Intelligent real-life key-pixel image detection system for early Arabic sign language learners.

Lack of an effective early sign language learning framework for a hard-of-hearing population can have traumatic consequences, causing social isolation and unfair treatment in workplaces. Alphabet and digit detection methods have been the basic framework for early sign language learning but are restricted by performance and accuracy, making it difficult to detect signs in real life. This article proposes an improved sign language detection method for early sign language learners based on the You Only Look Once version 8.0 (YOLOv8) algorithm, referred to as the intelligent sign language detection system (iSDS), which exploits the power of deep learning to detect sign language-distinct features. The iSDS method could overcome the false positive rates and improve the accuracy as well as the speed of sign language detection. The proposed iSDS framework for early sign language learners consists of three basic steps: (i) image pixel processing to extract features that are underrepresented in the frame, (ii) inter-dependence pixel-based feature extraction using YOLOv8, (iii) web-based signer independence validation. The proposed iSDS enables faster response times and reduces misinterpretation and inference delay time. The iSDS achieved state-of-the-art performance of over 97% for precision, recall, and F1-score with the best mAP of 87%. The proposed iSDS method has several potential applications, including continuous sign language detection systems and intelligent web-based sign recognition systems.

Genetically-clustered antifungal phytocytokines and receptor protein family members cooperate to trigger plant immune signaling.

Phytocytokines regulate plant immunity by cooperating with cell-surface proteins. Populus trichocarpa RUST INDUCED SECRETED PEPTIDE 1 (PtRISP1) exhibits an elicitor activity in poplar, as well as a direct antimicrobial activity against rust fungi. PtRISP1 gene directly clusters with a gene encoding a leucine-rich repeat receptor protein (LRR-RP), that we termed RISP-ASSOCIATED LRR-RP (PtRALR). In this study, we used phylogenomics to characterize the RISP and RALR gene families, and molecular physiology assays to functionally characterize RISP/RALR pairs. Both RISP and RALR gene families specifically evolved in Salicaceae species (poplar and willow), and systematically cluster in the genomes. Despite a low sequence identity, Salix purpurea RISP1 (SpRISP1) shows properties and activities similar to PtRISP1. Both PtRISP1 and SpRISP1 induced a reactive oxygen species (ROS) burst and mitogen-activated protein kinases (MAPKs) phosphorylation in Nicotiana benthamiana leaves expressing the respective clustered RALR. PtRISP1 also triggers a rapid stomatal closure in poplar. Altogether, these results suggest that plants evolved phytocytokines with direct antimicrobial activities, and that the genes coding these phytocytokines co-evolved and physically cluster with genes coding LRR-RPs required to initiate immune signaling.

Harnessing cGAS-STING axis for therapeutic benefits in systemic lupus erythematosus.

The cyclic GMP-AMP synthase (cGAS), a prominent intracellular DNA sensor in mammalian cells, controls the innate immune response and the stimulator of interferon genes (STING)-mediated synthesis of pro-inflammatory cytokines, such as type-I interferon (IFN-I). For decades, IFN-I has been hypothesized to be essential in the development of systemic lupus erythematosus (SLE), a chronic multisystem autoimmunity characterized by immune complex (IC) deposition in small vessels. Recent findings revealed that the activation of the cGAS-STING pathway by self-DNA would propagate the autoimmune responses via upregulating IFN-I production in SLE. In this review, we aimed to provide a comprehensive outlook of the role of the cGAS-STING pathway in SLE pathobiology, as well as, a better understanding of current therapeutic opportunities targeting this axis.

Beyond transcription, aryl hydrocarbon receptor plays a protective role in periodontitis by interacting with CaMKII.

