Deep Neural Networks have offered numerous innovative solutions to brain-related diseases including Alzheimer’s. However, there are still a few standpoints in terms of diagnosis and planning that can be transformed via quantum Machine Learning (QML). In this study, we present a hybrid classical–quantum machine learning model for the detection of Alzheimer’s using 6400 labeled MRI scans with two classes. Hybrid classical–quantum transfer learning is used, which makes it possible to optimally pre-process complex and high-dimensional data. Classical neural networks extract high-dimensional features and embed informative feature vectors into a quantum processor. We use resnet34 to extract features from the image and feed a 512-feature vector to our quantum variational circuit (QVC) to generate a four-feature vector for precise decision boundaries. Adam optimizer is used to exploit the adaptive learning rate corresponding to each parameter based on first- and second-order gradients. Furthermore, to validate the model, different quantum simulators (PennyLane, qiskit.aer and qiskit.basicaer) are used for the detection of the demented and non-demented images. The learning rate is set to 10⁻⁴ for and optimized quantum depth of six layers, resulting in a training accuracy of 99.1% and a classification accuracy of 97.2% for 20 epochs. The hybrid classical–quantum network significantly outperformed the classical network, as the classification accuracy achieved by the classical transfer learning model was 92%. Thus, a hybrid transfer-learning model is used for binary detection, in which a quantum circuit improves the performance of a pre-trained ResNet34 architecture. Therefore, this work offers a method for selecting an optimal approach for detecting Alzheimer’s disease. The proposed model not only allows for the automated detection of Alzheimer’s but would also speed up the process significantly in clinical settings.

Artificial intelligence is serving as an impetus in digital health, clinical support, and health informatics for an informed patient’s outcome. Previous studies only consider classification accuracies of cardiotocographic (CTG) datasets and disregard computational time, which is a relevant parameter in a clinical environment. This paper proposes a modified deep neural algorithm to classify untapped pathological and suspicious CTG recordings with the desired time complexity. In our newly developed classification algorithm, AlexNet architecture is merged with support vector machines (SVMs) at the fully connected layers to reduce time complexity. We used an open-source UCI (Machine Learning Repository) dataset of cardiotocographic (CTG) recordings. We divided 2126 CTG recordings into 3 classes (Normal, Pathological, and Suspected), including 23 attributes that were dynamically programmed and fed to our algorithm. We employed a deep transfer learning (TL) mechanism to transfer prelearned features to our model. To reduce time complexity, we implemented a strategy wherein layers in the convolutional base were partially trained to leave others in the frozen states. We used an ADAM optimizer for the optimization of hyperparameters. The presented algorithm also outperforms the leading architectures (RCNNs, ResNet, DenseNet, and GoogleNet) with respect to real-time accuracies, sensitivities, and specificities of 99.72%, 96.67%, and 99.6%, respectively, making it a viable candidate for clinical settings after real-time validation.

Photoacoustic imaging (PAI) with a linear-array-based probe can provide a convenient means of imaging the human microcirculation within its native structural context and adds functional information. PAI using a multielement linear transducer array combined with multichannel collecting system was used for in vivo volumetric imaging of the blood microcirculation, the total concentration of hemoglobin (HbT), and the hemoglobin oxygen saturation ($sO2$) within human tissue. Three-dimensional (3-D) PA and ultrasound (US) volumetric scans were acquired from the forearm skin by linearly translating the transducer with a stepper motor over a region of interest, while capturing two-dimensional images using 15, 21, and 40 MHz frequency transducer probes. For the microvasculature imaging, PA images were acquired at 800- and 1064-nm wavelengths. For the HbT and $sO2$ estimates, PA images were collected at 750- and 850-nm wavelengths. 3-D microcirculation, HbT, and $sO2$ maps of the forearm skin were obtained from normal subjects. The linear-array-based PAI has been found promising in terms of resolution, imaging depth, and imaging speed for in vivo microcirculation imaging within human skin. We believe that a reflection type probe, similar to existing clinical US probes, is most likely to succeed in real clinical applications. Its advantages include ease of use, speed, and familiarity for radiographers and clinicians.

Heart failure (HF) is a multi-faceted, complex clinical syndrome characterized by significant morbidity, high mortality rate, reduced quality of life, and rapidly increasing healthcare costs. A larger proportion of these costs comprise both ambulatory and emergency department visits, as well as hospital admissions. Despite the methods used by telehealth (TH) to improve self-care and quality of life, patient outcomes remain poor. HF management is associated with numerous challenges, such as conflicting evidence from clinical trials, heterogeneity of TH devices, variability in patient inclusion and exclusion criteria, and discrepancies between healthcare systems. A growing body of evidence suggests there is an unmet need for increased individualization of in-hospital management, continuous remote monitoring of patients pre and post-hospital admission, and continuation of treatment post-discharge in order to reduce re-hospitalizations and improve long-term outcomes. This review summarizes the current state-of-the-art for HF and associated novel technologies and advancements in the most frequently used types of TH (implantable sensors), categorizing devices in their preclinical and clinical stage, bench-to-bedside implementation challenges, and future perspectives on remote HF management to improve long-term outcomes of HF patients. The Review also highlights recent advancements in non-invasive remote monitoring technologies demonstrated by a few pilot observational prospective cohort studies.

The sudden rupture of an atherosclerotic plaque is one of the main causes of stroke and stroke induced death. Plaque composition plays a critical role in plaque rupture. In order to differentiate between different plaque components, an imaging technique suitable for patient follow-up is needed. Photoacoustic (PA) imaging (PAI), a relatively new imaging technique, can also be used for cardiovascular imaging as it resolves optical contrast with ultrasonic resolution, visualizes oxygenated and deoxygenated haemoglobin and a large range of optical agents. PAI can be used to visualize molecular tissue changes, not only stenosis, and relates to the evaluation treatment protocols and/or post-procedural follow-up. In this review, we explain the principles of PAI, describe the recent developments in PAI systems used for non-invasive carotid imaging and intravascular imaging of coronary atherosclerosis and suggest areas of future research that will help bring PAI imaging towards clinical cardiovascular imaging.