Improving the cleaning quality of tube lumen instruments by imaging analysis and deep learning techniques.

Abstract

Objectives: The complex structure of tube lumen instruments (TLIs) makes them more difficult to clean compared to solid instruments. This study aims to improve the cleaning quality inspection of reusable TLIs, ensuring patient safety and clinical reliability.

Methods: This study improves the inspection of TLI cleaning quality using imaging analysis and deep learning techniques. Internally cleaned TLIs were imaged using an electronic endoscope by clinical staff, and the resulting images formed the original dataset. To enhance the quality of the TLI images and augment the dataset, image preprocessing techniques such as enhancement, slicing, and threshold filtering were applied. Based on the sliced image dataset, baseline models with relatively better performance were selected by comparing the performance of multiple deep learning models in TLI image classification. To further improve the model's performance, two attention mechanisms were introduced to focus on important features.

Results: The optimized model outperforms the baseline model in both performance and stability. Specifically, the FA-ResNet18 model with the concurrent space and channel squeeze and excitation (scSE) attention mechanism performs the best, with accuracy, macro precision, macro recall and macro F2 metrics all exceeding 98.3 %.

Conclusions: This method can effectively reduce the risk of errors caused by subjective factors and visual fatigue in manual inspection.