Tang Chia-Pei, Chang Hong-Yi, Wang Wei-Chun, Hu Wei-Xuan
Division of Gastroenterology, Department of Internal Medicine, Dalin Tzu Chi Hospital, Buddhist Tzu Chi Medical Foundation, Chiayi 622401, Taiwan.
School of Medicine, Tzu Chi University, Hualien City 970374, Taiwan.
Diagnostics (Basel). 2023 Jan 4;13(2):170. doi: 10.3390/diagnostics13020170.
Using a deep learning algorithm in the development of a computer-aided system for colon polyp detection is effective in reducing the miss rate. This study aimed to develop a system for colon polyp detection and classification. We used a data augmentation technique and conditional GAN to generate polyp images for YOLO training to improve the polyp detection ability. After testing the model five times, a model with 300 GANs (GAN 300) achieved the highest average precision (AP) of 54.60% for SSA and 75.41% for TA. These results were better than those of the data augmentation method, which showed AP of 53.56% for SSA and 72.55% for TA. The AP, mAP, and IoU for the 300 GAN model for the HP were 80.97%, 70.07%, and 57.24%, and the data increased in comparison with the data augmentation technique by 76.98%, 67.70%, and 55.26%, respectively. We also used Gaussian blurring to simulate the blurred images during colonoscopy and then applied DeblurGAN-v2 to deblur the images. Further, we trained the dataset using YOLO to classify polyps. After using DeblurGAN-v2, the mAP increased from 25.64% to 30.74%. This method effectively improved the accuracy of polyp detection and classification.
在开发用于结肠息肉检测的计算机辅助系统中使用深度学习算法可有效降低漏检率。本研究旨在开发一种用于结肠息肉检测和分类的系统。我们使用数据增强技术和条件生成对抗网络（conditional GAN）来生成用于YOLO训练的息肉图像，以提高息肉检测能力。对模型进行五次测试后，具有300个生成对抗网络的模型（GAN 300）在锯齿状腺瘤（SSA）方面达到了最高平均精度（AP），为54.60%，在管状腺瘤（TA）方面为75.41%。这些结果优于数据增强方法，数据增强方法在SSA方面的AP为53.56%，在TA方面为72.55%。300个生成对抗网络模型对增生性息肉（HP）的AP、平均平均精度（mAP）和交并比（IoU）分别为80.97%、70.07%和57.24%，与数据增强技术相比，数据分别增加了76.98%、67.70%和55.26%。我们还使用高斯模糊来模拟结肠镜检查期间的模糊图像，然后应用DeblurGAN-v2对图像进行去模糊。此外，我们使用YOLO对数据集进行训练以对息肉进行分类。使用DeblurGAN-v2后，mAP从25.64%提高到了30.74%。该方法有效提高了息肉检测和分类的准确性。
