AI Sequencing Image Recovery From Motion Blur at Reduced Settling Time
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Sequencing technologies face performance, accuracy, and cost challenges due to delays in imaging processes that cause oligo damage and increased processing time, leading to reduced accuracy and higher costs.
Innovation Solution
AI-driven enhancement of motion blurred sequencing images using neural networks, such as Generative Adversarial Networks (GANs) and autoencoders, to recover high-quality images from reduced settling time data, improving performance, accuracy, and reducing costs by minimizing sample damage.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If imaging is performed after reduced movement settling time, then productivity is improved by reducing processing time, but measurement precision deteriorates due to motion blur causing oligo damage
Solution Approach 1:
A neural network model acts as an intermediary between the blurred image and the final enhanced output. The neural network receives the motion-blurred sequencing image as input and processes it through learned transformations to produce an enhanced image that recovers details and reduces blur artifacts, thereby improving measurement precision without requiring increased settling time
Solution Approach 2:
The system creates a computational copy of the blurred image and processes this copy through the neural network to generate an enhanced version. This allows the original captured image to remain unchanged while a processed version with improved quality is used for analysis, effectively decoupling the capture speed from the final image quality
2Loss of time
If movement settling time is reduced, then loss of time is decreased, but reliability deteriorates due to increased oligo damage
Solution Approach 1:
The system converts the harmful motion blur and oligo damage effects into beneficial information for training the neural network. By collecting training data that includes images with varying degrees of blur and damage, the neural network learns to recognize and correct these specific artifacts, transforming what were previously harmful effects into training signals that improve sequencing accuracy
Solution Approach 2:
The neural network serves as a mediator that compensates for the reduced settling time. It processes the hurriedly captured images and recovers the information quality that would normally require longer settling time to achieve, thereby maintaining reliability without the time penalty
Data Source
AI summary
Artificial intelligence driven enhancement of motion blurred sequencing images enables enhanced sequencing that determines a sequence of bases in genetic material with any one or more of: improved performance, improved accuracy, and/or reduced cost. A training set of images taken after unreduced and reduced movement settling times during sequencing is used to train a neural network to enable the neural network to recover enhanced images, as if taken after the unreduced movement settling time, from unenhanced images taken after the reduced movement settling time.