ETU-Net: efficient Transformer and convolutional U-style connected attention segmentation network applied to endoscopic image of epistaxis

Abstract

Epistaxis is a typical presentation in the otolaryngology and emergency department. When compressive therapy fails, directive nasal cautery is necessary, which strongly recommended operating under the nasal endoscope if it is possible. Limited by the operator's clinical experience, complications such as recurrence, nasal ulcer, and septum perforation may occur due to insufficient or excessive cautery. At present, deep learning technology is widely used in the medical field because of its accurate and efficient recognition ability, but it is still blank in the research of epistaxis. In this work, we first gathered and retrieved the Nasal Bleeding dataset, which was annotated and confirmed by many clinical specialists, filling a void in this sector. Second, we created ETU-Net, a deep learning model that smartly integrated the excellent performance of attention convolution with Transformer, overcoming the traditional model's difficulties in capturing contextual feature information and insufficient sequence modeling skills in picture segmentation. On the Nasal Bleeding dataset, our proposed model outperforms all others models that we tested. The segmentation recognition index, Intersection over Union, and F1-Score were 94.57 and 97.15%. Ultimately, we summarized effective ways of combining artificial intelligence with medical treatment and tested it on multiple general datasets to prove its feasibility. The results show that our method has good domain adaptability and has a cutting-edge reference for future medical technology development.