Detecting tympanostomy tubes from otoscopic images via offline and online training

• A new system is developed to detect tympanostomy tubes in otoscopic images.
• Image features are derived to reflect the characteristics of tympanostomy tubes.
• A 3-layer cascaded classifier is trained in an offline training process.
• A real-time refinement process is designed to improve the classifier at the point of patient care.
• The proposed system achieves high detection accuracy in an empirical study.

Tympanostomy tube placement has been commonly used nowadays as a surgical treatment for otitis media. Following the placement, regular scheduled follow-ups for checking the status of the tympanostomy tubes are important during the treatment. The complexity of performing the follow up care mainly lies on identifying the presence and patency of the tympanostomy tube. An automated tube detection program will largely reduce the care costs and enhance the clinical efficiency of the ear nose and throat specialists and general practitioners. In this paper, we develop a computer vision system that is able to automatically detect a tympanostomy tube in an otoscopic image of the ear drum. The system comprises an offline classifier training process followed by a real-time refinement stage performed at the point of care. The offline training process constructs a three-layer cascaded classifier with each layer reflecting specific characteristics of the tube. The real-time refinement process enables the end users to interact and adjust the system over time based on their otoscopic images and patient care. The support vector machine (SVM) algorithm has been applied to train all of the classifiers. Empirical evaluation of the proposed system on both high quality hospital images and low quality internet images demonstrates the effectiveness of the system. The offline classifier trained using 215 images could achieve a 90% accuracy in terms of classifying otoscopic images with and without a tympanostomy tube, and then the real-time refinement process could improve the classification accuracy by 3–5% based on additional 20 images.

Figure optionsDownload high-quality image (243 K)Download as PowerPoint slide