Sinogram Trace Analysis for Automated Medical Diagnosis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current medical imaging technologies rely on manual review and are limited in their ability to automatically detect and characterize anatomical, physiological, and pathological features with high accuracy, especially in complex conditions like cardiomyopathy, colonic polyps, and cancer, which can lead to inconsistencies and inefficiencies in diagnosis.
Innovation Solution
A system and method utilizing deep learning networks to process sinogram data from computed tomography scans, identifying regions of interest and determining diagnostic conditions by correlating sinogram traces with anatomical features, enabling automated detection and characterization of medical conditions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual review and evaluation of medical images is employed by medical professionals, then diagnostic accuracy can be maintained through human expertise, but the process is time-consuming and prone to human error and inconsistencies
Solution Approach 1:
The patent introduces an automated decision support system that acts as an intermediary between the medical imaging data and the final diagnosis. This system processes sinogram data through deep learning networks to extract anatomical features and provide diagnostic recommendations, thereby reducing the time burden on medical professionals while maintaining diagnostic accuracy through automated analysis
2Productivity
If automated decision support systems are introduced to reduce diagnosis time, then efficiency improves, but the ability to accurately detect and characterize complex anatomical features may be compromised
Solution Approach 1:
The patent replaces manual mechanical review of medical images with an automated deep learning-based decision support system. The system uses neural networks to automatically extract anatomical features from sinogram data, characterizing complex structures such as cardiomyopathy, colonic polyps, and cancer lesions with high precision while significantly improving diagnosis efficiency
Solution Approach 2:
The patent transforms the analysis from working with reconstructed images to working directly with sinogram data parameters. By processing the raw sinogram data through deep learning networks, the system extracts anatomical features at the parameter level, enabling more accurate detection and characterization of complex medical conditions while maintaining high computational efficiency
3Reliability
If deep learning networks are used to process sinogram data and automatically extract features, then diagnostic accuracy and efficiency both improve, but the system complexity increases
Solution Approach 1:
The patent segments the complex diagnostic task into distinct functional modules: sinogram data acquisition, deep learning-based feature extraction, anatomical characterization, and diagnostic decision support. This modular segmentation allows the system to achieve high diagnostic accuracy through specialized processing at each stage while managing overall system complexity through clear functional separation
Data Source
AI summary
A method for characterizing anatomical features includes receiving scanned data and image data corresponding to a subject. The scanned data comprises sinogram data. The method further includes identifying a first region in an image of the image data corresponding to a region of interest. The method also includes determining a second region in the scanned data. The second region corresponds to the first region. The method further includes identifying a sinogram trace corresponding to the region of interest. The sinogram trace comprises sinogram data present within the second region. The method includes determining a data feature of the subject based on the sinogram trace and a deep learning network. The method also includes determining a diagnostic condition corresponding to a medical condition of the subject based on the data feature.