Distributed deep learning across multisite datasets for generalized CT hemorrhage segmentation
Distributed deep learning across multisite datasets for generalized CT hemorrhage segmentation
复制标题
DOI：
10.1002/mp.13880
复制
发表时间：
2019-11-19
期刊：
影响因子：
3.8
通讯作者：
Pham, Dzung L.
中科院分区：
文献类型：
--
作者：
Remedios, Samuel W.;Roy, Snehashis;Pham, Dzung L.
随着深度神经网络在广泛的计算机视觉领域取得越来越多的成功，人们越来越重视这些模型的推广，以用于生产部署。对于足够大的训练数据集，模型通常可以避免过度拟合其数据;然而，对于医学成像，通常难以从单个站点获得足够的数据。由于安全措施和研究合规性限制，机构之间的数据共享也经常不可行或被禁止，以保护受保护的健康信息（PHI）和患者匿名。方法在本文中，我们实现了循环的重量转移与独立的数据集从多个地理上不同的网站，而不损害PHI。我们比较了单站点学习（SSL）和多站点学习（MSL）模型在每个培训站点以及其他两个机构的测试数据上的结果。结果MSL模型在holdout机构数据集上的平均骰子相似系数（DSC）为0.690，体积相关性为0.914，分别比SSL模型的平均DSC为0.646和平均相关性为0.871提高了7%和5%。结论我们表明，神经网络可以有效地训练来自两个物理远程站点的数据，而无需将患者数据合并到单个位置。由此产生的网络提高了模型的泛化能力，并在外部数据集上实现了比在单一来源数据上训练的神经网络更高的平均DSC。
Purpose As deep neural networks achieve more success in the wide field of computer vision, greater emphasis is being placed on the generalizations of these models for production deployment. With sufficiently large training datasets, models can typically avoid overfitting their data; however, for medical imaging it is often difficult to obtain enough data from a single site. Sharing data between institutions is also frequently nonviable or prohibited due to security measures and research compliance constraints, enforced to guard protected health information (PHI) and patient anonymity. Methods In this paper, we implement cyclic weight transfer with independent datasets from multiple geographically disparate sites without compromising PHI. We compare results between single-site learning (SSL) and multisite learning (MSL) models on testing data drawn from each of the training sites as well as two other institutions. Results The MSL model attains an average dice similarity coefficient (DSC) of 0.690 on the holdout institution datasets with a volume correlation of 0.914, respectively corresponding to a 7% and 5% statistically significant improvement over the average of both SSL models, which attained an average DSC of 0.646 and average correlation of 0.871. Conclusions We show that a neural network can be efficiently trained on data from two physically remote sites without consolidating patient data to a single location. The resulting network improves model generalization and achieves higher average DSCs on external datasets than neural networks trained on data from a single source.