PROJECT PUBLICATIONS
Download Here
Contributors
Karamintziou, S., Mavropoulos, T., Ntioudis, D., Meditskos, G., Vrochidis, S., & Kompatsiaris, I. Y.
Abstract
We face up to the challenge of explainability in Multimodal Artificial Intelligence (MMAI). At the nexus of neuroscience-inspired and quantum computing, interpretable and transparent spin-geometrical neural architectures for early fusion of large-scale, heterogeneous, graph-structured data are envisioned, harnessing recent evidence for relativistic quantum neural coding of (co-)behavioral states in the self-organizing brain, under competitive, multidimensional dynamics. The designs draw on a self-dual classical description – via special Clifford-Lipschitz operations – of spinorial quantum states within registers of at most 16 qubits for efficient encoding of exponentially large neural structures. Formally ‘trained’, Lorentz neural architectures with precisely one lateral layer of exclusively inhibitory interneurons accounting for anti-modalities, as well as their co-architectures with intra-layer connections are highlighted. The approach accommodates the fusion of up to 16 timeinvariant interconnected (anti-)modalities and the crystallization of latent multidimensional patterns. Comprehensive insights are expected to be gained through applications to Multimodal Big Data, under diverse real-world scenarios.
Download Here
Contributors
D Corrales, A Santos-Lozano, S López-Ortiz, A Lucia, D Rios-Insua
Abstract
Background and Objective: Only about 14% of eligible EU citizens finally participate in colorectal cancer (CRC) screening programs despite it being the third most common type of cancer worldwide. The development of CRC risk models can enable predictions to be embedded in decision-support tools facilitating CRC screening and treatment recommendations. This paper develops a predictive model that aids in characterizing CRC risk groups and assessing the influence of a variety of risk factors on the population.
Methods: A CRC Bayesian Network is learnt by aggregating extensive expert knowledge and data from a observational study and making use of structure learning algorithms to model the relations between variables. The network is then parametrised to characterize these relations in terms of local probability distributions at each of the nodes. It is finally used to predict the risks of developing CRC together with the uncertainty around such predictions.
Results: A graphical CRC risk mapping tool is developed from the model and used to segment the population into risk subgroups according to variables of interest. Furthermore, the network provides insights on the predictive influence of modifiable risk factors such as alcohol consumption and smoking, and medical conditions such as diabetes or hypertension linked to lifestyles that potentially have an impact on an increased risk of developing CRC.
Conclusion: CRC is most commonly developed in older individuals. However, some modifiable behavioral factors seem to have a strong predictive influence on its potential risk of development. Modeling these effects facilitates identifying risk groups and targeting influential variables which are subsequently helpful in the design of screening and treatment programs.
Download Here
Contributors
Carvalho, M. R., Caballero, D., Subhas, K. C., and Reis, R. L., Oliveira, J. M.
Abstract
Integrating biological material within soft microfluidic systems made of hydrogels offers countless possibilities in biomedical research to overcome the intrinsic limitations of traditional microfluidics based on solid, non-biodegradable, and non biocompatible materials. Hydrogel-based microfluidic technologies have the potential to transform in vitro cell/tissue culture and modeling. However, most hydrogel-based microfluidic platforms are associated with device deformation, poor structural definition, reduced stability/reproducibility due to swelling, and a limited range in rigidity, which threatens their applicability. Herein, we describe a new methodological approach for developing a soft cell-laden microfluidic device based on enzymatically-crosslinked silk fibroin (SF) hydrogels. Its unique mechano chemical properties and high structural fidelity, make this platform especially suited for in vitro disease modelling, as demonstrated by reproducing the native dynamic 3D microenvironment of colorectal cancer and its response to chemotherapeutics in a simplistic way. Results show that from all the tested concentrations, 14 wt% enzymatically-crosslinked SF microfluidic platform has outstanding structural stability and the ability to perfuse fluid while displaying in vivo-like biological responses. Overall, this work shows a novel technique to obtain an enzymatically-crosslinked SF microfluidic platform that can be employed for developing soft lab-on-a-chip in vitro models.
Download Here
Contributors
Hans Graux, Magdalena Gad-Nowak, Liesa Boghaert, Pieter Gryffroy
Abstract
The general impact of artificial intelligence (AI) systems on businesses, governments and the global economy is currently a hot topic. This isn’t surprising, considering that AI is believed to have the potential to bring about radical, unprecedented changes in the way people live and work.
