Deep Learning Framework for Preoperative Recognition of Inverted Papilloma and Nasal Polyp

Abstract

Surgery is the most commonly used method of curing inverted papilloma (IP) or nasal polyp (NP). Although accurate preoperative recognition by computed tomography (CT) is a critical aspect of surgical planning, the minor CT imaging differences in such lesions may be a challenge. Therefore, we have devised a deep learning framework for automatic recognition of IP and NP in CT. The proposed framework involves two major steps: (a) use of a convolutional neural network (CNN) to preclassify lesions and (b) automatic IP/NP recognition. The preclassify CNN enables classification of CT slices according to anatomic structure. Separate networks are then implemented to differentiate IP and NP accordingly. Once the framework was trained using a CT dataset (5681 slices) from 136 patients, it outperformed other methods during evaluation, achieving 89.30% accuracy (area under the curve [AUC]=0.95) in classification. The proposed framework has clear potential as a clinical tool, enabling effective and highly accurate preoperative recognition of IP and NP.