BACKGROUND: The aryl hydrocarbon receptor (AhR) has been studied as an intracellular pattern recognition receptor that can identify bacterial pigments. To identify a potential therapeutic target for periodontitis, we investigated the expression of AhR in periodontitis and its role in the pathogenesis of periodontitis. METHODS: First, we analyzed AhR expression in a single-cell dataset from human periodontal tissue. Quantitative polymerase chain reaction (qPCR), immunofluorescence, and immunohistochemistry were used to verify the AhR level. Later, we determined the phenotypes of ligature-induced periodontitis in myeloid-specific AhR-deficient mice (Lyz2-Cre+/- AhRfx/fx), after which RNA sequencing (RNA-seq), qPCR, Western blot, immunofluorescence, and immunohistochemistry were used to investigate the impacts of AhR on periodontitis and its mechanism. Finally, we determined the therapeutic effect of AhR agonist 6-Formylindolo[3,2-b]carbazole (FICZ) administration on murine periodontitis and verified the effects of FICZ on macrophage polarization in vitro. RESULTS: AhR expression was enhanced in macrophages from periodontitis patients. Deletion of AhR from macrophages aggravated ligature-induced periodontitis and promoted the inflammatory response. Calcium/calmodulin-stimulated protein kinase II (CaMKII) phosphorylation was accelerated in AhR-deficient macrophages. Inhibiting CaMKII phosphorylation ameliorated periodontitis in Lyz2-Cre+/- AhRfx/fx mice. FICZ treatment blocked alveolar bone loss and relieved periodontal inflammation. FICZ diminished M1 macrophage polarization and promoted M2 macrophage polarization upon M1 macrophage induction. CONCLUSION: AhR played a protective role in the pathogenesis of periodontitis by orchestrating macrophage polarization via interacting with the CaMKII signaling pathway.

Identification of Distinct, Quantitative Pattern Classes from Emergent Tissue-Scale hiPSC Bioelectric Properties.

Bioelectric signals possess the ability to robustly control and manipulate patterning during embryogenesis and tissue-level regeneration. Endogenous local and global electric fields function as a spatial 'pre-pattern', controlling cell fates and tissue-scale anatomical boundaries; however, the mechanisms facilitating these robust multiscale outcomes are poorly characterized. Computational modeling addresses the need to predict in vitro patterning behavior and further elucidate the roles of cellular bioelectric signaling components in patterning outcomes. Here, we modified a previously designed image pattern recognition algorithm to distinguish unique spatial features of simulated non-excitable bioelectric patterns under distinct cell culture conditions. This algorithm was applied to comparisons between simulated patterns and experimental microscopy images of membrane potential (Vmem) across cultured human iPSC colonies. Furthermore, we extended the prediction to a novel co-culture condition in which cell sub-populations possessing different ionic fluxes were simulated; the defining spatial features were recapitulated in vitro with genetically modified colonies. These results collectively inform strategies for modeling multiscale spatial characteristics that emerge in multicellular systems, characterizing the molecular contributions to heterogeneity of membrane potential in non-excitable cells, and enabling downstream engineered bioelectrical tissue design.

Novel ApeC-containing protein mediates the recognition and internalization of Vibrio splendidus in Apostichopus japonicus.

Pattern recognition receptors (PRRs) mediate the innate immune responses and play a crucial role in host defense against pathogen infections. Apextrin C-terminal (ApeC)-containing proteins (ACPs), a newly discovered class of PRRs specific to invertebrates, recognize pathogens through their ApeC domain as intracellular or extracellular effectors. However, the other immunological functions of ACPs remain unclear. In this study, a membrane-localized ACP receptor was identified in the sea cucumber Apostichopus japonicus (denoted as AjACP1). The ApeC domain of AjACP1, which was located outside of its cell membrane, exhibited the capability to recognize and aggregate Vibrio splendidus. AjACP1 was upregulated upon V. splendidus infection, internalizing into the cytoplasm of coelomocytes. AjACP1 overexpression enhanced the phagocytic activity of coelomocytes against V. splendidus, while knockdown of AjACP1 by RNA interfere inhibited coelomocyte endocytosis. Inhibitor experiments indicated that AjACP1 regulated coelomocyte phagocytosis through the actin-dependent endocytic signaling pathway. Further investigation revealed that AjACP1 interacted with the subunit of the actin-related protein 2/3 complex ARPC2, promoting F-actin polymerization and cytoskeletal rearrangement and thereby affecting the coelomocyte phagocytosis of V. splendidus via the actin-dependent endocytic signaling pathway. As a novel membrane PRR, AjACP1 mediates the recognition and phagocytic activity of coelomocytes against V. splendidus through the AjACP1-ARPC2-F-actin polymerization and cytoskeletal rearrangement pathway.

