Investigation on continual training of computer-aided diagnosis systems by semi-supervised learning
Investigation on continual training of computer-aided diagnosis systems by semi-supervised learning
复制标题
DOI：
10.1145/3524086.3524095
复制
发表时间：
2022-03
期刊：
影响因子：
--
通讯作者：
Chisako Muramamatsu;M. Nishio;M. Oiwa;M. Yakami;Takeshi Kubo;H. Fujita
中科院分区：
文献类型：
--
作者：
Chisako Muramamatsu;M. Nishio;M. Oiwa;M. Yakami;Takeshi Kubo;H. Fujita
医学图像分析系统可以帮助放射科医师准确、迅速地阅读图像。预计该系统对不同供应商和不同设施的任何成像系统获得的图像都具有鲁棒性。然而，由于疾病的流行和难以收集具有各种特征的样本，该系统可能无法很好地适用于所有图像。人工智能驱动的系统有望从经验中学习并不断改进。在这项研究中，我们研究了使用本地样本进行持续训练是否可以使用乳腺X射线摄影和肺部CT数据库提高系统性能。比较了使用未标记数据的不同训练策略。
Medical image analysis systems can help radiologists in reading images accurately and promptly. The systems are expected to be robust to images obtained with any imaging systems by different vendors and at different facilities. However, because of the prevalence of diseases and difficulty of collecting samples with various characteristics, the systems may not apply well to all the images. Artificial intelligence-powered systems are expected to learn from experience and be improved continuously. In this study, we investigated whether continual training with local samples can improve system performance using mammography and lung CT databases. Different training strategies using unlabeled data are compared.