Key Laboratory for Neuroinformation of Ministry of Education, University of Electronic Science and Technology of China, Chengdu, 610054, China.
School of Life Science and Technology, University of Electronic Science and Technology of China, Chengdu, 610054, China.
Int J Comput Assist Radiol Surg. 2022 Jul;17(7):1289-1302. doi: 10.1007/s11548-022-02651-x. Epub 2022 Jun 9.
As with several medical image analysis tasks based on deep learning, gastrointestinal image analysis is plagued with data scarcity, privacy concerns and an insufficient number of pathology samples. This study examines the generation and utility of synthetic samples of colonoscopy images with polyps for data augmentation.
We modify and train a pix2pix model to generate synthetic colonoscopy samples with polyps to augment the original dataset. Subsequently, we create a variety of datasets by varying the quantity of synthetic samples and traditional augmentation samples, to train a U-Net network and Faster R-CNN model for segmentation and detection of polyps, respectively. We compare the performance of the models when trained with the resulting datasets in terms of F score, intersection over union, precision and recall. Further, we compare the performances of the models with unseen polyp datasets to assess their generalization ability.
The average F coefficient and intersection over union are improved with increasing number of synthetic samples in U-Net over all test datasets. The performance of the Faster R-CNN model is also improved in terms of polyp detection, while decreasing the false-negative rate. Further, the experimental results for polyp detection outperform similar studies in the literature on the ETIS-PolypLaribDB dataset.
By varying the quantity of synthetic and traditional augmentation, there is the potential to control the sensitivity of deep learning models in polyp segmentation and detection. Further, GAN-based augmentation is a viable option for improving the performance of models for polyp segmentation and detection.
与基于深度学习的几项医学图像分析任务一样，胃肠道图像分析受到数据匮乏、隐私问题和病理学样本数量不足的困扰。本研究探讨了生成和利用具有息肉的结肠镜图像的合成样本进行数据扩充的问题。
我们修改并训练了一个 pix2pix 模型，以生成具有息肉的合成结肠镜样本，从而扩充原始数据集。随后，我们通过改变合成样本和传统扩充样本的数量来创建各种数据集，以分别训练 U-Net 网络和 Faster R-CNN 模型来分割和检测息肉。我们比较了在使用所得数据集训练后的模型的性能，包括 F 分数、交并比、精度和召回率。此外，我们还比较了模型在未见过的息肉数据集上的性能，以评估其泛化能力。
在所有测试数据集上，U-Net 中随着合成样本数量的增加，平均 F 系数和交并比都有所提高。Faster R-CNN 模型在检测息肉方面的性能也得到了提高，同时降低了假阴性率。此外，在 ETIS-PolypLaribDB 数据集上，与文献中的类似研究相比，息肉检测的实验结果表现更好。
通过改变合成和传统扩充的数量，有可能控制深度学习模型在息肉分割和检测中的敏感性。此外，基于 GAN 的扩充是提高息肉分割和检测模型性能的可行选择。