A quenched fluorescence sensor array based on bis-lanthanide metal-organic framework for acetaldehyde detection and Baijiu discrimination.

Discrimination of segmented Baijiu contributes to stabilizing the quality of products, improving revenue-generating effects. A fluorescence sensor array is constructed based on four fluorescence characteristic peaks of terbium@lanthanum metal-organic framework (Tb@La-MOF). Its fluorescence signal is specifically quenched, when Tb@La-MOF encounters acetaldehyde. Acetaldehyde may inhibit the absorption of energy by the organic ligands in MOF, or/and hydrogen bonding with -COOH on the organic ligand, resulting in energy transfer to Tb(Ⅲ). According to this, the quantitative detection of acetaldehyde is completed with a range of 10-300 µM and the detection limit of 5.5 µM. At the same time, it has been successfully applied to the discrimination of segmented Baijiu. Fifteen segmented from three wine cellars are 100 % discriminated with the combined processing of sensor arrays and analytical methods. Accuracy, simplicity, and low-cost are highlights of this fluorescence sensor array, which has considerable potential for application in detection, production, and food field.

A novel lectin with a distinct Gal_Lectin and CUB domain mediates haemocyte phagocytosis in oyster Crassostrea gigas.

Invertebrate lectins exhibit structural diversity and play crucial roles in the innate immune responses by recognizing and eliminating pathogens. In the present study, a novel lectin containing a Gal_Lectin, a CUB and a transmembrane domain was identified from the Pacific oyster Crassostrea gigas (defined as CgGal-CUB). CgGal-CUB mRNA was detectable in all the examined tissues with the highest expression in adductor muscle (11.00-fold of that in haemocytes, p < 0.05). The expression level of CgGal-CUB mRNA in haemocytes was significantly up-regulated at 3, 24, 48 and 72 h (8.37-fold, 12.13-fold, 4.28-fold and 10.14-fold of that in the control group, respectively) after Vibrio splendidus stimulation. The recombinant CgGal-CUB (rCgGal-CUB) displayed binding capability to Mannan (MAN), peptidoglycan (PGN), D-(+)-Galactose and L-Rhamnose monohydrate, as well as Gram-negative bacteria (Escherichia coli, V. splendidus and Vibrio anguillarum), Gram-positive bacteria (Micrococcus luteus, Staphylococcus aureus, and Bacillus sybtilis) and fungus (Pichia pastoris). rCgGal-CUB was also able to agglutinate V. splendidus, and inhibit V. splendidus growth. Furthermore, rCgGal-CUB exhibited the activities of enhancing the haemocyte phagocytosis towards V. splendidus, and the phagocytosis rate of haemocytes was descended in blockage assay with CgGal-CUB antibody. These results suggested that CgGal-CUB served as a pattern recognition receptor to bind various PAMPs and bacteria, and enhanced the haemocyte phagocytosis towards V. splendidus.

Stress and Microstructures Characterization Based on Magnetic Incremental Permeability and Magnetic Barkhausen Noise Techniques.

Both microstructure and stress affect the structure and kinematic properties of magnetic domains. In fact, microstructural and stress variations often coexist. However, the coupling of microstructure and stress on magnetic domains is seldom considered in the evaluation of microstructural characteristics. In this investigation, Magnetic incremental permeability (MIP) and magnetic Barkhausen noise (MBN) techniques are used to study the coupling effect of characteristic microstructure and stress on the reversible and irreversible motions of magnetic domains, and the quantitative relationship between microstructure and magnetic domain characteristics is established. Considering the coupling effect of microstructure and stress on magnetic domains, a patterned characterization method of microstructure and stress is innovatively proposed. Pattern recognition based on the Multi-layer Perceptron (MLP) model is realized for microstructure and stress with an accuracy rate higher than 97%. The results show that the pattern recognition accuracy of magnetic domain features and micro-magnetic features simultaneously as input parameters is higher than that of micro-magnetic features alone as input parameters.

