Automated detection of Alzheimer's disease: a multi-modal approach with 3D MRI and amyloid PET.

Recent advances in deep learning and imaging technologies have revolutionized automated medical image analysis, especially in diagnosing Alzheimer's disease through neuroimaging. Despite the availability of various imaging modalities for the same patient, the development of multi-modal models leveraging these modalities remains underexplored. This paper addresses this gap by proposing and evaluating classification models using 2D and 3D MRI images and amyloid PET scans in uni-modal and multi-modal frameworks. Our findings demonstrate that models using volumetric data learn more effective representations than those using only 2D images. Furthermore, integrating multiple modalities enhances model performance over single-modality approaches significantly. We achieved state-of-the-art performance on the OASIS-3 cohort. Additionally, explainability analyses with Grad-CAM indicate that our model focuses on crucial AD-related regions for its predictions, underscoring its potential to aid in understanding the disease's causes.

Evaluating the robustness of a contact-less mHealth solution for personal and remote monitoring of blood oxygen saturation.

MHealth technologies play a fundamental role in epidemiological situations such as the ongoing outbreak of COVID-19 because they allow people to self-monitor their health status (e.g. vital parameters) at any time and place, without necessarily having to physically go to a medical clinic. Among vital parameters, special care should be given to monitor blood oxygen saturation (SpO2), whose abnormal values are a warning sign for potential COVID-19 infection. SpO2 is commonly measured through the pulse oximeter that requires skin contact and hence could be a potential way of spreading contagious infections. To overcome this problem, we have recently developed a contact-less mHealth solution that can measure blood oxygen saturation without any contact device but simply processing short facial videos acquired by any common mobile device equipped with a camera. Facial video frames are processed in real-time to extract the remote photoplethysmographic signal useful to estimate the SpO2 value. Such a solution promises to be an easy-to-use tool for both personal and remote monitoring of SpO2. However, the use of mobile devices in daily situations holds some challenges in comparison to the controlled laboratory scenarios. One main issue is the frequent change of perspective viewpoint due to head movements, which makes it more difficult to identify the face and measure SpO2. The focus of this work is to assess the robustness of our mHealth solution to head movements. To this aim, we carry out a pilot study on the benchmark PURE dataset that takes into account different head movements during the measurement. Experimental results show that the SpO2 values obtained by our solution are not only reliable, since they are comparable with those obtained with a pulse oximeter, but are also insensitive to head motion, thus allowing a natural interaction with the mobile acquisition device.

Automatic facial emotion recognition at the COVID-19 pandemic time.

People use various nonverbal communicative channels to convey emotions, among which facial expressions are considered the most important ones. Thus, automatic Facial Expression Recognition (FER) is a fundamental task to increase the perceptive skills of computers, especially in human-computer interaction. Like humans, state-of-art FER systems are able to recognize emotions from the entire face of a person. However, the COVID-19 pandemic has imposed a massive use of face masks that help in preventing infection but may hamper social communication and make the recognition of facial expressions a very challenging task due to facial occlusion. In this paper we propose a FER system capable to recognize emotions from masked faces. The system checks for the presence of a mask on the face image and, in case of mask detection, it extracts the eyes region and recognizes the emotion only considering that portion of the face. The effectiveness of the developed FER system was tested in recognizing emotions and their valence only from the eyes region and comparing the results when considering the entire face. As it was expected, emotions that are related mainly to the mouth region (e.g., disgust) are barely recognized, while positive emotions are better identified by considering only the eyes region. Moreover, we compared the results of our FER system to the human annotation of emotions on masked faces. We found out that the FER system outperforms the human annotation, thus showing that the model is able to learn proper features for each emotion leveraging only the eyes region.

Editorial for Special Issue "Fine Art Pattern Extraction and Recognition".

Cultural heritage, especially the fine arts, plays an invaluable role in the cultural, historical, and economic growth of our societies [...].

Euryhalinity of subtropical marine and estuarine polychaetes evaluated through carbonic anhydrase activity and cell volume regulation.

Polychaete worms are widespread and diverse in marine and estuarine habitats subject to varying salinity, in areas influenced by tides, demanding physiological adjustment for internal homeostasis. They are typically considered and reported to be osmoconformers, but they are not often studied for their osmoregulation. Here, three species of polychaete worms from distinct coastal habitats have been investigated: the spionid Scolelepis goodbody (intertidal in saline, exposed sandy beaches), the nereidid Laeonereis culveri (estuarine polyhaline), and the nephtyid Nephtys fluviatilis (estuarine oligohaline). The general objective here was to relate ecological aspects and physiology of the studied species. Constitutive whole body osmolality and carbonic anhydrase activity (CAA, relevant for osmoregulation, acid-base balance and respiration) have been assayed. In addition, cell volume regulatory capacity (from whole body cell dissociation) was challenged under hypoosmotic and hyperosmotic shocks (50% intensity), with respect to isosmotic control. S. googdbody and L. culveri, the two species from most saline environments (marine/estuarine), showed higher CAA than N. fluviatilis, which, in turn, displayed a hyperosmotic gradient to water of salinity 15. Cells from S. goodbody and L. culveri showed regulatory volume decrease upon swelling, with S. goodbody showing the largest volume increase. As in other more studied marine invertebrate groups, polychaetes also show variability in their osmoregulatory physiology, related to distinct saline challenges faced in their coastal habitats.

