Neural Network Molybdenum Target Image Processing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Manual screening of suspected malignant tumors in molybdenum target images is inefficient and inaccurate, requiring extensive experience and leading to low screening efficiency and positioning accuracy.
Innovation Solution
An image processing method using a neural network model trained through deep learning to extract and mark candidate regions in molybdenum target images, where the probability of a lump being a malignant tumor exceeds specific thresholds, indicating a mapping relationship between regions and tumor probabilities.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual screening is used to position suspected malignant tumors, then the doctor can identify tumors based on experience, but the screening efficiency and positioning accuracy are low
Solution Approach 1:
The patent replaces the manual mechanical screening process with an automated image processing system using neural networks. The system automatically extracts features from molybdenum target images, classifies lumps as malignant or benign, and positions suspected tumors without manual intervention, thereby improving both screening efficiency and positioning accuracy simultaneously
Solution Approach 2:
The neural network model performs self-learning and automatic classification of tumor regions. The system independently processes images, extracts features, and identifies malignant tumors without requiring continuous human guidance, enabling high-throughput automated screening while maintaining accurate positioning
2Reliability
If manual screening is used to position suspected malignant tumors, then the process can be performed with current technology, but extensive experience is required and positioning accuracy is low
Solution Approach 1:
The patent replaces experience-dependent manual assessment with an automated neural network system that objectively analyzes image features. The system processes multiple features (shape, density, margin characteristics) systematically to provide reliable positioning without requiring doctor experience, thereby improving positioning reliability while managing system complexity through automation
3Productivity
If automated image processing is implemented, then screening efficiency is improved, but the system complexity increases
Solution Approach 1:
The patent divides the image processing task into distinct modular stages: image acquisition, feature extraction, classification, and result output. Each module performs a specific function independently, which improves screening efficiency through automated processing while managing complexity by organizing the system into manageable, specialized components
Solution Approach 2:
The neural network model serves multiple functions simultaneously: it extracts features from images, classifies lumps as malignant or benign, and positions suspected tumors. This multi-functionality improves screening efficiency by consolidating multiple operations into a single system while avoiding the complexity of separate specialized systems
Data Source
AI summary
An image processing method performed by a terminal is provided. A molybdenum target image is obtained, and a plurality of candidate regions are extracted from the molybdenum target image. In the molybdenum target image, a target region is marked in the plurality of candidate regions by using a neural network model obtained by deep learning training, a probability that a lump comprised in the target region is a target lump being greater than a first threshold, a probability that the target lump is a malignant tumor being greater than a second threshold, and the neural network model being used for indicating a mapping relationship between a candidate region and a probability that a lump comprised in the candidate region is the target lump.