Partial Discharge Signal Pattern Recognition of Composite Insulation Defects in Cross-Linked Polyethylene Cables.

To investigate the pattern recognition of complex defect types in XLPE (cross-linked polyethylene) cable partial discharges and analyze the effectiveness of identifying partial discharge signal patterns, this study employs the variational mode decomposition (VMD) algorithm alongside entropy theories such as power spectrum entropy, fuzzy entropy, and permutation entropy for feature extraction from partial discharge signals of composite insulation defects. The mean power spectrum entropy (PS), mean fuzzy entropy (FU), mean permutation entropy (PE), as well as the permutation entropy values of IMF2 and IMF13 (Pe) are selected as the characteristic quantities for four categories of partial discharge signals associated with composite defects. Six hundred samples are selected from the partial discharge signals of each type of compound defect, amounting to a total of 2400 samples for the four types of compound defects combined. Each sample comprises five feature values, which are compiled into a dataset. A Snake Optimization Algorithm-optimized Support Vector Machine (SO-SVM) model is designed and trained, using the extracted features from cable partial discharge datasets as case examples for recognizing cable partial discharge signals. The identification outcomes from the SO-SVM model are then compared with those from conventional learning models. The results demonstrate that for partial discharge signals of XLPE cable composite insulation defects, the SO-SVM model yields better identification results than traditional learning models. In terms of recognition accuracy, for scratch and water ingress defects, SO-SVM improves by 14.00% over BP (Back Propagation) neural networks, by 5.66% over GA-BP (Genetic Algorithm-Back Propagation), and by 12.50% over SVM (support vector machine). For defects involving metal impurities and scratches, SO-SVM improves by 13.39% over BP, 9.34% over GA-BP, and 12.56% over SVM. For defects with metal impurities and water ingress, SO-SVM shows enhancements of 13.80% over BP, 9.47% over GA-BP, and 13.97% over SVM. Lastly, for defects combining metal impurities, water ingress, and scratches, SO-SVM registers increases of 11.90% over BP, 9.59% over GA-BP, and 12.05% over SVM.

Phase-Resolved Partial Discharge (PRPD) Pattern Recognition Using Image Processing Template Matching.

This paper proposes a new method for recognizing, extracting, and processing Phase-Resolved Partial Discharge (PRPD) patterns from two-dimensional plots to identify specific defect types affecting electrical equipment without human intervention while retaining the principals that make PRPD analysis an effective diagnostic technique. The proposed method does not rely on training complex deep learning algorithms which demand substantial computational resources and extensive datasets that can pose significant hurdles for the application of on-line partial discharge monitoring. Instead, the developed Cosine Cluster Net (CCNet) model, which is an image processing pipeline, can extract and process patterns from any two-dimensional PRPD plot before employing the cosine similarity function to measure the likeness of the patterns to predefined templates of known defect types. The PRPD pattern recognition capabilities of the model were tested using several manually classified PRPD images available in the existing literature. The model consistently produced similarity scores that identified the same defect type as the one from the manual classification. The successful defect type reporting from the initial trials of the CCNet model together with the speed of the identification, which typically does not exceed four seconds, indicates potential for real-time applications.

Effective recognition design in 8-ball billiards vision systems for training purposes based on Xception network modified by improved Chaos African Vulture Optimizer.

