Search

Artificial intelligence (AI) models often face performance drops after deployment to external datasets. This study evaluated the potential of a novel data augmentation framework based on generative adversarial networks (GANs) that creates synthetic patient image data for model training to improve model generalizability. Model development and external testing were performed for a given classification task, namely the detection of new fluid-attenuated inversion recovery lesions at MRI during longitudinal follow-up of patients with multiple sclerosis (MS). An internal dataset of 669 patients with MS ( n = 3083 examinations) was used to develop an attention-based network, trained both with and without the inclusion of the GAN-based synthetic data augmentation framework. External testing was performed on 134 patients with MS from a different institution, with MR images acquired using different scanners and protocols than images used during training. Models trained using synthetic data augmentation showed a significant performance improvement when applied on external data (area under the receiver operating characteristic curve [AUC], 83.6% without synthetic data vs 93.3% with synthetic data augmentation; P = .03), achieving comparable results to the internal test set (AUC, 95.0%; P = .53), whereas models without synthetic data augmentation demonstrated a performance drop upon external testing (AUC, 93.8% on internal dataset vs 83.6% on external data; P = .03). Data augmentation with synthetic patient data substantially improved performance of AI models on unseen MRI data and may be extended to other clinical conditions or tasks to mitigate domain shift, limit class imbalance, and enhance the robustness of AI applications in medical imaging. Keywords: Brain, Brain Stem, Multiple Sclerosis, Synthetic Data Augmentation, Generative Adversarial Network Supplemental material is available for this article. © RSNA, 2024.

Commercial software based on artificial intelligence (AI) is entering clinical practice in neuroradiology. Consequently, medico-legal aspects of using Software as a Medical Device (SaMD) become increasingly important. These medico-legal issues warrant an interdisciplinary approach and may affect the way we work in daily practice. In this article, we seek to address three major topics: medical malpractice liability, regulation of AI-based medical devices, and privacy protection in shared medical imaging data, thereby focusing on the legal frameworks of the European Union and the USA. As many of the presented concepts are very complex and, in part, remain yet unsolved, this article is not meant to be comprehensive but rather thought-provoking. The goal is to engage clinical neuroradiologists in the debate and equip them to actively shape these topics in the future., (© 2023. The Author(s).)

Purpose: Image analysis is one of the most promising applications of artificial intelligence (AI) in health care, potentially improving prediction, diagnosis, and treatment of diseases. Although scientific advances in this area critically depend on the accessibility of large-volume and high-quality data, sharing data between institutions faces various ethical and legal constraints as well as organizational and technical obstacles., Methods: The Joint Imaging Platform (JIP) of the German Cancer Consortium (DKTK) addresses these issues by providing federated data analysis technology in a secure and compliant way. Using the JIP, medical image data remain in the originator institutions, but analysis and AI algorithms are shared and jointly used. Common standards and interfaces to local systems ensure permanent data sovereignty of participating institutions., Results: The JIP is established in the radiology and nuclear medicine departments of 10 university hospitals in Germany (DKTK partner sites). In multiple complementary use cases, we show that the platform fulfills all relevant requirements to serve as a foundation for multicenter medical imaging trials and research on large cohorts, including the harmonization and integration of data, interactive analysis, automatic analysis, federated machine learning, and extensibility and maintenance processes, which are elementary for the sustainability of such a platform., Conclusion: The results demonstrate the feasibility of using the JIP as a federated data analytics platform in heterogeneous clinical information technology and software landscapes, solving an important bottleneck for the application of AI to large-scale clinical imaging data.

