Gunzer Felix, Jantscher Michael, Hassler Eva M, Kau Thomas, Reishofer Gernot
Division of Neuroradiology, Vascular and Interventional Radiology, Department of Radiology, Medical University Graz, Auenbruggerplatz 2, 8036, Graz, Austria.
Research Center for Data-Driven Business Big Data Analytics, Know-Center GmbH, Inffeldgasse 13/6, 8010, Graz, Austria.
Insights Imaging. 2022 Oct 27;13(1):173. doi: 10.1186/s13244-022-01311-7.
When developing artificial intelligence (AI) software for applications in radiology, the underlying research must be transferable to other real-world problems. To verify to what degree this is true, we reviewed research on AI algorithms for computed tomography of the head. A systematic review was conducted according to the preferred reporting items for systematic reviews and meta-analyses. We identified 83 articles and analyzed them in terms of transparency of data and code, pre-processing, type of algorithm, architecture, hyperparameter, performance measure, and balancing of dataset in relation to epidemiology. We also classified all articles by their main functionality (classification, detection, segmentation, prediction, triage, image reconstruction, image registration, fusion of imaging modalities). We found that only a minority of authors provided open source code (10.15%, n 0 7), making the replication of results difficult. Convolutional neural networks were predominantly used (32.61%, n = 15), whereas hyperparameters were less frequently reported (32.61%, n = 15). Data sets were mostly from single center sources (84.05%, n = 58), increasing the susceptibility of the models to bias, which increases the error rate of the models. The prevalence of brain lesions in the training (0.49 ± 0.30) and testing (0.45 ± 0.29) datasets differed from real-world epidemiology (0.21 ± 0.28), which may overestimate performances. This review highlights the need for open source code, external validation, and consideration of disease prevalence.
在开发用于放射学应用的人工智能（AI）软件时，基础研究必须能够应用于其他现实世界的问题。为了验证这一情况的真实程度，我们回顾了关于头部计算机断层扫描AI算法的研究。根据系统评价和Meta分析的首选报告项目进行了系统评价。我们识别出83篇文章，并从数据和代码的透明度、预处理、算法类型、架构、超参数、性能指标以及与流行病学相关的数据集平衡等方面对它们进行了分析。我们还根据文章的主要功能（分类、检测、分割、预测、分诊、图像重建、图像配准、成像模态融合）对所有文章进行了分类。我们发现只有少数作者提供了开源代码（10.15%，n = 7），这使得结果难以复制。卷积神经网络被广泛使用（32.61%，n = 15），而超参数的报告频率较低（32.61%，n = 15）。数据集大多来自单一中心来源（84.05%，n = 58），这增加了模型对偏差的敏感性，进而增加了模型的错误率。训练数据集（0.49±0.30）和测试数据集（0.45±0.29）中脑病变的患病率与现实世界流行病学（0.21±0.28）不同，这可能高估了模型的性能。本综述强调了开源代码、外部验证以及考虑疾病患病率的必要性。
