Real-time Monitoring of Urinary Stone Status During Shockwave Lithotripsy.

Area of Science:

• Medical Imaging
• Urology
• Artificial Intelligence

Background:

• Shockwave lithotripsy (SWL) is a common procedure for treating kidney stones.
• Real-time monitoring of stone fragmentation during SWL is crucial for optimizing treatment efficacy and patient safety.
• Current methods for assessing stone fragmentation during SWL can be subjective and lack real-time feedback.

Purpose of the Study:

• To develop a standardized, real-time feedback system for monitoring urinary stone fragmentation during SWL.
• To optimize SWL treatment efficacy and minimize patient risk through objective, real-time assessment.
• To provide actionable insights for clinicians during SWL procedures.

Main Methods:

• A two-pronged approach was used to quantify stone fragmentation in C-arm X-ray images.
• Stone area loss was measured by comparing pre-treatment images with subsequent images.
• A Convolutional Neural Network (CNN) was trained to estimate the probability of an image containing a urinary stone.

Main Results:

• The developed system integrates stone area loss and CNN output for real-time assessment of stone fragmentation.
• Utilizing data from 522 SWL treatments and 4057 images, the system demonstrated consistent real-time feedback capabilities.
• The system provides actionable feedback to guide SWL in various clinical scenarios.

Conclusions:

• The proposed system offers a novel and reliable method for monitoring urinary stone fragmentation during SWL.
• It aids in balancing treatment efficacy with patient safety.
• The system shows promise for semi-automated SWL platforms, especially in resource-limited settings and for extended space missions.