深度学习实现息肉匹配，准确率达 92%
Polyp Matching Using Deep Learning
医生标注的一万多对息肉图像训练出的 Siamese 网络，判断两图是否同一息肉能到 92% 准确率，做医疗影像的可以看看。
一项发表于 arXiv 的研究针对结肠胶囊内镜（CCE）中判断多张图像是否为同一息肉的难题，提出基于对比学习的 Siamese 神经网络方法。模型使用 ResNet18/34/50、DenseNet121 和 EfficientNet B0/B3 作为骨干网络，以余弦距离进行分类。训练数据来自丹麦 CareForColon2015 试验，包含 5,103 对同一息肉图像和 5,103 对不同息肉图像，由临床医生标注。实验中分类准确率最高达 92%，AUC 接近 0.98，有助于减少息肉重复计数和不必要的随访结肠镜检查。
Polyp Matching Using Deep Learning
A key challenge in colon capsule endoscopy (CCE) analysis is accurately identifying whether multiple images depict the same polyp, which is critical to avoid over-counting and unnecessary clinical interventions. Additionally, this prevents prolonged follow-up colonoscopies where endoscopists search for duplicate polyps without precise localization. This study presents a novel contrastive learning-based approach to polyp matching using a Siamese neural network architecture. The model was trained on a dataset from the Danish CareForColon2015 trial. The dataset comprises 5,103 image pairs of confirmed same polyp and 5,103 pairs of different polyps, annotated by experienced clinicians. The proposed model employs ResNet variants (ResNet18, ResNet34, ResNet50), DenseNet121 and EfficientNet B0/B3 as backbones and utilizes contrastive learning with cosine vector distance metric for classification. Experimental results demonstrate high classification accuracies of up to 92% and AUC values close to 0.98. These results suggest that automated polyp matching has the potential to reduce polyp over-counting, improve patient risk stratification, and reduce unnecessary follow-up colonoscopies.