This research paper presents a comprehensive investigation into the utilization of color image processing technologies and deep learning algorithms in the development of a robot vision system specifically designed for 8-ball billiards. The sport of billiards, with its various games and ball arrangements, presents unique challenges for robotic vision systems. The proposed methodology addresses these challenges through two main components: object detection and ball pattern recognition. Initially, a robust algorithm is employed to detect the billiard balls using color space transformation and thresholding techniques. This is followed by determining the position of the billiard table through strategic cropping and isolation of the primary table area. The crucial phase involves the intricate task of recognizing ball patterns to differentiate between solid and striped balls. To achieve this, a modified convolutional neural network is utilized, leveraging the Xception network optimized by an innovative algorithm known as the Improved Chaos African Vulture Optimization (ICAVO) algorithm. The ICAVO algorithm enhances the Xception network's performance by efficiently exploring the solution space and avoiding local optima. The results of this study demonstrate a significant enhancement in recognition accuracy, with the Xception/ICAVO model achieving remarkable recognition rates for both solid and striped balls. This paves the way for the development of more sophisticated and efficient billiards robots. The implications of this research extend beyond 8-ball billiards, highlighting the potential for advanced robotic vision systems in various applications. The successful integration of color image processing, deep learning, and optimization algorithms shows the effectiveness of the proposed methodology. This research has far-reaching implications that go beyond just billiards. The cutting-edge robotic vision technology can be utilized for detecting and tracking objects in different sectors, transforming industrial automation and surveillance setups. By combining color image processing, deep learning, and optimization algorithms, the system proves its effectiveness and flexibility. The innovative approach sets the stage for creating advanced and productive robotic vision systems in various industries.

Automatic gait events detection with inertial measurement units: healthy subjects and moderate to severe impaired patients.

BACKGROUND: Recently, the use of inertial measurement units (IMUs) in quantitative gait analysis has been widely developed in clinical practice. Numerous methods have been developed for the automatic detection of gait events (GEs). While many of them have achieved high levels of efficiency in healthy subjects, detecting GEs in highly degraded gait from moderate to severely impaired patients remains a challenge. In this paper, we aim to present a method for improving GE detection from IMU recordings in such cases. METHODS: We recorded 10-meter gait IMU signals from 13 healthy subjects, 29 patients with multiple sclerosis, and 21 patients with post-stroke equino varus foot. An instrumented mat was used as the gold standard. Our method detects GEs from filtered acceleration free from gravity and gyration signals. Firstly, we use autocorrelation and pattern detection techniques to identify a reference stride pattern. Next, we apply multiparametric Dynamic Time Warping to annotate this pattern from a model stride, in order to detect all GEs in the signal. RESULTS: We analyzed 16,819 GEs recorded from healthy subjects and achieved an F1-score of 100%, with a median absolute error of 8 ms (IQR [3-13] ms). In multiple sclerosis and equino varus foot cohorts, we analyzed 6067 and 8951 GEs, respectively, with F1-scores of 99.4% and 96.3%, and median absolute errors of 18 ms (IQR [8-39] ms) and 26 ms (IQR [12-50] ms). CONCLUSIONS: Our results are consistent with the state of the art for healthy subjects and demonstrate a good accuracy in GEs detection for pathological patients. Therefore, our proposed method provides an efficient way to detect GEs from IMU signals, even in degraded gaits. However, it should be evaluated in each cohort before being used to ensure its reliability.

Paper-based optical sensor arrays for simultaneous detection of multi-targets in aqueous media: A review.

Sensor arrays, which draw inspiration from the mammalian olfactory system, are fundamental concepts in high-throughput analysis based on pattern recognition. Although numerous optical sensor arrays for various targets in aqueous media have demonstrated their diverse applications in a wide range of research fields, practical device platforms for on-site analysis have not been satisfactorily established. The significant limitations of these sensor arrays lie in their solution-based platforms, which require stationary spectrophotometers to record the optical responses in chemical sensing. To address this, this review focuses on paper substrates as device components for solid-state sensor arrays. Paper-based sensor arrays (PSADs) embedded with multiple detection sites having cross-reactivity allow rapid and simultaneous chemical sensing using portable recording apparatuses and powerful data-processing techniques. The applicability of office printing technologies has promoted the realization of PSADs in real-world scenarios, including environmental monitoring, healthcare diagnostics, food safety, and other relevant fields. In this review, we discuss the methodologies of device fabrication and imaging analysis technologies for pattern recognition-driven chemical sensing in aqueous media.

Knotify_V2.0: Deciphering RNA Secondary Structures with H-Type Pseudoknots and Hairpin Loops.

