Identification and Reduction of Fat Shadows in Obese Patients using Robotic Echocardiography
Tomoshige Hashimoto, Soma Tsukamoto, Yuuki Shida, Hiroyasu Iwata
AI summary
Problem
Subcutaneous fat and lung shadows severely degrade ultrasound image quality in obese patients, hindering accurate cardiac diagnosis and automated robotic examinations. Current clinical adjustments for probe pressure are subjective and lack quantitative, patient-specific optimization.
Approach
The study introduces a luminance-based algorithm to detect fat and lung shadows, paired with a robotic mechanism that calculates and applies optimal probe pressure directly from the patient's BMI to compress fat layers without discomfort.
Key results
- Fat and lung shadow detection F-measures of 92.7% and 96.8%
- Strong BMI-probe pressure correlation (r=0.83) for optimal valve visualization
- Increased number and spatial range of mitral valve detections
- Minimized patient pressure sensation while maintaining image clarity
Why it matters
This approach enables reliable, automated robotic echocardiography for obese populations, reducing diagnostic errors and operator dependency in a clinically challenging demographic.
Abstract
The present study proposes a method to identify fat and lung shadows and reduce fat shadows in obese patients to obtain clear ultrasound (US) images. The shadow identification method focuses on the difference between the luminance value of the shadow and the direction of image loss caused by the degree of reflection and absorption of US waves in fat and lungs, thereby registering the degree of image blurring caused by each shadow. The method for reducing fat shadows was based on preliminary experiments to derive the appropriate probe pressing pressure for the patient’s BMI, enabling the acquisition of US images with fewer fat shadows while relieving the patient from feeling pressure. Verification tests were conducted using the proposed method. With regard to the shadow identification method, it was possible to detect fat shadows and lung shadows with an accuracy of 92.7% and 96.8% of the F-measure, respectively. The introduction of the shadow reduction method increased the number and range of mitral valve detections. These results underline the usefulness of the proposed method.