Image-Text Deep Neural Network for Patch-Wise CXR Pathology Detection

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current AI algorithms for CXR abnormality analysis provide limited accuracy and reliability, especially for pathologies like pneumothorax, and lack spatial information that aids medical practitioners in understanding and validating the AI model's output.

Innovation Solution

An image-text deep neural network (DNN) is employed to process medical imaging data, using a vision transformer architecture for patch-wise prediction, which integrates a text prompt to provide localized findings of pathologies, enabling unsupervised learning and refining predictions through a patch-wise loss function.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of information

If AI algorithms provide classification results for the overall CXR image, then the analysis covers the entire observation region, but the output lacks spatial information making it difficult for medical practitioners to assess relevance and reliability

Engineering Contradiction:
Improvespatial informationVSAvoidalgorithm complexity
Core Design Contradiction:
Loss of informationVSDevice complexity

Solution Approach 1:

The CXR image is divided into multiple spatial patches, and the AI algorithm generates separate classification results for each patch. This segmentation approach preserves spatial information by providing localized predictions while maintaining the overall coverage of the image, allowing medical practitioners to assess relevance and reliability of findings in specific regions.

Inventive Principle:
Principle #1Segmentation

2Reliability

If reference AI algorithms are used for CXR abnormality analysis, then the analysis can be performed, but the accuracy is limited especially for pathologies like pneumothorax with varying manifestations

Engineering Contradiction:
Improvedetection accuracyVSAvoidadaptability to varying pathology manifestations
Core Design Contradiction:
ReliabilityVSAdaptability or versatility

Solution Approach 1:

The algorithm applies local quality by generating specialized classification results for each spatial patch rather than applying a uniform classification to the entire image. This allows the system to adapt to varying manifestations of pathologies like pneumothorax by providing localized predictions that capture region-specific characteristics, thereby improving detection accuracy for diverse pathology presentations.

Inventive Principle:
Principle #3Local quality

Data Source

PatentEP4583046A1Image-text deep neural network algorithm for patch-wise prediction of pathology finding
Publication Date: 2025.07.09 SIEMENS HEALTHINEERS AG
  • EP4583046A1 patent drawingFigure 1
  • EP4583046A1 patent drawingFigure 2~3
  • EP4583046A1 patent drawingFigure 4~5

AI summary

Imaging data is processed in an image-text deep neural network, e.g., a vision transformer deep neural network. The image-text deep neural network also processes a text input indicative of a pathology. For each of multiple spatial patches within an observation region, a respective prediction of the presence or the absence of a finding of a pathology is provided.