You Zhenzhen, Han Botao, Shi Zhenghao, Du Shuangli, Zhao Minghua, Lv Zhiyong, Hei Xinhong, Liu Haiqin, Ren Xiaoyong, Yan Yan
Shaanxi Key Laboratory for Network Computing and Security Technology, School of Computer Science and Engineering, Xi'an University of Technology, Xi'an, China.
Department of Otolaryngology, Second Affiliated Hospital of Medical College, Xi'an Jiaotong University, Xi'an, China.
Head Neck. 2025 Sep;47(9):2584-2593. doi: 10.1002/hed.28157. Epub 2025 Apr 27.
Laryngeal cancer is the second most common upper respiratory tract cancer. Early and accurate diagnosis can improve the cure rate of patients. Laryngoscopy with NBI is a commonly used tool that can help endoscopists diagnose laryngeal diseases. However, the fine classification of laryngeal leukoplakia using NBI images is challenging for computer-aided diagnosis.
In this article, we propose a single-view contrastive learning network to locate lesion regions, construct sample pairs for contrastive learning, and provide pseudo-labels to unlabeled data in order to achieve fine classification under small samples. Firstly, we pretrain the backbone network using the original NBI images. Secondly, in order to augment the number of samples for contrastive learning, we design different patch generation methods based on an attention-guided network. The original NBI images are cropped into small patches for the purpose of generating lesion-related regions and complementary samples. The pseudo-labels of these small patches are obtained by applying the pre-trained backbone network. Finally, we combine the contrastive loss function and the cross-entropy loss function for jointly training the backbone network and contrastive learning network. Our NBI dataset is classified into six categories: normal tissue, inflammatory keratosis, mild dysplasia, moderate dysplasia, severe dysplasia, and squamous cell carcinoma.
Experimental results demonstrate that our model achieves an accuracy of 96.12%, which is higher than the current mainstream models. Our model also achieves high specificity and sensitivity. The code is available at https://github.com/hans-bbt/single-view-contrastive-learning.
喉癌是上呼吸道第二常见的癌症。早期准确诊断可提高患者治愈率。窄带成像（NBI）喉镜检查是一种常用工具，可帮助内镜医师诊断喉部疾病。然而，利用NBI图像对喉白斑进行精细分类对计算机辅助诊断来说具有挑战性。
在本文中，我们提出一种单视图对比学习网络，用于定位病变区域，构建用于对比学习的样本对，并为未标记数据提供伪标签，以便在小样本情况下实现精细分类。首先，我们使用原始NBI图像对骨干网络进行预训练。其次，为了增加用于对比学习的样本数量，我们基于注意力引导网络设计不同的补丁生成方法。将原始NBI图像裁剪成小补丁，以生成与病变相关的区域和补充样本。通过应用预训练的骨干网络获得这些小补丁的伪标签。最后，我们将对比损失函数和交叉熵损失函数相结合，用于联合训练骨干网络和对比学习网络。我们的NBI数据集分为六类：正常组织、炎性角化病、轻度发育异常、中度发育异常、重度发育异常和鳞状细胞癌。
实验结果表明，我们的模型准确率达到96.12%，高于当前主流模型。我们的模型还具有较高的特异性和敏感性。代码可在https://github.com/hans-bbt/single-view-contrastive-learning获取。
