Facial emotion recognition is a crucial process for many applications and is still unresolved. Historically, emotional recognition has usually been achieved through artificial intelligence techniques such as Convolutional Neural Networks. However, this approach is quite expensive in terms of computational power and complexity. To alleviate this problem, we propose a lightweight CNN for facial emotion recognition, called Custom Lightweight CNN-based Model (CLCM), based on the well-known MobileNetV2 architecture. Performance was evaluated on four public datasets, FER-2013, RAF-DB, AffectNet, and CK+, where seven facial emotions were detected. The CLCM model was compared to the well-known MobileNetV2 and ShuffleNetV2 architectures. The CLCM performance results were close to or better than the more complex models. Specifically, in the FER-2013 dataset, CLCM achieved an accuracy of 63%, while MobileNetV2 was 58%, and ShuffleNetV2 65%. In the RAF-DB dataset, CLCM showed 84%, MobileNetV2 73%, and ShuffleNetV2 80%. Lastly, in the AffectNet dataset, MobileNetV2 and ShuffleNetV2 showed an accuracy of 57%, while CLCM showed 54%. The results obtained from this study establish CLCM as one of the efficient models in FER. Although CLCM is a smaller model in terms of parameters (2.3 Million) compared to MobileNetV2 (3.5 Million) and ShuffleNetV2 (3.9 Million), it showed good results in almost all analyses. The reduced CLCM’s computational power allows its application in enhanced human-computer interaction, affective computing, and personalized user experience, especially for real-world scenarios such as psychological and medical assessment, automotive (real-time driver emotional state), and vulnerable individual care where limited resource systems are commonly employed and real-time and reliable response are strongly recommended.

Objectives: We developed quantitative methods to analyze microbubble kinetics based on renal contrast-enhanced ultrasound imaging combined with measurements of sublingual microcirculation on a fixed area to quantify early microvascular alterations in sepsis-induced acute kidney injury. Design: Prospective controlled animal experiment study. Setting: Hospital-affiliated animal research institution. Subjects: Fifteen female pigs. Interventions: The animals were instrumented with a renal artery flow probe after surgically exposing the kidney. Nine animals were given IV infusion of lipopolysaccharide to induce septic shock, and six were used as controls. Measurements and Main Results: Contrast-enhanced ultrasound imaging was performed on the kidney before, during, and after having induced shock. Sublingual microcirculation was measured continuously using the Cytocam on the same spot. Contrast-enhanced ultrasound effectively allowed us to develop new analytical methods to measure dynamic variations in renal microvascular perfusion during shock and resuscitation. Renal microvascular hypoperfusion was quantified by decreased peak enhancement and an increased ratio of the final plateau intensity to peak enhancement. Reduced intrarenal blood flow could be estimated by measuring the microbubble transit times between the interlobar arteries and capillary vessels in the renal cortex. Sublingual microcirculation measured using the Cytocam in a fixed area showed decreased functional capillary density associated with plugged sublingual capillary vessels that persisted during and after fluid resuscitation. Conclusions: In our lipopolysaccharide model, with resuscitation targeted at blood pressure, contrast-enhanced ultrasound imaging can identify renal microvascular alterations by showing prolonged contrast enhancement in microcirculation during shock, worsened by resuscitation with fluids. Concomitant analysis of sublingual microcirculation mirrored those observed in the renal microcirculation.

Augmented reality (AR) is an innovative system that enhances the real world by superimposing virtual objects on reality. The aim of this study was to analyze the application of AR in medicine and which of its technical solutions are the most used. We carried out a scoping review of the articles published between 2019 and February 2022. The initial search yielded a total of 2649 articles. After applying filters, removing duplicates and screening, we included 34 articles in our analysis. The analysis of the articles highlighted that AR has been traditionally and mainly used in orthopedics in addition to maxillofacial surgery and oncology. Regarding the display application in AR, the Microsoft HoloLens Optical Viewer is the most used method. Moreover, for the tracking and registration phases, the marker-based method with a rigid registration remains the most used system. Overall, the results of this study suggested that AR is an innovative technology with numerous advantages, finding applications in several new surgery domains. Considering the available data, it is not possible to clearly identify all the fields of application and the best technologies regarding AR.

