Medical Video Overlay Adaptation for Low-Latency Real-Time Augmentation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing medical procedures using endoscopes face delays in video image updates, causing irritation for practitioners, and there is a need for real-time augmentation of video data to enhance visualization.

Innovation Solution

A computer-implemented method that compares multiple video frames to determine changes, calculates an extrapolation of overlay data, and generates a real-time overlay with low latency by processing pixels directly and adapting initial overlay data based on frame analysis, using field programmable gate arrays (FPGA) for optimization.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If video processing and overlay generation are performed using traditional computing methods, then the system can provide comprehensive image information and analysis, but the processing latency increases causing irritation for the medical practitioner

Engineering Contradiction:
Improvecomprehensive image informationVSAvoidvideo processing latency
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The patent replaces traditional CPU-based video processing with FPGA-based parallel processing architecture. The FPGA hardware directly processes video streams at the pixel level, eliminating the need for software-based image processing pipelines. This substitution of mechanical/computational approach enables real-time overlay generation with latency below one video frame while maintaining comprehensive anatomical structure visualization and surgical instrument tracking capabilities.

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

Solution Approach 2:

The patent segments the video processing task into independent parallel operations within the FPGA: video frame acquisition, overlay image generation, drift detection, and composite image assembly all occur simultaneously in different hardware modules. This segmentation allows each processing stage to operate independently and concurrently, achieving real-time performance without sequential processing delays.

Inventive Principle:
Principle #1Segmentation

2Loss of time

If real-time video processing is implemented to reduce latency, then practitioner irritation is reduced, but the complexity of the processing system increases

Engineering Contradiction:
Improvevideo processing latencyVSAvoidprocessing system complexity
Core Design Contradiction:
Loss of timeVSDevice complexity

Solution Approach 1:

The patent replaces complex software-based real-time processing with dedicated FPGA hardware circuits that perform processing natively in parallel. The FPGA's reconfigurable logic allows direct hardware implementation of video processing algorithms, eliminating the need for complex software scheduling, memory management, and processing pipelines that would otherwise be required to achieve real-time performance.

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

Solution Approach 2:

The FPGA serves multiple functions simultaneously: it acts as a video frame grabber, image processing unit, overlay generator, drift detection system, and composite image assembler all in one device. This multi-functionality consolidates what would otherwise require multiple separate processing systems into a single integrated hardware platform, reducing overall system complexity despite the advanced capabilities.

Inventive Principle:
Principle #6Universality (Multi-functionality)

3Measurement precision

If overlay data is continuously updated in real-time to maintain accuracy, then visualization accuracy is improved, but the processing load and latency increase

Engineering Contradiction:
Improveoverlay data accuracyVSAvoidprocessing latency
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent implements continuous real-time processing within the FPGA where video frames are processed as they arrive without interruption or batching. The overlay generation and drift detection operate continuously on the incoming video stream, ensuring that overlay data is always current and accurately reflects the current surgical scene. This continuous processing eliminates delays associated with batch processing while maintaining high accuracy through constant updates.

Inventive Principle:
Principle #20Continuity of useful action

Solution Approach 2:

The patent uses FPGA hardware to perform continuous overlay updates through dedicated parallel processing circuits that operate independently of frame rate or processing bottlenecks. The hardware directly computes overlay positions and transforms based on current video frame data, eliminating the sequential processing delays that would occur with software-based continuous updates.

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

Data Source

PatentEP4721695A2Real time augmentation
Publication Date: 2026.04.08 BRAINLAB AG
  • EP4721695A2 patent drawingFigure 1~2
  • EP4721695A2 patent drawingFigure 3~4
  • EP4721695A2 patent drawingFigure 5

AI summary

A computer-implemented method of generating an overlay of medical video data and overlay data is presented. The method comprising the steps acquiring, from a medical video modality, the medical video data comprising at least a first video frame and a second video frame of different points in time, t1 and t2, (step S1), analysing the acquired medical video data comprising a comparison of the video data captured by the first and the second video frames (step S2); providing initial overlay data (step S3), generating modified overlay data by adapting the initial overlay data based on a result of the analysis of the medical video data (step S4), and generating the overlay by generating a video output comprising at least medical video data originating from the medical video modality and comprising the generated modified overlay data (step S5). In a particular embodiment, the determined change over time in the first and second video frames is a spatial shift of an object imaged in the video frames.