Published online Dec 28, 2024. doi: 10.3748/wjg.v30.i48.5111
Revised: September 8, 2024
Accepted: October 8, 2024
Published online: December 28, 2024
Processing time: 179 Days and 21 Hours
Wireless capsule endoscopy (WCE) has become an important noninvasive and portable tool for diagnosing digestive tract diseases and has been propelled by advancements in medical imaging technology. However, the complexity of the digestive tract structure, and the diversity of lesion types, results in different sites and types of lesions distinctly appearing in the images, posing a challenge for the accurate identification of digestive tract diseases.
To propose a deep learning-based lesion detection model to automatically identify and accurately label digestive tract lesions, thereby improving the diagnostic efficiency of doctors, and creating significant clinical application value.
In this paper, we propose a neural network model, WCE_Detection, for the accurate detection and classification of 23 classes of digestive tract lesion images. First, since multicategory lesion images exhibit various shapes and scales, a multidetection head strategy is adopted in the object detection network to increase the model's robustness for multiscale lesion detection. Moreover, a bidirectional feature pyramid network (BiFPN) is introduced, which effectively fuses shallow semantic features by adding skip connections, significantly reducing the detection error rate. On the basis of the above, we utilize the Swin Transformer with its unique self-attention mechanism and hierarchical structure in conjunction with the BiFPN feature fusion technique to enhance the feature representation of multicategory lesion images.
The model constructed in this study achieved an mAP50 of 91.5% for detecting 23 lesions. More than eleven single-category lesions achieved an mAP50 of over 99.4%, and more than twenty lesions had an mAP50 value of over 80%. These results indicate that the model outperforms other state-of-the-art models in the end-to-end integrated detection of human digestive tract lesion images.
The deep learning-based object detection network detects multiple digestive tract lesions in WCE images with high accuracy, improving the diagnostic efficiency of doctors, and demonstrating significant clinical application value.
Core Tip: In clinical practice, wireless capsule endoscopy is commonly used to detect lesions in the digestive tract and search for their causes. Here, we propose a multilesion classification and detection model to automatically identify 23 types of lesions in the digestive tract, and accurately mark the lesions. The model can improve the diagnostic efficiency of doctors and their ability to identify the categories of digestive tract lesions.