Boundary-Based Medical Image Compression
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional data compression techniques for medical images result in unacceptable loss of fidelity, limiting their usefulness in medical diagnosis, as they treat image data as homogenous and apply uniform compression, which is inefficient in terms of storage and transmission.
Innovation Solution
The technique involves segmenting medical images into regions of interest and non-interest, applying different compression rates to maintain image fidelity, allowing for lossless compression of critical areas and more aggressive compression of less relevant regions, thereby reducing system resource consumption while preserving data integrity.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If uniform compression is applied to entire medical images, then storage and transmission efficiency is improved, but image fidelity in critical regions deteriorates
Solution Approach 1:
The patent divides the medical image into multiple regions of interest (ROIs) and non-ROI areas. Different compression algorithms and parameters are applied to each region: lossless or low-compression methods for ROIs containing critical diagnostic information, and lossy high-compression methods for non-critical background areas. This segmentation allows the system to achieve overall high compression ratios while preserving fidelity where needed.
Solution Approach 2:
The patent implements local quality control by assigning different compression quality levels to different spatial regions of the image. Critical anatomical structures and pathological features are identified and protected with higher quality compression settings, while less important regions receive aggressive compression. This ensures that diagnostic quality is maintained in essential areas without sacrificing overall compression efficiency.
2Manufacturing precision
If lossless compression is used for medical images, then image fidelity is maintained, but storage and transmission efficiency deteriorates
Solution Approach 1:
The patent segments the image into ROI and non-ROI regions, applying lossless compression only to ROI areas where diagnostic fidelity is critical. Non-ROI regions are compressed using more efficient lossy algorithms. This selective approach maintains necessary image quality while achieving practical compression ratios for storage and transmission.
Solution Approach 2:
The patent dynamically adjusts compression parameters based on regional importance. For ROI areas, compression parameters are set to preserve all diagnostic information (lossless or near-lossless). For non-ROI areas, parameters are relaxed to enable higher compression ratios. This parameter adaptation resolves the contradiction between fidelity and efficiency.
3Quantity of substance
If aggressive compression is applied to reduce file size, then storage and transmission costs are reduced, but diagnostic quality deteriorates
Solution Approach 1:
The patent identifies and segments critical diagnostic regions from the rest of the image. Aggressive compression is applied only to non-diagnostic background areas, while ROI regions containing anatomical structures and pathological features are compressed with methods that preserve diagnostic quality. This ensures overall file size reduction without compromising diagnostic capability.
Solution Approach 2:
The patent implements quality differentiation across the image: high quality preservation in ROI areas where diagnostic decisions are made, and lower quality acceptance in non-ROI areas. This local quality strategy allows aggressive compression overall while maintaining diagnostic quality where it matters most.
Data Source
AI summary
Compressing a data file representing an image wherein one or more regions within the image are identified. At least one of the regions is selected and the data corresponding to the selected region is compressed at a different rate that the data corresponding to non-selected regions of the image. The different compression rates are selected to maintain a desired fidelity in an image reconstructed from the compressed data file. The different compression rates can be predetermined, selected by a user, or automatically selected. Compression rates can be based upon the type of image to be compressed such as x-ray, CT scan or MRI images, the structure that is being analyzed, parameters regarding the use of the image, system parameters such as storage capacity available, or bandwidth of a communication channel used to transmit the compressed file.