MIB-ANet: A novel multi-scale deep network for nasal endoscopy-based adenoid hypertrophy grading

• Published in: Frontiers in medicine Vol. 10; p. 1142261
• Main Authors: Bi, Mingmin, Zheng, Siting, Li, Xuechen, Liu, Haiyan, Feng, Xiaoshan, Fan, Yunping, Shen, Linlin
• Format: Journal Article
• Language: English
• Published: Switzerland Frontiers Media S.A 14-04-2023
• Subjects: adenoid hypertrophy; convolutional neural networks; deep learning; medical image classification; Medicine; nasal endoscopy; deep learning; convolutional neural networks; medical image classification; nasal endoscopy; adenoid hypertrophy
• ISSN: 2296-858X; 2296-858X
• DOI: 10.3389/fmed.2023.1142261

To develop a novel deep learning model to automatically grade adenoid hypertrophy, based on nasal endoscopy, and asses its performance with that of E.N.T. clinicians.
A total of 3,179 nasoendoscopic images, including 4-grade adenoid hypertrophy (Parikh grading standard, 2006), were collected to develop and test deep neural networks. MIB-ANet, a novel multi-scale grading network, was created for adenoid hypertrophy grading. A comparison between MIB-ANet and E.N.T. clinicians was conducted.
In the SYSU-SZU-EA Dataset, the MIB-ANet achieved 0.76251 F1 score and 0.76807 accuracy, and showed the best classification performance among all of the networks. The visualized heatmaps show that MIB-ANet can detect whether adenoid contact with adjacent tissues, which was interpretable for clinical decision. MIB-ANet achieved at least 6.38% higher F1 score and 4.31% higher accuracy than the junior E.N.T. clinician, with much higher (80× faster) diagnosing speed.
The novel multi-scale grading network MIB-ANet, designed for adenoid hypertrophy, achieved better classification performance than four classical CNNs and the junior E.N.T. clinician. Nonetheless, further studies are required to improve the accuracy of MIB-ANet.