Medical Image Compression with Extra-Dimension Autoencoders
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for compressing digital medical image data sets, particularly 3D images like MRI scans, face challenges in efficiently reducing data redundancy and optimizing storage and transmission resources without significant information loss.
Innovation Solution
A method utilizing a trained autoencoder network that incorporates an extra dimension to exploit data redundancy, such as the coil, time, or layer dimensions, to compress medical image data sets, allowing for efficient storage and resource-saving transmission.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If traditional compression methods are used for medical image data, then storage space is reduced, but data redundancy is not sufficiently exploited and information loss occurs
Solution Approach 1:
The patent introduces an additional dimension to the autoencoder architecture that specifically processes redundancy dimensions (coil, time, layer) separately from the spatial dimensions. This dimensional separation allows the model to exploit data redundancy without compromising spatial information integrity, resolving the contradiction between compression and information preservation.
Solution Approach 2:
The autoencoder is divided into separate processing streams: one for spatial information and another for redundancy dimensions. This segmentation enables independent optimization of compression in redundancy dimensions while preserving spatial fidelity, achieving effective data reduction without significant information loss.
2Quantity of substance
If data redundancy is reduced through compression, then storage resources are saved, but transmission reliability may be compromised
Solution Approach 1:
By separating redundancy dimensions from spatial dimensions in the autoencoder architecture, the system can compress data in redundancy dimensions while maintaining spatial information integrity. This ensures that transmission reliability is preserved even with reduced data volume, as the critical spatial information remains intact.
3Productivity
If compression is applied to medical image data, then transmission bandwidth requirements are reduced, but image quality may deteriorate
Solution Approach 1:
The patent segments the compression process into separate handling of redundancy dimensions and spatial dimensions. This allows aggressive compression in redundancy dimensions (improving transmission efficiency) while maintaining high fidelity in spatial dimensions (preserving image quality), thus resolving the contradiction between transmission efficiency and image quality.
Data Source
AI summary
A computer-implemented method may include receiving, at an input layer of a trained autoencoder, the digital medical image data set from the medical scanner. The trained autoencoder may include at least one extra dimension in the input layer and optionally in an output layer. The at least one extra dimension is provided in particular in response to a received notification of at least one data redundancy dimension of the received digital medical image data set. The method may include compressing, by the trained autoencoder, at least one part of the received digital medical image data set using the received notification of the at least one data redundancy dimension and/or data received by the at least one extra dimension.