Department of Otolaryngology, Samsung Changwon Hospital, Sungkyunkwan University School of Medicine, Changwon, Korea.
Department of Biomedical Informatics, College of Medicine, Konyang University, Daejeon, Korea.
PLoS One. 2024 Mar 13;19(3):e0297536. doi: 10.1371/journal.pone.0297536. eCollection 2024.
Nasal endoscopy is routinely performed to distinguish the pathological types of masses. There is a lack of studies on deep learning algorithms for discriminating a wide range of endoscopic nasal cavity mass lesions. Therefore, we aimed to develop an endoscopic-examination-based deep learning model to detect and classify nasal cavity mass lesions, including nasal polyps (NPs), benign tumors, and malignant tumors. The clinical feasibility of the model was evaluated by comparing the results to those of manual assessment. Biopsy-confirmed nasal endoscopic images were obtained from 17 hospitals in South Korea. Here, 400 images were used for the test set. The training and validation datasets consisted of 149,043 normal nasal cavity, 311,043 NP, 9,271 benign tumor, and 5,323 malignant tumor lesion images. The proposed Xception architecture achieved an overall accuracy of 0.792 with the following class accuracies on the test set: normal = 0.978 ± 0.016, NP = 0.790 ± 0.016, benign = 0.708 ± 0.100, and malignant = 0.698 ± 0.116. With an average area under the receiver operating characteristic curve (AUC) of 0.947, the AUC values and F1 score were highest in the order of normal, NP, malignant tumor, and benign tumor classes. The classification performances of the proposed model were comparable with those of manual assessment in the normal and NP classes. The proposed model outperformed manual assessment in the benign and malignant tumor classes (sensitivities of 0.708 ± 0.100 vs. 0.549 ± 0.172, 0.698 ± 0.116 vs. 0.518 ± 0.153, respectively). In urgent (malignant) versus nonurgent binary predictions, the deep learning model achieved superior diagnostic accuracy. The developed model based on endoscopic images achieved satisfactory performance in classifying four classes of nasal cavity mass lesions, namely normal, NP, benign tumor, and malignant tumor. The developed model can therefore be used to screen nasal cavity lesions accurately and rapidly.
鼻内窥镜检查通常用于区分肿块的病理类型。目前缺乏用于鉴别广泛的鼻腔内窥镜肿块病变的深度学习算法的研究。因此，我们旨在开发一种基于内窥镜检查的深度学习模型，以检测和分类鼻腔肿块病变，包括鼻息肉（NPs）、良性肿瘤和恶性肿瘤。通过将模型的结果与手动评估的结果进行比较，评估了该模型的临床可行性。从韩国的 17 家医院获得了经活检证实的鼻内窥镜图像。这里，400 张图像被用于测试集。训练和验证数据集由 149043 张正常鼻腔、311043 张 NP、9271 张良性肿瘤和 5323 张恶性肿瘤病变图像组成。所提出的 Xception 架构在测试集上的总体准确率为 0.792，以下是测试集的类别准确率：正常=0.978±0.016，NP=0.790±0.016，良性=0.708±0.100，恶性=0.698±0.116。平均受试者工作特征曲线下面积（AUC）为 0.947，正常、NP、恶性肿瘤和良性肿瘤类别的 AUC 值和 F1 分数最高。在正常和 NP 类中，与手动评估相比，所提出模型的分类性能相当。在所提出的模型中，良性和恶性肿瘤类别的性能优于手动评估（敏感性分别为 0.708±0.100 对 0.549±0.172，0.698±0.116 对 0.518±0.153）。在紧急（恶性）与非紧急的二元预测中，深度学习模型实现了卓越的诊断准确性。基于内窥镜图像开发的模型在分类正常、NP、良性肿瘤和恶性肿瘤这四类鼻腔肿块病变方面取得了令人满意的性能。因此，该模型可以用于准确、快速地筛查鼻腔病变。
