# US 12,119,107 B2 · AI system for predicting reading time and reading complexity for reviewing 2D/3D breast images

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

- Number: US 12,119,107 B2
- Document ID: US12119107B2
- Status: Granted
- Kind: B2
- Application number: 18/319,727
- Filed: 2023-05-18
- Published: 2024-01-18
- Granted: 2024-10-15
- Earliest claimed: 2019-09-27
- Assignees: Hologic, Inc.
- Applicants: Hologic, Inc.
- Inventors: Ashwini Kshirsagar; Haili Chui; Nikolaos Gkanatsios; Adora Dsouza; Xiangwei Zhang
- Web page: https://patentgrep.com/patent/US12119107B2

## CPC

- G16H 40/20: for the management or administration of healthcare resources or facilities, e.g. managing hospital staff or surgery rooms
- A61B 6/502: {for diagnosis of breast, i.e. mammography}
- G06Q 10/06311: {Scheduling, planning or task assignment for a person or group}
- G06Q 10/06398: {Performance of employee with respect to a job function}
- G06Q 10/1097: {using calendar-based scheduling for task assignment}
- G06T 7/0012: {Biomedical image inspection}
- G16H 10/20: for electronic clinical trials or questionnaires
- G16H 30/20: for handling medical images, e.g. DICOM, HL7 or PACS
- G16H 30/40: for processing medical images, e.g. editing
- G16H 50/20: for computer-aided diagnosis, e.g. based on medical expert systems
- G16H 50/30: for calculating health indices; for individual health risk assessment
- A61B 5/7267: {involving training the classification device}
- A61B 6/465: {adapted to display user selection data, e.g. graphical user interface, icons or menus}
- G06T 2200/24: involving graphical user interfaces [GUIs]
- G06T 2207/20081: Training; Learning
- G06T 2207/30068: Mammography; Breast
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D)
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

Examples of the present disclosure describe systems and methods for predicting the reading time and/or reading complexity of a breast image. In aspects, a first set of data relating to the reading time of breast images may be collected from one or more data sources, such as image acquisition workstations, image review workstations, and healthcare professional profile data. The first set of data may be used to train a predictive model to predict/estimate an expected reading time and/or an expected reading complexity for various breast images. Subsequently, a second set of data comprising at least one breast image may be provided as input to the trained predictive model. The trained predictive model may output an estimated reading time and/or reading complexity for the breast image. The output of the trained predictive model may be used to prioritize mammographic studies or optimize the utilization of available time for radiologists.

## Claims

### Claim 1

A method of analyzing medical image data, the method comprising:
receiving, from an X-ray imaging system, mammographic exam data for a patient, wherein the mammographic exam data includes breast image data including one or more X-ray images of the patient's breast tissue;
processing the breast image data to determine one or more image factors;
providing the mammographic exam data and the determined one or more image factors to a predictive model;
determining, by the predictive model, correlations between the one or more image factors and training factors, wherein the training factors are determined based at least in part on mammographic exam data for one or more patients and evaluation data for one or more exam readers, wherein determining the correlations comprises evaluating the determined one or more image factors against a complexity index, wherein the complexity index comprises machine learning-generated mappings of a plurality of factors that affect an amount of time required to interpret the mammographic exam data, wherein the plurality of factors include image factors derived from a training set of mammographic exam data and reader factors derived from a training set of evaluation data;
determining an expected reading time for the mammographic exam data based on the correlations;
assigning a complexity label to the breast image data based on at least one of the expected reading time, the correlations, and a portion of the breast image data;
receiving a selection of the mammographic exam data for the patient; and
in response to receiving the selection of the mammographic exam data, displaying the complexity label in association with the mammographic exam data.

### Claim 2 (depends on 1)

The method of claim 1, wherein the complexity label is assigned according to the complexity index.

### Claim 3 (depends on 2)

The method of claim 2, wherein the complexity index comprises a plurality of complexity index ratings that are each mapped to a range of factor values.

### Claim 4 (depends on 1)

The method of claim 1, further comprising determining a reading priority based on the correlations.

### Claim 5 (depends on 4)

The method of claim 4, further comprising displaying the reading priority in response to the selection of the mammographic exam data.

