Application of artificial intelligence in screening for adverse perinatal outcomes: A protocol for systematic review

The article presents a systematic review protocol. The aim of the study is an assessment of current studies regarding the application of artificial intelligence and neural networks in the screening for adverse perinatal outcomes. We intend to compare the reported efficacy of these methods to improve pregnancy care and outcomes. There are more and more studies that describe the role of machine learning in facilitating the diagnosis of adverse perinatal outcomes, like gestational diabetes or pregnancy hypertension. A systematic review of available literature seems to be crucial to compare the known efficacy and application. Publication of a systematic review in this category would improve the value of future studies. The studies reporting on artificial intelligence application will have a major impact on future prenatal practice.     

On instabilities of deep learning in image reconstruction and the potential costs of AI

Deep learning, due to its unprecedented success in tasks such as image classification, has emerged as a new tool in image reconstruction with potential to change the field. In this paper, we demonstrate a crucial phenomenon: Deep learning typically yields unstable methods for image reconstruction. The instabilities usually occur in several forms: 1) Certain tiny, almost undetectable perturbations, both in the image and sampling domain, may result in severe artefacts in the reconstruction; 2) a small structural change, for example, a tumor, may not be captured in the reconstructed image; and 3) (a counterintuitive type of instability) more samples may yield poorer performance. Our stability test with algorithms and easy-to-use software detects the instability phenomena. The test is aimed at researchers, to test their networks for instabilities, and for government agencies, such as the Food and Drug Administration (FDA), to secure safe use of deep learning methods.