Biological Image Tiling for Accurate Patient Response Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional patient response prediction techniques for pharmaceutical drugs are inaccurate and computationally inefficient due to the large size and complexity of biological images, often resulting in low prediction accuracy and high computational requirements.
Innovation Solution
The use of image processing and machine learning techniques to process biological images by generating image tiles, preprocessing them to identify discrete tissue components, and applying an artificial neural network (ANN) to predict patient responses, such as tumor reduction or adverse reactions, by assigning predictive values to these components.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional patient response prediction techniques are used, then the process is simple, but prediction accuracy is low and computational requirements are high
Solution Approach 1:
The patent divides the biological image into multiple smaller image tiles (e.g., 256x256 pixels each) to make the data more manageable. This segmentation allows the system to process large images without overwhelming computational resources, while maintaining prediction accuracy by analyzing multiple smaller regions rather than the entire image at once.
Solution Approach 2:
The patent extracts and pre-processes specific features from the image tiles, such as identifying discrete biological tissue components and normalizing color information. This extraction of relevant features reduces the computational burden by focusing only on the most informative aspects of the images rather than processing all pixel data.
2Productivity
If biological images are processed without segmentation, then the complete information is available, but computational efficiency decreases and processing time increases
Solution Approach 1:
By segmenting the biological image into smaller tiles, the system can process each tile independently and in parallel, significantly reducing processing time. The patent applies this by dividing full-resolution images into multiple lower-resolution tiles that can be handled more efficiently by the neural network.
Solution Approach 2:
The patent performs preliminary processing steps on the image tiles before feeding them to the neural network, including color normalization and feature extraction. This preliminary action prepares the data in advance, reducing the computational load during the actual prediction phase and improving overall processing efficiency.
Data Source
AI summary
In an aspect, a data processing system includes a computer-readable memory comprising computer-executable instructions, and at least one processor configured to execute executable logic including at least one artificial neural network trained to predict one or more responses to a chemical substance by identifying one or more discrete biological tissue components in a biological image. When the at least one processor is executing the computer-executable instructions, the at least one processor is configured to carry out operations including: receiving spatially arranged image data representing a biological image of a patient; generating spatially arranged image tile data representing a plurality of image tiles; processing the spatially arranged image tile data through one or more data structures storing one or more portions of executable logic included in the artificial neural network to predict one or more responses of a patient.