### Claim 6 (depends on 1)

The method of claim 1, further comprising adjusting the expected reading time based on the complexity label assigned.

### Claim 7 (depends on 1)

The method of claim 1, further comprising configuring a first workload for a first clinician and a second workload for a second clinician, wherein a first combined reading time of the first workload and a second combined reading time of the second workload differ by less than a threshold amount of time.

### Claim 8 (depends on 7)

The method of claim 7, wherein the first workload comprises a first number of exam readings and the second workload comprises a second number of exam readings, and the first number of exam readings differs from the second number of exam readings.

### Claim 9 (depends on 1)

The method of claim 1, wherein determining, by the predictive model, the correlations between the one or more image factors and the training factors, includes scoring each of the one or more image factors based on a scoring model.

### Claim 10 (depends on 9)

The method of claim 9, wherein the complexity label is associated with a range of scores.

### Claim 11 (depends on 10)

The method of claim 10, wherein assigning the complexity label to the breast image data includes determining a total score for the one or more image factors falls within the range of scores.

### Claim 12 (depends on 10)

The method of claim 10, wherein assigning the complexity label to the breast image data based on the expected reading time comprises determining the expected reading time falls within a predetermined range, wherein the predetermined range comprises a percentile of aggregated reading time durations.

### Claim 13 (depends on 1)

The method of claim 1, wherein the one or more image factors include one or more of a number of regions of interest in the breast image data, a type of region of interest in the breast image data, a number of computer aided design (CAD) marks in the breast image data, a type of CAD marks in the breast image data, a breast evaluation location, a breast density, and a tissue composition.

### Claim 14 (depends on 13)

The method of claim 13, wherein processing of the breast image data includes one or more of artifact reduction and de-noising.

### Claim 15 (depends on 1)

The method of claim 1, further comprising receiving one or more reader factors, wherein determining the expected reading time for the mammographic exam data is further based on the one or more reader factors.

### Claim 16 (depends on 15)

The method of claim 15, wherein the one or more reader factors include factors characterizing an average reader.

### Claim 17 (depends on 15)

The method of claim 15, wherein the one or more reader factors and the selection of the mammographic exam data are each associated with a same reader.

### Claim 18 (depends on 15)

The method of claim 15, wherein the one or more reader factors includes one or more of a reader experience score, a reader knowledge score, a reader evaluation technique score, and a reader competency score.

### Claim 19 (depends on 1)

The method of claim 1, wherein the image factors includes a quantity of factors and the complexity label is associated with a threshold number of factors, and wherein associating the complexity label with the mammographic exam data comprises determining the quantity of factors exceeds the threshold number of factors; and
wherein the quantity of factors includes one or more of a number of computer aided design (CAD) marks in the breast image data, a number of CAD marks in a specific portion of the breast image data, or an amount of dense tissue in the breast image data.

### Claim 20

A system for analyzing medical image data and determining a complexity of the medical image data, the system comprising:
a processor; and
memory coupled to the processor, the memory comprising computer executable instructions that, when executed by the processor, performs a method comprising:
receiving, from an X-ray imaging system, mammographic exam data for a patient, wherein the mammographic exam data includes breast image data including one or more X-ray images of the patient's breast tissue;
processing the breast image data to determine one or more image factors;
providing the mammographic exam data and the determined one or more image factors to a predictive model;
determining, by the predictive model, correlations between the one or more image factors and training factors, wherein the training factors are determined based at least in part on mammographic exam data for one or more patients and evaluation data for one or more exam readers, wherein determining the correlations comprises evaluating the one or more image factors against a complexity index, wherein the complexity index comprises machine learning-generated mappings of a plurality of factors that affect an amount of time required to interpret the mammographic exam data, wherein the plurality of factors include image factors derived from a training set of mammographic exam data and reader factors derived from a training set of evaluation data;
determining an expected reading time for the mammographic exam data based on the correlations;
assigning a complexity label to the breast image data based on at least one of the expected reading time, the correlations, and a portion of the breast image data;
receiving a selection of the mammographic exam data for the patient; and
in response to receiving the selection of the mammographic exam data, displaying the complexity label in association with the mammographic exam data.