Ultrasound Bladder Extraction Accuracy via Pattern Feedback
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional ultrasound diagnostic apparatuses face challenges in accurately measuring urine volume when the bladder is in an abnormal condition, such as gas accumulation or deformation due to prostatic hypertrophy, leading to incorrect extraction of the bladder region and subsequent measurement errors.
Innovation Solution
The apparatus employs a bladder extraction unit that determines the success or failure of bladder extraction based on specific criteria, including convex hull analysis and brightness variance, and adjusts image quality to improve accuracy. It also stores abnormal bladder patterns and provides guidance for acquiring new ultrasound images when the bladder region does not match the reference pattern, allowing for classification and improved extraction.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If automated bladder extraction is performed using machine learning methods, then ease of operation is improved, but measurement precision deteriorates when the bladder is in abnormal condition
Solution Approach 1:
The system performs feedback by comparing the extracted bladder region with the reference pattern, calculating similarity metrics, and using this feedback to determine whether to accept or reject the extraction result. When the similarity is below the threshold, the system requests a new ultrasound image, creating a closed-loop feedback mechanism that ensures extraction accuracy.
Solution Approach 2:
The system changes parameters by adjusting the similarity threshold and using different pattern matching criteria to accommodate abnormal bladder conditions. The reference pattern can be modified or replaced when abnormalities are detected, allowing the system to adapt its extraction criteria to different bladder states.
2Measurement precision
If the system strictly follows reference pattern matching, then measurement precision is improved, but adaptability deteriorates when abnormal bladder patterns are present
Solution Approach 1:
The system dynamically adjusts its behavior based on the comparison results. When the bladder region matches the reference pattern, it proceeds with measurement. When abnormalities are detected (low similarity), it switches to requesting a new image or adjusting the reference pattern, making the system flexible and adaptive to different bladder conditions.
Solution Approach 2:
The system performs preliminary comparison between the extracted bladder region and the reference pattern before finalizing the measurement. This preliminary action allows the system to detect potential extraction errors due to abnormal conditions and take corrective measures before proceeding with urine volume calculation.
3Measurement precision
If multiple determination criteria are used to verify bladder region, then measurement precision is improved, but device complexity increases
Solution Approach 1:
The system uses a set of determination criteria with a similarity threshold to verify bladder region extraction. Rather than using all possible verification methods, it applies a focused set of criteria (pattern matching, similarity calculation, threshold comparison) that provides sufficient verification without excessive complexity. The system performs partial verification through convex hull analysis and brightness comparison when needed.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This approach enhances the accuracy of bladder extraction by adjusting image quality and pattern classification, effectively handling abnormal bladder conditions and improving the precision of urine volume measurement.
Implementation Method 1
ultrasonic waves are transmitted from the ultrasound probe toward a subject, the ultrasound probe receives ultrasound echoes from the subject
Implementation Method 2
In a case where a median value of brightness in the bladder region exceeds a predetermined first threshold value and a variance value of brightness in the differential region is equal to or less than a predetermined second threshold value, the image quality adjustment unit may lower a gain to adjust the image quality of the ultrasound image
Implementation Method 3
in a case where a difference between a median value of brightness in the bladder region and a median value of brightness in the differential region is equal to or less than a predetermined third threshold value and a variance value of brightness in the differential region exceeds a predetermined fourth threshold value, the image quality adjustment unit may narrow a dynamic range to adjust the image quality of the ultrasound image
Data Source
Figure 1
Figure 2~3
Figure 4
AI summary
Provided are an ultrasound diagnostic apparatus and a control method of an ultrasound diagnostic apparatus capable of improving the accuracy of extracting a bladder. The ultrasound diagnostic apparatus 1 includes a bladder pattern storage unit 22 that stores a bladder pattern, a reference pattern setting unit 21 that sets a normal or abnormal bladder pattern as a reference pattern, a bladder extraction unit 18 that extracts a bladder region from an ultrasound image, a bladder extraction success/failure determination unit 19 that determines whether the bladder region represents a bladder having the reference pattern, and an image quality adjustment unit 20 that adjusts the image quality of the ultrasound image in a case where determination is made that the bladder region does not represent the bladder having the reference pattern, in which in a case where the determination is made that the bladder region does not represent the bladder having the reference pattern even in an ultrasound image of which the image quality is adjusted, the bladder extraction success/failure determination unit 19 determines whether the bladder region represents the bladder having the abnormal bladder pattern.