Abstract
The possibility of high-precision and rapid detection of pathologies on chest X-rays makes it possible to detect the development of pneumonia at an early stage and begin immediate treatment. Artificial intelligence can speed up and qualitatively improve the procedure of X-ray analysis and give recommendations to the doctor for additional consideration of suspicious images. The purpose of this study is to determine the best models and implementations of the transfer learning method in the binary classification problem in the presence of a small amount of training data. In this article, various methods of augmentation of the initial data and approaches to training ResNet and DenseNet models for black-and-white X-ray images are considered, those approaches that contribute to obtaining the highest results of the accuracy of determining cases of pneumonia and norm at the testing stage are identified.
Abstract (translated)
在高分辨率和快速检测 chest X-ray 中的常见病理的情况下,有可能早期检测出肺炎并立即开始治疗。人工智能可以加速和优化 X-ray 分析的过程,并建议医生对可疑图像进行额外的考虑。本文旨在确定在少量训练数据的情况下,在二进制分类问题中最佳的模型和实现,以及用于训练 ResNet 和 DenseNet 模型的增强方法。本文考虑了各种增加初始数据的方法和训练黑白 X-ray 图像的 ResNet 和 DenseNet 模型的方法。这些方法有助于在测试阶段获得最高的确定肺炎病例和标准的准确率。
URL
https://arxiv.org/abs/2303.10601
