Ultrasound Tissue Damage Estimation via Deep Neural Network Biotrace Maps
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current ultrasound image-guided systems face challenges in deriving real-time tissue damage estimations during thermal ablation due to dynamic gas bubble generation, patient characteristics like fat, and tumor location near shadowing elements such as ribs, making it difficult to obtain accurate acoustic images.
Innovation Solution
An ultrasound module configured with a deep neural network (DNN) to process B-mode ultrasound images, generating a biotrace map (BTM) for real-time tissue damage assessment by segmenting tissue damage in received images.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of time
If real-time tissue damage estimation is attempted during thermal ablation, then immediate feedback for procedure optimization is achieved, but image quality deteriorates due to dynamic gas bubble generation and shadowing elements
Solution Approach 1:
The system performs preliminary registration of ultrasound images before ablation begins, establishing a reference framework that accounts for patient anatomy and potential shadowing elements. This pre-processing enables the DNN to focus on detecting tissue damage changes relative to the pre-established baseline, improving real-time assessment accuracy despite image quality degradation from gas bubbles
Solution Approach 2:
The deep neural network acts as an intermediary that processes degraded ultrasound images during ablation, extracting tissue damage information even when image quality is compromised by gas bubbles and shadowing. The DNN learns to filter out artifacts and identify genuine tissue damage signals from noisy inputs
2Measurement precision
If traditional post-ablation imaging is used for tissue damage assessment, then accurate damage evaluation is achieved, but additional imaging procedures and time are required
Solution Approach 1:
The ultrasound-guided thermal ablation system performs self-assessment by using its own ultrasound imaging capability to evaluate tissue damage during and immediately after ablation. The integrated DNN processes the ultrasound images to provide damage assessment without requiring separate post-ablation imaging procedures, making the system self-sufficient for both treatment and evaluation
Solution Approach 2:
The system replaces traditional post-ablation imaging methods (such as CT or MRI scans) with ultrasound-based assessment enhanced by deep neural network analysis. This substitution eliminates the need for additional imaging equipment and procedures, providing accurate damage evaluation using only the ultrasound system already present during ablation
Data Source
AI summary
Ultrasound (US) modules and methods in US image-guided systems for thermal ablation are provided, which utilize regular two-dimensional (2D) B mode US images to evaluate in real-time the damage achieved by the thermal ablation, including the prediction of tissue damage immediately after completion of the thermal ablation procedure, as well as the expected damage after 24 hours. Three-dimensional (3D) biotrace map (BTM) representation(s) may be constructed from the received US images by applying deep neural networks (DNN) to segment tissue damage in US frames, and present the damage to the user in 3D and/or in virtual sections through the BTM representation(s). Using regular 2D US probes allows much flexibility in operating the US probe and imaging the target successfully, while the construction of the 3D BTM representation(s) enables accumulating, updating and analyzing the volume data to provide a full and updating representation of the ablation procedure.