PDF(Pubmed)
Abstract：
BACKGROUND: Nasal polyps and inverted papillomas often look similar. Clinically, it is difficult to distinguish the masses by endoscopic examination. Therefore, in this study, we aimed to develop a deep learning algorithm for computer-aided diagnosis of nasal endoscopic images, which may provide a more accurate clinical diagnosis before pathologic confirmation of the nasal masses.
METHODS: By performing deep learning of nasal endoscope images, we evaluated our computer-aided diagnosis system\'s assessment ability for nasal polyps and inverted papilloma and the feasibility of their clinical application. We used curriculum learning pre-trained with patches of nasal endoscopic images and full-sized images. The proposed model\'s performance for classifying nasal polyps, inverted papilloma, and normal tissue was analyzed using five-fold cross-validation.
RESULTS: The normal scores for our best-performing network were 0.9520 for recall, 0.7900 for precision, 0.8648 for F1-score, 0.97 for the area under the curve, and 0.8273 for accuracy. For nasal polyps, the best performance was 0.8162, 0.8496, 0.8409, 0.89, and 0.8273, respectively, for recall, precision, F1-score, area under the curve, and accuracy. Finally, for inverted papilloma, the best performance was obtained for recall, precision, F1-score, area under the curve, and accuracy values of 0.5172, 0.8125, 0.6122, 0.83, and 0.8273, respectively.
CONCLUSIONS: Although there were some misclassifications, the results of gradient-weighted class activation mapping were generally consistent with the areas under the curve determined by otolaryngologists. These results suggest that the convolutional neural network is highly reliable in resolving lesion locations in nasal endoscopic images.
METHODS: By performing deep learning of nasal endoscope images, we evaluated our computer-aided diagnosis system\'s assessment ability for nasal polyps and inverted papilloma and the feasibility of their clinical application. We used curriculum learning pre-trained with patches of nasal endoscopic images and full-sized images. The proposed model\'s performance for classifying nasal polyps, inverted papilloma, and normal tissue was analyzed using five-fold cross-validation.
RESULTS: The normal scores for our best-performing network were 0.9520 for recall, 0.7900 for precision, 0.8648 for F1-score, 0.97 for the area under the curve, and 0.8273 for accuracy. For nasal polyps, the best performance was 0.8162, 0.8496, 0.8409, 0.89, and 0.8273, respectively, for recall, precision, F1-score, area under the curve, and accuracy. Finally, for inverted papilloma, the best performance was obtained for recall, precision, F1-score, area under the curve, and accuracy values of 0.5172, 0.8125, 0.6122, 0.83, and 0.8273, respectively.
CONCLUSIONS: Although there were some misclassifications, the results of gradient-weighted class activation mapping were generally consistent with the areas under the curve determined by otolaryngologists. These results suggest that the convolutional neural network is highly reliable in resolving lesion locations in nasal endoscopic images.
摘要：
背景：鼻息肉和内翻性乳头状瘤通常看起来相似。临床上,通过内窥镜检查很难区分肿块。因此,在这项研究中，我们旨在开发一种用于计算机辅助诊断鼻内窥镜图像的深度学习算法，这可以在鼻部肿块的病理确认之前提供更准确的临床诊断。
方法：通过对鼻内窥镜图像进行深度学习，我们评估了计算机辅助诊断系统对鼻息肉和内翻性乳头状瘤的评估能力及其临床应用的可行性。我们使用经鼻内窥镜图像和全尺寸图像的补丁预先训练的课程学习。所提出的模型对鼻息肉进行分类的性能，内翻性乳头状瘤,和正常组织使用5倍交叉验证进行分析。
结果：我们表现最好的网络的正常评分为0.9520，0.7900的精度，F1分数为0.8648，曲线下面积为0.97，和0.8273的准确性。对于鼻息肉，最佳性能分别为0.8162、0.8496、0.8409、0.89和0.8273，为了召回，精度,F1分数，曲线下的面积,和准确性。最后,对于内翻性乳头状瘤,召回获得了最好的表现，精度,F1分数，曲线下的面积,和精度值分别为0.5172、0.8125、0.6122、0.83和0.8273。
结论：尽管存在一些错误分类，梯度加权类别激活图谱的结果与耳鼻喉科医师测定的曲线下面积基本一致.这些结果表明，卷积神经网络在解决鼻内窥镜图像中的病变位置方面非常可靠。
方法：通过对鼻内窥镜图像进行深度学习，我们评估了计算机辅助诊断系统对鼻息肉和内翻性乳头状瘤的评估能力及其临床应用的可行性。我们使用经鼻内窥镜图像和全尺寸图像的补丁预先训练的课程学习。所提出的模型对鼻息肉进行分类的性能，内翻性乳头状瘤,和正常组织使用5倍交叉验证进行分析。
结果：我们表现最好的网络的正常评分为0.9520，0.7900的精度，F1分数为0.8648，曲线下面积为0.97，和0.8273的准确性。对于鼻息肉，最佳性能分别为0.8162、0.8496、0.8409、0.89和0.8273，为了召回，精度,F1分数，曲线下的面积,和准确性。最后,对于内翻性乳头状瘤,召回获得了最好的表现，精度,F1分数，曲线下的面积,和精度值分别为0.5172、0.8125、0.6122、0.83和0.8273。
结论：尽管存在一些错误分类，梯度加权类别激活图谱的结果与耳鼻喉科医师测定的曲线下面积基本一致.这些结果表明，卷积神经网络在解决鼻内窥镜图像中的病变位置方面非常可靠。
