Radiology Report Generation Through Tumor Segmentation and 3D Visuals

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Manual interpretation of medical imaging is time-consuming, expensive, and subjective, making it difficult for non-expert clinicians and patients to interpret radiology reports, which often lack important quantitative measurements.

Innovation Solution

A method for generating radiology reports that includes segmenting medical images to visualize tumor burdens and generate quantitative measurements, using a computer system to create visual representations of tumor and skeletal structures from CT scans, and display them alongside relevant measurements and timelines.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If manual interpretation of medical imaging is performed by radiologists, then diagnostic accuracy and professional judgment are improved, but time consumption and cost increase significantly

Engineering Contradiction:
Improvediagnostic accuracyVSAvoidtime consumption
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The patent introduces an automated image analysis system as an intermediary between the medical imaging data and the radiologist. This system performs preliminary segmentation, quantification, and measurement of anatomical structures, generating a draft report that the radiologist then reviews and finalizes. The intermediary handles time-consuming manual measurement tasks while preserving radiologist oversight for diagnostic accuracy.

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The system enables self-service by automatically performing image segmentation, volume calculation, and report generation without requiring radiologist intervention for these specific tasks. The automated pipeline processes imaging data independently, extracting quantitative measurements and generating structured reports that reduce the radiologist's workload to review and validation only.

Inventive Principle:
Principle #25Self-service

2Measurement precision

If manual measurements and quantitative analysis are performed, then measurement precision and detail are improved, but productivity and efficiency decrease

Engineering Contradiction:
Improvequantitative measurement accuracyVSAvoidreport generation efficiency
Core Design Contradiction:
Measurement precisionVSProductivity

Solution Approach 1:

The patent replaces the mechanical manual measurement process with an automated computational system. Software algorithms automatically segment images, calculate volumes, and perform quantitative analysis, substituting the radiologist's manual tracing and measurement activities. This maintains measurement precision through algorithmic consistency while dramatically improving productivity by eliminating time-consuming manual operations.

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

3Loss of information

If detailed radiology reports with comprehensive measurements are generated, then information completeness is improved, but ease of interpretation for non-experts deteriorates

Engineering Contradiction:
Improveinformation completenessVSAvoidinterpretability for non-experts
Core Design Contradiction:
Loss of informationVSEase of operation

Solution Approach 1:

The patent segments the radiology report into distinct components: a detailed technical section with comprehensive measurements for experts, and a simplified visual summary with key findings for non-experts. The system separates quantitative data from interpretive commentary, allowing each audience to access the appropriate level of detail without being overwhelmed by unnecessary information.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The report structure applies local quality by providing different levels of information density in different sections. The executive summary uses simplified language and visual aids for patient understanding, while the full report contains detailed measurements and technical analysis for clinician review. Each section is optimized for its specific audience's needs.

Inventive Principle:
Principle #3Local quality

4Productivity

If automated systems are used for radiology report generation, then productivity and time efficiency are improved, but measurement precision and reliability may deteriorate

Engineering Contradiction:
Improvereport generation speedVSAvoidmeasurement accuracy
Core Design Contradiction:
ProductivityVSReliability

Solution Approach 1:

The system incorporates feedback mechanisms where automated measurements are validated against established anatomical ranges and consistency checks. The automated report generation includes quality control steps that flag unusual measurements for review, and the radiologist's final approval serves as a feedback loop to verify automated analysis accuracy before report finalization.

Inventive Principle:
Principle #23Feedback

Data Source

PatentEP4610930A1Systems and methods for generating a radiology report
Publication Date: 2025.09.03 TEMPUS AI INC
  • EP4610930A1 patent drawingFigure 1A
  • EP4610930A1 patent drawingFigure 1B
  • EP4610930A1 patent drawingFigure 1C

AI summary

System and methods for visualizing a cancer in a subject are provided herein. Medical images of a three-dimensional region of interest of the subject are obtained. The medical images are segmented by assigning labels corresponding to tissue types for each of a plurality of sets of one or more pixels in the medical images. Masks are generated for the tissue types based on the segmentation labels. A visual representation of tumor tissue is generated based on a corresponding mask for the tumor tissue. A visual representation of a skeleton of the subject is also generated based on the medical images. The visual representation of the tumor tissue and the visual representation of the skeleton of the subject is displayed in a single image, in a same spatial orientation as in the set of medical images, and at a same relative size as in the set of medical images.