Depth-Sensing-Based Algorithm for Chest Morphology Assessment in Children with Cerebral Palsy.

Area of Science:

• Biomedical Engineering
• Rehabilitation Science
• Medical Imaging

Background:

• Assessing chest morphology changes is crucial for physical therapy effectiveness.
• Breathing causes periodic morphological variations, complicating accurate measurements.
• Existing methods may lack the precision to capture subtle chest changes.

Purpose of the Study:

• To introduce a depth-sensing approach for tracking relative morphological changes in patients' chests.
• To develop robust algorithms for analyzing chest morphology during physical therapy.
• To validate the reliability and reproducibility of the proposed measurement technique.

Main Methods:

• Utilized depth-sensing technology for continuous chest recording.
• Extracted morphological parameters from transverse cross-sections (CSs) at maximal and minimal chest volumes (inspiration/expiration).
• Assessed measurement reliability using the coefficient of variation (CV) and reproducibility through two-session recordings.

Main Results:

• Mean CV for CS depth values was <2%; mean CV for CS area was <1%, indicating high reliability.
• Statistical analysis confirmed no significant difference between two measurement sessions, supporting reproducibility.
• The algorithm successfully evaluated chest mobility during quiet breathing, showing consistent results across sessions.

Conclusions:

• The proposed depth-sensing algorithm is a reliable and reproducible tool for monitoring chest morphology.
• This method can effectively evaluate the impact of physical therapy and rehabilitation exercises on chest changes.
• The findings support the clinical utility of this approach in patient monitoring and treatment assessment.