Indicator Features in Micro-Ultrasound Prostate Imaging
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional ultrasound technologies face limitations in accurately visualizing prostate cancer due to low resolution and difficulty in distinguishing between acoustically homogeneous tissues, leading to high false-negative rates and unnecessary biopsies, necessitating a new imaging methodology for improved prostate cancer detection and diagnosis.
Innovation Solution
The development of Indicator Features in high-resolution micro-ultrasound images, which are used to train classifiers to identify statistically significant patterns associated with cancerous or benign tissues, guiding targeted biopsies and improving diagnostic accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional ultrasound technology is used, then the imaging process is quick and inexpensive, but the resolution is low and cancer detection accuracy is poor
Solution Approach 1:
The patent applies parameter changes by transitioning from conventional ultrasound frequencies to high-frequency micro-ultrasound (20-50 MHz), fundamentally changing the imaging parameters to achieve cellular-level resolution. This parameter change enables the detection of acoustic features at the cellular level, directly improving cancer detection accuracy while maintaining the non-invasive nature of ultrasound imaging
Solution Approach 2:
The patent introduces a new dimension of analysis by examining tissue architecture and acoustic features at the cellular level rather than just at the organ level. This dimensional shift from macroscopic to microscopic visualization allows for the identification of cancer-specific patterns that are invisible to conventional ultrasound, resolving the contradiction between detection accuracy and system complexity
2Reliability
If conventional ultrasound is used, then the procedure is simple, but false-negative rates are high and necessary biopsies are missed
Solution Approach 1:
The patent introduces indicator features as an intermediary between the imaging modality and the biopsy procedure. These computed features serve as a bridge that translates complex high-frequency ultrasound data into actionable diagnostic information, guiding biopsy targeting with high reliability while improving overall diagnostic efficiency by reducing false negatives
Solution Approach 2:
The patent implements feedback by using computed indicator features to guide and adjust biopsy targeting in real-time. The system continuously analyzes ultrasound images, computes cancer likelihood indicators, and uses this feedback to optimize biopsy needle placement, thereby improving both reliability and productivity in the diagnostic workflow
3Measurement precision
If high-frequency micro-ultrasound is used, then cellular-level resolution is achieved, but the ability to distinguish acoustically homogeneous tissues remains challenging
Solution Approach 1:
The patent applies segmentation by dividing the prostate tissue into discrete cellular-level units and analyzing the acoustic properties of individual cells and small groups of cells. This segmentation approach allows for the detection of subtle architectural patterns and heterogeneity that are characteristic of cancer, even in tissues that appear acoustically homogeneous at lower resolutions
Solution Approach 2:
The patent implements local quality analysis by examining acoustic features at the cellular level rather than averaging over large tissue regions. This local approach enables the detection of focal abnormalities and subtle variations in tissue architecture that distinguish cancer from benign tissue, overcoming the challenge of detecting differences in acoustically homogeneous tissues
4Productivity
If targeted biopsy is performed based on visual inspection, then fewer biopsies are needed, but cancer detection accuracy decreases due to invisible cancers
Solution Approach 1:
The patent replaces the mechanical visual inspection process with an automated computational analysis system that processes high-frequency ultrasound images and computes indicator features. This substitution eliminates the limitations of human visual inspection, allowing for the detection of cancer patterns that are invisible to the naked eye while maintaining efficient targeted biopsy procedures
Data Source
Figure 1
Figure 2
Figure 3
AI summary
This invention provides a system and method for providing Indicator Features in high resolution micro-ultrasound prostate images, wherein the ultrasound device operates at a center frequency of 15 MHz and above. Indicator Features are features, which have been identified alone and/or in combination with other features in high resolution micro-ultrasound images, and have been determined to be significantly statistically correlated to either benign tissue or some grade of cancerous tissue on the basis of predictive probabilities. These Indicator Features can be used to train a linear or non-linear classifier, which can be used to classify patient images of the prostate. These Indicator Features can be used to guide a clinician as to where to take a biopsy core from the prostate, as well as assist in diagnosis of the tissue.