Stroke has become a leading cause of death and long-term disability in the world with no effective treatment. Deep learning-based approaches have the potential to outperform existing stroke risk prediction models, but they rely on large well-labeled data. Due to the strict privacy protection policy in health-care systems, stroke data is usually distributed among different hospitals in small pieces. In addition, the positive and negative instances of such data are extremely imbalanced. Transfer learning can solve small data issue by exploiting the knowledge of a correlated domain, especially when multiple source of data are available. In this work, we propose a novel Hybrid Deep Transfer Learning-based Stroke Risk Prediction (HDTL-SRP) scheme to exploit the knowledge structure from multiple correlated sources (i.e., external stroke data, chronic diseases data, such as hypertension and diabetes). The proposed framework has been extensively tested in synthetic and real-world scenarios, and it outperforms the state-of-the-art stroke risk prediction models. It also shows the potential of real-world deployment among multiple hospitals aided with 5 G/B5G infrastructures.

This work proposes a joint selective encryption and data hiding scheme based on Compressed Sensing (CS), with a focus to its application in secure imaging. Specifically, working with a semantic-secure stream cipher, we suggest to selectively encrypt the sign bits of the CS measurements during its quantization stage and insert the authentication information using a non-separable histogram-shifting based data hiding scheme. The rationale behind the sign encryption is that CS measurements, when measured by random subspace projection, is random in nature and thus, from both theoretical and experimental points of view, the mean squared errors associated with authorized users and attackers are significant. Due to the indistinguishability of the output ciphertext and the nonlinearity of the CS decoder, it is robust, when comparing to existing selective encryption system of multimedia data, against known error concealment attacks. When applied in imaging, we demonstrate it could effectively degrade the visual quality level while saving the computation load by at least 90%. Moreover, we further show that a state-of-the-art data hiding system can be seamlessly incorporated into the sign encryption, thus allowing soft data authentication without heavy computation. The proposed scheme is expected to strengthen the security of applications in the field where both energy and privacy are the concerns, such as sensitive information protection for multimedia data in wireless sensor networks.

Background: Acute ischemic stroke (AIS) is the main cause of worldwide death and disability. Early neurological deterioration (END) can further increase the probability of death and disability in patients with ischemic stroke. Therefore, it is essential to find biomarkers to predict END early. Inflammatory response plays a crucial role in determining the course, outcome, and prognosis of END. Earlier studies focused on the relationship between routine hematological inflammatory markers and END, which limited the results. At present, relatively new and comprehensive markers of inflammatory response are relatively scarce. In this study, we investigate the predictive value of inflammatory markers in acute ischemic stroke cases for END which include systemic inflammatory response index (SIRI), platelet/lymphocyte ratio (PLR), lymphocyte/monocyte ratio (LMR), neutrophil/lymphocyte ratio (NLR), and then to establish a nomogram model. Methods: A total of 375 patients with AIS were analyzed who were admitted to the Second Affiliated Hospital of Harbin Medical University from September 2019 to June 2021. The associations between END and inflammatory markers were studied by employing the analysis of univariate. Following that, through regression models of the least absolute shrinkage and selection operator, the END risk model’s feature selection was optimized. The development of the model of prediction was carried out by applying the multivariable logistic regression analysis. The calibration, discrimination, and clinical efficacy of the prediction model were studied via calibration plot, C-index, and decision curve analysis (DCA). The bootstrapping validation method was used for the evaluation of internal validation. Results: We constructed a nomogram consisting of CRP, monocytes, NIHSS and SIRI. This model had desirable calibration and discrimination, with a C-index of 0.757 (95% confidence interval: 0.702–0.805). Interval validation could still achieve the higher C-index value of 0.747. When the risk threshold for END was greater than 13% but less than 84%, DCA proved to be clinically useful. Conclusions: Our research shows that SIRI can be used as a new predictor of END, as well as a monitor of treatment response. Compared with the traditional single inflammatory indicator, the integration of SIRI nomogram can predict the occurrence of END more objectively and reliably.