The transformative potential of AI originates to a large extent from its ability to analyse data at scale, and to notice and internalise patterns and correlations in that data that humans (or fully deterministic algorithms) would struggle to identify. In simpler terms: modern AIs flourish especially if they can be trained on large volumes of data, and when they are used in relation to large volumes of data.
Download Here
Abstract
This article reports on a molecular-spin-sensitive-antenna (MSSA) that is based on stacked layers of organically functionalized graphene on a fibrous helical cellulose network for carrying out spatiotemporal identification of chiral enantiomers. The MSSA structures combine three complementary features: (i) chiral separation via a helical quantum sieve for chiral trapping, (ii) chiral recognition by a synthetically implanted spin-sensitive center in a graphitic lattice; and (iii) chiral selectivity by a chirality-induced-spin mechanism that polarizes the local electronic band-structure in graphene through chiral-activated Rashba spin–orbit interaction field. Combining the MSSA structures with decision-making principles based on neuromorphic artificial intelligence shows fast, portable, and wearable spectrometry for the detection and classification of pure and a mixture of chiral molecules, such as butanol (S and R), limonene (S and R), and xylene isomers, with 95–98% accuracy. These results can have a broad impact where the MSSA approach is central as a precautionary risk assessment against potential hazards impacting human health and the environment due to chiral molecules; furthermore, it acts as a dynamic monitoring tool of all parts of the chiral molecule life cycles.
Download Here
Abstract
In recent years, wearable technology has transcended its initial emphasis on fitness and lifestyle applications, expanding its horizons to encompass a critical role in healthcare and environmental monitoring. This remarkable evolution has been propelled by the advancement of wearable chemical sensors, a burgeoning field that has piqued the interest of both the scientific community and the general public. Wearable chemical sensors are distinct in their unparalleled ability to offer direct and precise insights into our health and surroundings. This trait is crucial in providing real-time insights into various personalised healthcare, environmental safety, and ubiquity of Internet of Things (IoT) that cannot bematched by other sensor types. For instance, these sensors can identify biomarkers in sweat or monitor air quality, yielding critical information that can lead to early disease detection or the identification of environmental risks.
Download Here
Contributors
César R. Casanova, Marta R. Casanova, Rui L. Reis & Joaquim M. Oliveira
Abstract
Soft microfluidic systems play a pivotal role in personalized medicine, particularly in in vitro diagnostics tools and disease modeling. These systems offer unprecedented precision and versatility, enabling the creation of intricate three dimensional (3D) tissue models that can closely emulate both physiological and pathophysiological conditions. By leveraging innovative biomaterials and bioinks, soft microfluidic systems can circumvent the current limitations involving the use of polydimethylsiloxane (PDMS), thus facilitating the development of customizable systems capable of sustaining the functions of encapsulated cells and mimicking complex biological microenvironments. The integration of lab-on-a-chip technologies with soft nanodevices further enhances disease models, paving the way for tailored therapeutic strategies. The current research concepts underscore the transformative potential of soft microfluidic systems, exemplified by recent breakthroughs in soft lithography and 3D (bio)printing. Novel applications, such as multi-layered tissues-on-chips and skin-on-a-chip devices, demonstrate significant advancements in disease modeling and personalized medicine. However, further exploration is warranted to address challenges in replicating intricate tissue structures while ensuring scalability and reproducibility. This exploration promises to drive innovation in biomedical research and healthcare, thus offering new insights and solutions to complex medical challenges and unmet needs.
Download Here
Contributors
Baron R. and Haick H.
Abstract
This article reviews the revolutionary impact of emerging technologies and artificial intelligence (AI) in reshaping modern healthcare systems, with a particular focus on the implementation of mobile diagnostic clinics. It presents an insightful analysis of the current healthcare challenges, including the shortage of healthcare workers, financial constraints, and the limitations of traditional clinics in continual patient monitoring. The concept of “Mobile Diagnostic Clinics” is introduced as a transformative approach where healthcare delivery is made accessible through the incorporation of advanced technologies. This approach is a response to the impending shortfall of medical professionals and the financial and operational burdens conventional clinics face. The proposed mobile diagnostic clinics utilize digital health tools and AI to provide a wide range of services, from everyday screenings to diagnosis and continual monitoring, facilitating remote and personalized care. The article delves into the potential of nanotechnology in diagnostics, AI’s role in enhancing predictive analytics, diagnostic accuracy, and the customization of care. Furthermore, the article discusses the importance of continual, noninvasive monitoring technologies for early disease detection and the role of clinical decision support systems (CDSSs) in personalizing treatment guidance. It also addresses the challenges and ethical concerns of implementing these advanced technologies, including data privacy, integration with existing healthcare infrastructure, and the need for transparent and bias-free AI systems.
