Automated Multimedia Radiological Report Generation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

The generation of multimedia radiological reports is labor-intensive and requires manual intervention, making it inefficient for conveying medical information to patients and healthcare professionals, as conventional methods rely on manual selection and creation of images and speech output from written reports.

Innovation Solution

A computer-implemented method using a large language model to automatically create a multimedia radiological report by generating a script, selecting relevant data, and combining visual and audio elements, allowing for the creation of a fully automated report without manual intervention.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If manual methods are used to generate multimedia radiological reports with 3D technicians and radiologists, then the quality and accuracy of the report can be maintained, but the time consumption and workload increase significantly

Engineering Contradiction:
Improvereport qualityVSAvoidtime consumption
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The system enables automatic generation of multimedia radiological reports by having the computer system perform tasks that previously required manual intervention by radiologists and 3D technicians. The automated workflow extracts data from written reports, generates corresponding visualizations, and assembles the final multimedia report without human assistance, thereby maintaining quality while dramatically reducing time consumption.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The system performs preliminary processing of written medical reports by automatically extracting relevant information, identifying key findings, and preparing data structures before the actual multimedia report generation. This preliminary action includes parsing the written report to identify anatomical regions, pathological findings, and measurement data that will be needed for subsequent automated visualization and report assembly.

Inventive Principle:
Principle #10Preliminary action

2Ease of operation

If manual selection and creation of images and speech output is performed, then the comprehensibility for patients can be improved, but the labor intensity increases

Engineering Contradiction:
ImprovecomprehensibilityVSAvoidlabor intensity
Core Design Contradiction:
Ease of operationVSDevice complexity

Solution Approach 1:

The system replaces the mechanical manual process of selecting images and creating speech output with automated computational processes. The computer system automatically generates 3D visualizations from medical imaging data and synthesizes speech output from extracted text, eliminating the need for manual intervention while maintaining comprehensibility for patients through consistent application of visualization and text-to-speech algorithms.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

3Productivity

If automated generation of multimedia reports is implemented, then productivity increases, but the complexity of the system increases

Engineering Contradiction:
Improvereport generation speedVSAvoidsystem complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The automated report generation system is divided into distinct functional modules: a text processing module that parses written reports, a data extraction module that identifies relevant findings, a visualization module that generates 3D images, and an assembly module that combines all elements into the final multimedia report. This segmentation allows each module to be independently optimized and maintained, managing system complexity while achieving high productivity.

Inventive Principle:
Principle #1Segmentation

Data Source

PatentUS20250095813A1Computer-implemented method and system for automatic creation of a multimedia radiological report and computer program product
Publication Date: 2025.03.20 SIEMENS HEALTHINEERS AG
  • US20250095813A1 patent drawing
  • US20250095813A1 patent drawing
  • US20250095813A1 patent drawing

AI summary

One or more example embodiments relates to a method and a system for automatic creation of a multimedia radiological report on a patient, having: a medical information database which has written medical reports on patients; and a data processing unit which is configured: to create a multimedia report script based on the provided written medical report making use of a large language model; to provide selected data to which the written medical report on the patient and/or the created multimedia report script relate; to create a visual medical report on the patient based on the provided data and the created multimedia report script; and which is configured to combine automatically the created visual medical report and audio data for creating the multimedia radiological report on the patient.