Gunduz Emrah, Alçin Omer Faruk, Kizilay Ahmet, Yildirim Ismail Okan
Department of Otorhinolaryngology Head and Neck Surgery, Malatya Training and Research Hospital, Malatya, Turkey.
Department of Electric and Electronics Engineering Faculty of Engineering and Natural Sciences Malatya, Turgut Ozal University Malatya, Malatya, Turkey.
Eur Arch Otorhinolaryngol. 2022 Nov;279(11):5389-5399. doi: 10.1007/s00405-022-07455-y. Epub 2022 May 21.
To create a new artificial intelligence approach based on deep learning (DL) from multiparametric MRI in the differential diagnosis of common parotid tumors.
Parotid tumors were classified using the InceptionResNetV2 DL model and majority voting approach with MRI images of 123 patients. The study was conducted in three stages. At stage I, the classification of the control, pleomorphic adenoma, Warthin tumor and malignant tumor (MT) groups was examined, and two approaches in which MRI sequences were given in combined and non-combined forms were established. At stage II, the classification of the benign tumor, MT and control groups was made. At stage III, patients with a tumor in the parotid gland and those with a healthy parotid gland were classified.
A stage I, the accuracy value for classification in the non-combined and combined approaches was 86.43% and 92.86%, respectively. This value at stage II and stage III was found respectively as 92.14% and 99.29%.
The approach presented in this study classifies parotid tumors automatically and with high accuracy using DL models.
基于深度学习（DL）创建一种新的人工智能方法，用于多参数磁共振成像在腮腺常见肿瘤鉴别诊断中的应用。
使用InceptionResNetV2 DL模型和多数投票方法，对123例患者的磁共振成像图像进行腮腺肿瘤分类。该研究分三个阶段进行。在第一阶段，检查对照组、多形性腺瘤、沃辛瘤和恶性肿瘤（MT）组的分类，并建立磁共振序列以组合和非组合形式给出的两种方法。在第二阶段，对良性肿瘤、MT和对照组进行分类。在第三阶段，对腮腺有肿瘤的患者和腮腺健康的患者进行分类。
在第一阶段，非组合和组合方法分类的准确率分别为86.43%和92.86%。在第二阶段和第三阶段，该值分别为92.14%和99.29%。
本研究提出的方法使用DL模型对腮腺肿瘤进行自动且高精度的分类。