Early time course of variation in coelomic fluid ionic concentrations in sea urchins abruptly exposed to hypo- and hyper-osmotic salinity challenges: Role of size and cross-section area of test holes.

Echinoderms are restricted to the marine environment and are osmoconformer invertebrates. However, some species live in unstable environments. Especially those species, and those of larger body size, tend to show variable, albeit transient, ionic gradients between their coelomic fluid and external seawater. In order to further examine how sea urchin size relates to apparent ionic permeability of their body wall/epithelia, specimens of Echinometra lucunter, Lytechinus variegatus, Paracentrotus gaimardi, and Arbacia lixula-A. lixula of two distinct populations, Rio de Janeiro and Santa Catarina-were abruptly transferred from 35 psu to either 25 or 45 psu. Sodium, chloride, magnesium, and potassium concentrations were assayed in their coelomic fluids after 0, 1, 2, and 3 hr of exposure. Relative area of putative permeable (i.e., cross section areas of soft tissues, or test holes) surfaces (PPS) was estimated in empty tests as the sum of the peristomial area (oral hole in the empty test) and the total cross-section area of ambulacral holes, divided by the total volume (TV) of the test. L. variegatus and E. lucunter, the largest species, had PPS/TV values similar to that of the much smaller P. gaimardi. A. lixula was the "most putatively-permeable and conformer" among them all, especially urchins from the Santa Catarina population. Internal ionic levels equilibrated faster with external water in 45 than in 25, and differences among ions were observed. Body size is relevant, among many other factors, to aid conformers such as sea urchins to dwell in intertidal unstable habitats.

Volume regulation of intestinal cells of echinoderms: Putative role of ion transporters (Na(+)/K(+)-ATPase and NKCC).

Echinoderms are exclusively marine osmoconformer invertebrates. Some species occupy the challenging intertidal region. Upon salinity changes, the extracellular osmotic concentration of these animals also varies, exposing tissues and cells to osmotic challenges. Cells and tissues may then respond with volume regulation mechanisms, which involve transport of ions and water into and/or out of the cells, through ion transporters, such as the Na(+)/K(+)-ATPase and NKCC. The goal of this study was to relate the cell volume regulation capacity of echinoderm intestinal cells Na(+)/K(+)-ATPase and NKCC activities, in three echinoderm species: Holothuria grisea, Arbacia lixula, and Echinometra lucunter. Isolated cells of these species displayed some control of their cell volume upon exposure to anisosmotic media (isolated intestinal cells, calcein fluorescence as indicator of volume change), with a distinct higher capacity shown by H. grisea, which did not swell even upon 50% hyposmotic shock. The holothuroid cells showed indirect evidence (effect of furosemide) of the participation of NKCC in this process, with a secretory function, and of a secondary role by the NKA (effect of ouabain). Other mechanisms are probably responsible for this function in the urchins. Variable expression of these transporters, and others not examined here, may to some extent account for the variability in cell volume regulation capacity in echinoderm cells.

Direct relationship between osmotic and ionic conforming behavior and tissue water regulatory capacity in echinoids.

Echinoderms are considered marine osmoconforming invertebrates. However, many are intertidal or live next to estuaries, tolerating salinity changes and showing extracellular gradients to dilute seawater. Three species of echinoids - Lytechinus variegatus, which can occur next to estuarine areas, the rocky intertidal Echinometra lucunter, and the mostly subtidal Arbacia lixula - were submitted to a protocol of stepwise (rate of 2-3 psu/h) dilution, down to 15 psu, or concentration, up to 45 psu, of control seawater (35 psu). Coelomic fluid samples were obtained every hour. The seawater dilution experiment lasted 8h, while the seawater concentration experiment lasted 6h. Significant gradients (40-90% above value in 15 psu seawater) for osmolality, sodium, magnesium, and potassium were shown by L. variegatus and E. lucunter. A. lixula showed the smallest gradients, displaying the strongest conforming behavior. The esophagus of the three species was challenged in vitro with 20 and 50% osmotic shocks (hypo- and hyperosmotic). A. lixula, the most "conforming" species, showed the highest capacity to avoid swelling of its tissues upon the -50% hyposmotic shock, and was also the species less affected by salinity changes concerning the observation of spines and ambulacral feet movement in the whole-animal experiments. Thus, the most conforming species (A. lixula) displayed the highest capacity to regulate tissue water/volume, and was also the most euryhaline among the three studied species. In addition, tissues from all three species swelled much more than they shrank under osmotic shocks of same magnitude. This distinct trend to gain water, despite the capacity to hold some gradients upon seawater dilution, helps to explain why echinoderms cannot be fully estuarine, or ever enter fresh water.

An empirical risk functional to improve learning in a neuro-fuzzy classifier.

The paper proposes a new Empirical Risk Functional as cost function for training neuro-fuzzy classifiers. This cost function, called Approximate Differentiable Empirical Risk Functional (ADERF), provides a differentiable approximation of the misclassification rate so that the Empirical Risk Minimization Principle formulated in Vapnik's Statistical Learning Theory can be applied. Also, based on the proposed ADERF, a learning algorithm is formulated. Experimental results on a number of benchmark classification tasks are provided and comparison to alternative approaches given.