Related Experiment Video
Updated: Dec 30, 2025

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
Published on: April 13, 2013
Pressure injury image analysis with machine learning techniques: A systematic review on previous and possible future
Sofia Zahia1, Maria Begoña Garcia Zapirain2, Xavier Sevillano3
1eVida Research Laboratory, University of Deusto, Bilbao 48007, Spain; Department of Computer Engineering and Computer Science, Duthie Center for Engineering, University of Louisville, Louisville, KY 40292, USA.
Accurate diagnosis of pressure injuries is crucial for effective treatment, especially in elderly and disabled populations. This survey highlights non-invasive imaging techniques and Deep Learning
Area of Science:
- Medical Imaging
- Wound Care Technology
- Artificial Intelligence in Healthcare
Background:
- Pressure injuries pose a significant global healthcare challenge, disproportionately affecting the elderly and disabled.
- Accurate diagnosis and monitoring of pressure injuries are essential for effective treatment and patient outcomes.
- Traditional invasive methods for wound assessment carry risks of pain and infection, necessitating safer alternatives.
Purpose of the Study:
- To provide an overview of non-invasive imaging techniques for pressure injury analysis and monitoring.
- To evaluate the efficiency of Deep Learning (DL) in improving pressure injury diagnosis and healing assessment.
- To synthesize findings from 114 analyzed research papers on pressure injuries, chronic wounds, and skin lesions.
Main Methods:
- Systematic review of 114 research papers from 8 databases.
- Analysis of non-invasive imaging techniques for wound segmentation, tissue classification, and metric calculation (diameter, area, volume).
- Evaluation of Deep Learning models for pressure injury assessment and healing monitoring.
Main Results:
- Non-invasive imaging offers a safe and effective alternative to invasive methods for monitoring wound healing.
- Deep Learning models demonstrate superior performance in analyzing pressure injury characteristics compared to traditional methods.
- Imaging systems incorporating wound segmentation, tissue classification, and metric analysis are key for comprehensive evaluation.
Conclusions:
- Non-invasive imaging techniques, particularly when enhanced by Deep Learning, offer a promising approach for the accurate diagnosis and monitoring of pressure injuries.
- Deep Learning significantly improves the analysis of wound characteristics and healing progress, outperforming previous methods.
- This survey underscores the potential of advanced imaging and AI to revolutionize pressure injury care.
More Related Videos
06:28Biomechanical Changes Related to Low Back Pain: An Innovative Tool for Movement Pattern Assessment and Treatment Evaluation in Rehabilitation
Published on: December 13, 2024
04:09Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
Published on: October 10, 2018