Download Here
Contributors
D De Pascale, G Cascavilla, DA Tamburri, WJVD Heuvel
Abstract
Dark web crawling is a complex process that involves specific methodologies and techniques to navigate the Tor network and extract data from hidden services. This study proposes a general dark web crawler designed to extract pages handling security protocols, such as captchas, efficiently. Our approach uses a combination of seed URL lists, link analysis, and scanning to discover new content. We also incorporate methods for user-agent rotation and proxy usage to maintain anonymity and avoid detection. We evaluate the effectiveness of our crawler using metrics such as coverage, performance and robustness. Our results demonstrate that our crawler effectively extracts pages handling security protocols while maintaining anonymity and avoiding detection. Our proposed dark web crawler can be used for various applications, including threat intelligence, cybersecurity, and online investigations. Index Terms—LEA, TOR, Dark Web, crawler, Open Source Intelligence
Download Here
Abstract
Early detection of colorectal cancer is crucial for improving outcomes and reducing mortality. While there is strong evidence of effectiveness, currently adopted screening methods present several shortcomings which negatively impact the detection of early stage carcinogenesis, including low uptake due to patient discomfort. As a result, developing novel, non-invasive alternatives is an important research priority. Recent advancements in the field of breathomics, the study of breath composition and analysis, have paved the way for new avenues for non invasive cancer detection and effective monitoring. Harnessing the utility of Volatile Organic Compounds in exhaled breath, breathomics has the potential to disrupt colorectal cancer screening practices. Our goal is to outline key research efforts in this area focusing on machine learning methods used for the analysis of breathomics data, highlight challenges involved in artificial intelligence application in this context, and suggest possible future directions which are currently considered within the framework of the European project ONCOSCREEN.
Download Here
Contributors
Guy Decante, Ibrahim Fatih Cengiz, João B. Costa, Maurice N. Collins, Rui L. Reis, Joana Silva-Correia, J. Miguel Oliveira
Abstract
Hydrogels and bioinks obtained from gelatin (Gel) generally present poor mechanical properties and require a series of time-consuming and stepwise chemical processes to exhibit improved elasticity and resistance to fatigue. Alkali lignin (AL) is an underutilized by-product of the paper and pulp industry. It is a widely available and inexpensive biomaterial that presents enormous potential for high-value applications owing to its ease of chemical modification and unique naturally occurring polyaromatic structure. This work aims to develop different GelAL hydrogel formulations with a single-step method that are innovative and sustainable. The results obtained from the mechanical, rheological, and degradation studies of the developed GelAL hydrogels demonstrated that their properties can be easily modified and tuned using straightforward processing techniques, allowing these stretchable and tough hydrogels to be used as bioinks in 3D printing. The modulation of mechanical properties through hydrogel formulations is a result of interactions between the Gel and AL which can be associated with the interplay of anionic sulfonates in AL and the arginine and lysine residues from Gel. The tensile stress at the break for the Gel20AL10 formulation was 32% higher than the value for Gel20AL5 and 157% higher than that of Gel10AL10. The elongation at break also decreased as it averaged 659 ± 149% for the Gel20AL10 formulation, which is 20% more than that of Gel20AL5 and 55% more than the average elongation at break of Gel10AL10. Further zeta potential measurements and quartz crystal microbalance with energy dissipation studies demonstrated that Gel and AL seem to form neutral complexes when mixed. These assays support the idea that AL and Gel are readily bound through weak interactions, and chemical crosslinking strategies need to be considered when degradability and mechanical properties tuning are envisioned. Altogether, these highperformance GelAL hydrogels display mechanical properties similar to soft tissues with high elasticity beyond that of natural hydrogels and fulfill the requirements of a broad range of biomedical and tissue engineering scaffolding applications.
Download Here
Abstract
Only about 14% of eligible EU citizens finally participate in colorectal cancer (CRC) screening programs despite it being the third most common type of cancer worldwide. The development of CRC risk models can enable predictions to be embedded in decision-support tools facilitating CRC screening and treatment recommendations. This paper develops a predictive model that aids in characterizing CRC risk groups and assessing the influence of a variety of risk factors on the population.