-trained image detection network configured to extract the one or more features, and
wherein the SSD head comprises a plurality of convolutional layers stacked on top of the backbone model.

### Claim 7 (depends on 1)

The method of claim 1, comprising:
displaying, by the image processing device, the real-time imaging data on a display screen with a bounding box corresponding to the at least one object in each of the corresponding pre-processed image frames.

### Claim 8 (depends on 7)

The method of claim 7, comprising:
generating and displaying, by the image processing device, a report along with the bounding box, wherein the report comprises the classification of the at least one object and one or more recommendations determined based on the classification of the at least one object.

### Claim 9 (depends on 1)

The method of claim 1, wherein the CNN model is pretrained to determine a class of the at least one object from one of the cancerous type, the pre-cancerous type or the non-cancerous type based on determination of one or more object classification features.

### Claim 10

A system for correcting a set of input images, comprising:
a processor; and
a memory communicably coupled to the processor, wherein the memory stores processor-executable instructions, which, on execution by the processor, cause the processor to:
receive real-time imaging data captured by an imaging device,
wherein the imaging data comprises a set of image frames;
for each of the set of image frames:
generate a pre-processed image frame based on:
correction of one or more pixels corresponding to one or more reflections in a corresponding image frame using an autoencoder based deep learning (DL) model;
splitting the corrected image frame into a R channel image, a G channel image, and a B channel image;
generation of a texture enhanced G channel image by performing texture enhancement of the G channel image;
generation of a denoised B channel image by denoising the B channel image using a Wiener filter; and
generation of a color enhanced image frame from the R channel image, the texture enhanced G channel image and the denoised B channel image;
determine at least one region of interest corresponding to at least one object in the pre-processed image frame using a Single Shot Detection (SSD) model,
wherein the SSD model is pre-trained to detect the at least one object by extracting one or more features from the pre-processed image frame corresponding to the at least one object; and
classify the at least one object as one of: a cancerous type, a pre-cancerous type or a non-cancerous type using a Convolution Neural Network (CNN) model.

### Claim 11 (depends on 10)

The system of claim 10, wherein the generation of the pre-processed image frame is based on:
enhancement of a contrast level of the corresponding image frame using a gamma correction technique based on a first predefined gamma correction parameter.

### Claim 12 (depends on 10)

The system of claim 10, wherein the autoencoder based DL model is trained to correct one or more pixels corresponding to the one or more reflections based on the corresponding input image frame.

### Claim 13 (depends on 10)

The system of claim 10, wherein the generation of the color enhanced image frame is based on:
normalization of the R channel image, the texture enhanced G channel image, and the denoised B channel image based on a predefined normalization threshold range; and
determination of a modified RGB image frame based on a predefined modification factor and performing a gamma correction based on a second predefined gamma correction parameter.

### Claim 14 (depends on 13)

The system of claim 13, wherein the determination of the modified RGB image frame is based on:
generation of a normalized RGB image by combining the normalized R channel image, the texture enhanced G channel image, and the denoised B channel image;
segregation of each of a plurality of pixels of the normalized RGB image into one of a first cluster or a second cluster based on a pre-defined clustering threshold; and
generation of an enhanced image frame by scaling each of the plurality of pixels of the first cluster and the second cluster based on a first scaling factor and a second first scaling factor respectively.

### Claim 15 (depends on 10)

The system of claim 10, wherein the SSD model comprises a backbone model and an SSD head, wherein the backbone model is a pre-trained image detection network configured to extract the one or more features, and
wherein the SSD head comprises a plurality of convolutional layers stacked on top of the backbone model.

### Claim 16 (depends on 10)

The system of claim 10, wherein the processor is configured to:
display the real-time imaging data on a display screen with a bounding box corresponding to the at least one object in each of the corresponding pre-processed image frames.

### Claim 17 (depends on 16)

The system of claim 16, wherein the processor is configured to generate and display a report along with the bounding box, wherein the report comprises the classification of the at least one object and one or more recommendations determined based on the classification of the at least one object.

### Claim 18 (depends on 10)

The system of claim 10, wherein the CNN model is pretrained to determine a class of the at least one object from one of the cancerous type, the pre-cancerous type or the non-cancerous type based on determination of one or more object classification features.

### Claim 19

A non-transitory computer-readable medium storing computer-executable instructions for extracting relevant data from a document image, the computer-executable instructions configured for:
receiving real-time imaging data captured by an imaging device,
wherein the imaging data comprises a set of image frames;
for each of the set of image frames:
generating a pre-processed image frame by:
correcting one or more pixels corresponding to one or more reflections in a corresponding image frame using an autoencoder based deep learning (DL) model;
splitting the corrected image frame into a R channel image, a G channel image, and a B channel image;
performing texture enhancement of the G channel image;
denoising the B channel image using a Wiener filter; and
generating a color enhanced image frame from the R channel image, the texture enhanced G channel image and the denoised B channel image;
determining at least one region of interest corresponding to at least one object in the pre-processed image frame using a Single Shot Detection (SSD) model,
wherein the SSD model is pre-trained to detect the at least one object by extracting one or more features from the pre-processed image frame corresponding to the at least one object; and
classifying the at least one object as one of: a cancerous type, a pre-cancerous type or a non-cancerous type, using a Convolution Neural Network (CNN) model.

### Claim 20 (depends on 19)

The non-transitory computer-readable medium of claim 19, wherein the generation of the pre-processed image frame comprises:
enhancing a contrast level of the corresponding image frame using a gamma correction technique based on a first predefined gamma correction parameter.
