# US 12,217,856 B2 · Apparatus and method for identifying regions of interest during slide digitization

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

- Number: US 12,217,856 B2
- Document ID: US12217856B2
- Status: Granted
- Kind: B2
- Application number: 18/602,776
- Filed: 2024-03-12
- Published: 2024-11-07
- Granted: 2025-02-04
- Earliest claimed: 2023-05-03
- Assignees: Pramana, Inc.
- Applicants: Pramana, Inc.
- Inventors: Prasanth Perugupalli; Jaya Jain; Durgaprasad Dodle; Prateek Jain; Suhash Gerald; Dipankar Das
- Web page: https://patentgrep.com/patent/US12217856B2

## CPC

- G06V 20/693: {Acquisition}
- G16H 30/40: for processing medical images, e.g. editing
- G06V 10/10: Image acquisition (document image scanning and transmission H04N1/00; control of digital cameras H04N23/60)
- G06V 10/25: Determination of region of interest [ROI] or a volume of interest [VOI]
- G16H 50/20: for computer-aided diagnosis, e.g. based on medical expert systems
- G16H 70/60: relating to pathologies
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA

## Abstract

An apparatus for identifying regions of interest during slide digitization is disclosed. The apparatus includes at least processor and a memory communicatively connected to the processor. The memory contains instructions configuring the processor to receive a user dataset associated with at least a pathology slide. The memory contains instructions configuring the processor to identify one or more regions of interest within at least a pathology slide as a function of the user dataset. The memory contains instructions configuring the processor to identify at least one scan parameter as a function of the one or more regions of interest. The memory contains instructions configuring the processor to generate a digitized slide by scanning the at least a pathology slide as a function the at least one scan parameter.

## Claims

### Claim 1

An apparatus for identifying regions of interest during slide digitization, wherein the apparatus comprises:
at least a processor; and
a memory communicatively connected to the at least a processor, wherein the memory comprises instructions configuring the at least a processor to:
receive identification data as a function of a user dataset associated with at least a pathology slide;
identify one or more regions of interest within the at least a pathology slide as a function of the user dataset;
identify at least one scan parameter as a function of the one or more regions of interest;
train a machine learning model iteratively with identification training data, wherein the identification training data correlates a plurality of pathology slides and the user dataset to a plurality of regions of interest;
calculate an accuracy score for the machine learning model, wherein the accuracy score identifies regions of interest within a plurality of pathology slides;
modify the pathology slide by the identification training data as a function of user feedback and accuracy score;
retrain the machine learning model by iteratively adding outputs of the machine learning model to the plurality of pathology slides and the user data set;
generate a digitized slide by scanning the at least a modified pathology slide as a function of the at least one scan parameter;
process images from the modified pathology slide, wherein processing the images comprises enhancing at least a region of interest by performing a color space conversation operation; and
display the digitized slide using a user interface at a display device.

### Claim 2 (depends on 1)

The apparatus of claim 1, wherein receiving the user dataset comprises receiving the user dataset for an electronic health record.

### Claim 3 (depends on 1)

The apparatus of claim 1, wherein the memory comprises instructions configuring the at least a processor to:
generate diagnostic data as a function of the user dataset; and
identify the one or more regions of interest as a function of the diagnostic data.

### Claim 4 (depends on 1)

The apparatus of claim 1, wherein the memory comprises instructions configuring the at least a processor to generate a plurality of slide data as a function of the digitized slide and the user dataset.

### Claim 5 (depends on 4)

The apparatus of claim 4, wherein the memory comprises instructions configuring the at least a processor to attach the plurality of slide data to the digitized slide as metadata.

### Claim 6 (depends on 1)

The apparatus of claim 1, wherein the user dataset comprises:
a plurality of textual data associated with the at least a pathology slide; and
a plurality of image data associated with the at least a pathology slide.

### Claim 7 (depends on 1)

The apparatus of claim 1, wherein the at least one scan parameter comprises a magnification level.

### Claim 8 (depends on 1)

The apparatus of claim 1, wherein the at least one scan parameter comprises a focus depth.

### Claim 9 (depends on 1)

The apparatus of claim 1, wherein scanning the at least a pathology slide comprises scanning the at least a pathology slide in a single pass.

### Claim 10

A method for identifying regions of interest during slide digitization, wherein the method comprises:
receiving, using at least a processor, a user dataset associated with at least a pathology slide;
identifying, using the at least a processor, one or more regions of interest within the at least a pathology slide as a function of the user dataset;
identifying, using the at least a processor, at least one scan parameter as a function of the one or more regions of interest;
training a machine learning model iteratively with identification training data, wherein the identification training data correlates a plurality of pathology slides and the user dataset to a plurality of regions of interest;
calculating an accuracy score for the machine learning model, wherein the accuracy score identifies regions of interest within a plurality of pathology slides;
modify the pathology slide by the identification training data as a function of user feedback and accuracy score;
retrain the machine learning model by iteratively adding outputs of the machine learning model to the plurality of pathology slides and the user data set;
generate a digitized slide by scanning the at least a modified pathology slide as a function of the at least one scan parameter;
process images from the modified pathology slide, wherein processing the images comprises enhancing at least a region of interest by performing a color space conversation operation; and
displaying, using a user interface at a display device, the digitized slide.

### Claim 11 (depends on 10)

The method of claim 10, wherein receiving the user dataset comprises receiving the user dataset for an electronic health record.

### Claim 12 (depends on 10)

The method of claim 10, further comprising:
generating, using the at least a processor, diagnostic data as a function of the user dataset; and
identifying, using the at least a processor, the one or more regions of interest as a function of the diagnostic data.

### Claim 13 (depends on 10)

The method of claim 10, further comprising:
generating, using the at least a processor, a plurality of slide data as a function of the digitized slide and the user dataset.

### Claim 14 (depends on 13)

The method of claim 13, further comprising:
attaching, using the at least a processor, the plurality of slide data to the digitized slide as metadata.

### Claim 15 (depends on 10)

The method of claim 10, wherein the user dataset comprises:
a plurality of textual data associated with the at least a pathology slide; and
a plurality of image data associated with the at least a pathology slide.

### Claim 16 (depends on 10)

The method of claim 10, wherein the at least one scan parameter comprises a magnification level.

### Claim 17 (depends on 10)

The method of claim 10, wherein the at least one scan parameter comprises a focus depth.

### Claim 18 (depends on 10)

The method of claim 10, wherein scanning the at least a pathology slide comprises scanning the at least a pathology slide in a single pass.