The aim of this study was to employ artificial intelligence (AI)-based magnetic resonance imaging (MRI) brain volumetry to potentially distinguish between idiopathic normal pressure hydrocephalus (iNPH), Alzheimer's disease (AD), and age- and sex-matched healthy controls (CG) by evaluating cortical, subcortical, and ventricular volumes. Additionally, correlations between the measured brain and ventricle volumes and two established semi-quantitative radiologic markers for iNPH were examined. An IRB-approved retrospective analysis was conducted on 123 age- and sex-matched subjects (41 iNPH, 41 AD, and 41 controls), with all of the iNPH patients undergoing routine clinical brain MRI prior to ventriculoperitoneal shunt implantation. Automated AI-based determination of different cortical and subcortical brain and ventricular volumes in mL, as well as calculation of population-based normalized percentiles according to an embedded database, was performed; the CE-certified software mdbrain v4.4.1 or above was used with a standardized T1-weighted 3D magnetization-prepared rapid gradient echo (MPRAGE) sequence. Measured brain volumes and percentiles were analyzed for between-group differences and correlated with semi-quantitative measurements of the Evans' index and corpus callosal angle: iNPH patients exhibited ventricular enlargement and changes in gray and white matter compared to AD patients and controls, with the most significant differences observed in total ventricular volume (+67%) and the lateral (+68%), third (+38%), and fourth (+31%) ventricles compared to controls. Global ventriculomegaly and marked white matter reduction with concomitant preservation of gray matter compared to AD and CG were characteristic of iNPH, whereas global and frontoparietally accentuated gray matter reductions were characteristic of AD. Evans' index and corpus callosal angle differed significantly between the three groups and moderately correlated with the lateral ventricular volumes in iNPH patients [Evans' index (r > 0.83, p ≤ 0.001), corpus callosal angle (r < −0.74, p ≤ 0.001)]. AI-based MRI volumetry in iNPH patients revealed global ventricular enlargement and focal brain atrophy, which, in contrast to healthy controls and AD patients, primarily involved the supratentorial white matter and was marked temporomesially and in the midbrain, while largely preserving gray matter. Integrating AI volumetry in conjunction with traditional radiologic measures could enhance iNPH identification and differentiation, potentially improving patient management and therapy response assessment. [ABSTRACT FROM AUTHOR]

Cohort studies that quantify volumetric brain data among individuals with different levels of COVID-19 severity are presently limited. It is still uncertain whether there exists a potential correlation between disease severity and the effects of COVID-19 on brain integrity. Our objective was to assess the potential impact of COVID-19 on measured brain volume in patients with asymptomatic/mild and severe disease after recovery from infection, compared with healthy controls, using artificial intelligence (AI)-based MRI volumetry. A total of 155 participants were prospectively enrolled in this IRB-approved analysis of three cohorts with a mild course of COVID-19 (n = 51, MILD), a severe hospitalised course (n = 48, SEV), and healthy controls (n = 56, CTL) all undergoing a standardised MRI protocol of the brain. Automated AI-based determination of various brain volumes in mL and calculation of normalised percentiles of brain volume was performed with mdbrain software, using a 3D T1-weighted magnetisation-prepared rapid gradient echo (MPRAGE) sequence. The automatically measured brain volumes and percentiles were analysed for differences between groups. The estimated influence of COVID-19 and demographic/clinical variables on brain volume was determined using multivariate analysis. There were statistically significant differences in measured brain volumes and percentiles of various brain regions among groups, even after the exclusion of patients undergoing intensive care, with significant volume reductions in COVID-19 patients, which increased with disease severity (SEV > MILD > CTL) and mainly affected the supratentorial grey matter, frontal and parietal lobes, and right thalamus. Severe COVID-19 infection, in addition to established demographic parameters such as age and sex, was a significant predictor of brain volume loss upon multivariate analysis. In conclusion, neocortical brain degeneration was detected in patients who had recovered from SARS-CoV-2 infection compared to healthy controls, worsening with greater initial COVID-19 severity and mainly affecting the fronto-parietal brain and right thalamus, regardless of ICU treatment. This suggests a direct link between COVID-19 infection and subsequent brain atrophy, which may have major implications for clinical management and future cognitive rehabilitation strategies. [ABSTRACT FROM AUTHOR]

Focal cortical dysplasias (FCDs) are malformations of cortical development and one of the most common pathologies causing pharmacoresistant focal epilepsy. Resective neurosurgery yields high success rates, especially if the full extent of the lesion is correctly identified and completely removed. The visual assessment of magnetic resonance imaging does not pinpoint the FCD in 30%–50% of cases, and half of all patients with FCD are not amenable to epilepsy surgery, partly because the FCD could not be sufficiently localized. Computational approaches to FCD detection are an active area of research, benefitting from advancements in computer vision. Automatic FCD detection is a significant challenge and one of the first clinical grounds where the application of artificial intelligence may translate into an advance for patients' health. The emergence of new methods from the combination of health and computer sciences creates novel challenges. Imaging data need to be organized into structured, well‐annotated datasets and combined with other clinical information, such as histopathological subtypes or neuroimaging characteristics. Algorithmic output, that is, model prediction, requires a technically correct evaluation with adequate metrics that are understandable and usable for clinicians. Publication of code and data is necessary to make research accessible and reproducible. This critical review introduces the field of automatic FCD detection, explaining underlying medical and technical concepts, highlighting its challenges and current limitations, and providing a perspective for a novel research environment. [ABSTRACT FROM AUTHOR]