Microcalcifications (microCas) are often early signs of breast cancer. However, detecting them is a difficult visual task and recognizing malignant lesions is a complex diagnostic problem. In recent years, several research groups have been working to develop computer-aided diagnosis (CAD) systems for X-ray mammography. In this paper, we propose a method to detect and classify microcalcifications. In order to discover the presence of microCas clusters, particular attention is paid to the analysis of the spatial arrangement of detected lesions. A fractal model has been used to describe the mammographic image, thus, allowing the use of a matched filtering stage to enhance microcalcifications against the background. A region growing algorithm, coupled with a neural classifier, detects existing lesions. Subsequently, a second fractal model is used to analyze their spatial arrangement so that the presence of microcalcification clusters can be detected and classified. Reported results indicate that fractal models provide an adequate framework for medical image processing; consequently high correct classification rates are achieved.

Vascular ageing is known to be accompanied by arterial stiffening and vascular endothelial dysfunction, and represents an independent factor contributing to the development of cardiovascular disease. The microvascular pulse is affected by the biomechanical alterations of the circulatory system, and has been the focus of studies aiming at the development of non-invasive methods able to extract physiologically relevant features. Objective: proposing an approach for the assessment of vascular ageing based on a support vector machine (SVM) learning from features of the pulse contour. Methods: the supervised classifier was trained and validated over 20935 models of pulse wave, obtained with a multi-Gaussian decomposition algorithm, applied to laser Doppler flowmetry signals of 54 healthy, non-smoker subjects. Results: the multi-Gaussian model showed a mean R ² of 0.98 and an average normalized root mean square error of 0.90, demonstrating the ability to reconstruct the pulse shape. Over 30 training and validation experiments, the SVM showed a mean Pearson's r of 0.808 between the rate of waves classified as old and the age of the subjects, along with an average area under the ROC curve of 0.953. Conclusion: the SVM showed the capability to discriminate differently aged individuals. Significance: the proposed method might detect the ageing-related modifications of the vascular tree; furthermore, since diabetes promotes vascular alterations comparable to ageing, this approach may be also suitable for the screening of diabetic angiopathy.

Key points: Although optogenetics has clearly demonstrated the feasibility of cardiac manipulation, current optical stimulation strategies lack the capability to react acutely to ongoing cardiac wave dynamics. Here, we developed an all‐optical platform to monitor and control electrical activity in real‐time. The methodology was applied to restore normal electrical activity after atrioventricular block and to manipulate the intraventricular propagation of the electrical wavefront. The closed‐loop approach was also applied to simulate a re‐entrant circuit across the ventricle. The development of this innovative optical methodology provides the first proof‐of‐concept that a real‐time all‐optical stimulation can control cardiac rhythm in normal and abnormal conditions. Optogenetics has provided new insights in cardiovascular research, leading to new methods for cardiac pacing, resynchronization therapy and cardioversion. Although these interventions have clearly demonstrated the feasibility of cardiac manipulation, current optical stimulation strategies do not take into account cardiac wave dynamics in real time. Here, we developed an all‐optical platform complemented by integrated, newly developed software to monitor and control electrical activity in intact mouse hearts. The system combined a wide‐field mesoscope with a digital projector for optogenetic activation. Cardiac functionality could be manipulated either in free‐run mode with submillisecond temporal resolution or in a closed‐loop fashion: a tailored hardware and software platform allowed real‐time intervention capable of reacting within 2 ms. The methodology was applied to restore normal electrical activity after atrioventricular block, by triggering the ventricle in response to optically mapped atrial activity with appropriate timing. Real‐time intraventricular manipulation of the propagating electrical wavefront was also demonstrated, opening the prospect for real‐time resynchronization therapy and cardiac defibrillation. Furthermore, the closed‐loop approach was applied to simulate a re‐entrant circuit across the ventricle demonstrating the capability of our system to manipulate heart conduction with high versatility even in arrhythmogenic conditions. The development of this innovative optical methodology provides the first proof‐of‐concept that a real‐time optically based stimulation can control cardiac rhythm in normal and abnormal conditions, promising a new approach for the investigation of the (patho)physiology of the heart.