Accurately predicting the pairing order of bases in RNA molecules is essential for anticipating RNA secondary structures. Consequently, this task holds significant importance in unveiling previously unknown biological processes. The urgent need to comprehend RNA structures has been accentuated by the unprecedented impact of the widespread COVID-19 pandemic. This paper presents a framework, Knotify_V2.0, which makes use of syntactic pattern recognition techniques in order to predict RNA structures, with a specific emphasis on tackling the demanding task of predicting H-type pseudoknots that encompass bulges and hairpins. By leveraging the expressive capabilities of a Context-Free Grammar (CFG), the suggested framework integrates the inherent benefits of CFG and makes use of minimum free energy and maximum base pairing criteria. This integration enables the effective management of this inherently ambiguous task. The main contribution of Knotify_V2.0 compared to earlier versions lies in its capacity to identify additional motifs like bulges and hairpins within the internal loops of the pseudoknot. Notably, the proposed methodology, Knotify_V2.0, demonstrates superior accuracy in predicting core stems compared to state-of-the-art frameworks. Knotify_V2.0 exhibited exceptional performance by accurately identifying both core base pairing that form the ground truth pseudoknot in 70% of the examined sequences. Furthermore, Knotify_V2.0 narrowed the performance gap with Knotty, which had demonstrated better performance than Knotify and even surpassed it in Recall and F1-score metrics. Knotify_V2.0 achieved a higher count of true positives (tp) and a significantly lower count of false negatives (fn) compared to Knotify, highlighting improvements in Prediction and Recall metrics, respectively. Consequently, Knotify_V2.0 achieved a higher F1-score than any other platform. The source code and comprehensive implementation details of Knotify_V2.0 are publicly available on GitHub.

A robust event-driven approach to always-on object recognition.

We propose a neuromimetic architecture capable of always-on pattern recognition, i.e. at any time during processing. To achieve this, we have extended an existing event-based algorithm (Lagorce et al., 2017), which introduced novel spatio-temporal features as a Hierarchy Of Time-Surfaces (HOTS). Built from asynchronous events captured by a neuromorphic camera, these time surfaces allow to encode the local dynamics of a visual scene and to create an efficient event-based pattern recognition architecture. Inspired by neuroscience, we have extended this method to improve its performance. First, we add a homeostatic gain control on the activity of neurons to improve the learning of spatio-temporal patterns (Grimaldi et al., 2021). We also provide a new mathematical formalism that allows an analogy to be drawn between the HOTS algorithm and Spiking Neural Networks (SNN). Following this analogy, we transform the offline pattern categorization method into an online and event-driven layer. This classifier uses the spiking output of the network to define new time surfaces and we then perform the online classification with a neuromimetic implementation of a multinomial logistic regression. These improvements not only consistently increase the performance of the network, but also bring this event-driven pattern recognition algorithm fully online. The results have been validated on different datasets: Poker-DVS (Serrano-Gotarredona and Linares-Barranco, 2015), N-MNIST (Orchard, Jayawant et al., 2015) and DVS Gesture (Amir et al., 2017). This demonstrates the efficiency of this bio-realistic SNN for ultra-fast object recognition through an event-by-event categorization process.

State-of-art technologies, challenges, and emerging trends of computer vision in dental images.

Computer vision falls under the broad umbrella of artificial intelligence that mimics human vision and plays a vital role in dental imaging. Dental practitioners visualize and interpret teeth, and the structure surrounding the teeth and detect abnormalities by manually examining various dental imaging modalities. Due to the complexity and cognitive difficulty of comprehending medical data, human error makes correct diagnosis difficult. Automated diagnosis may be able to help alleviate delays, hasten practitioners' interpretation of positive cases, and lighten their workload. Several medical imaging modalities like X-rays, CT scans, color images, etc. that are employed in dentistry are briefly described in this survey. Dentists employ dental imaging as a diagnostic tool in several specialties, including orthodontics, endodontics, periodontics, etc. In the discipline of dentistry, computer vision has progressed from classic image processing to machine learning with mathematical approaches and robust deep learning techniques. Here conventional image processing techniques solely as well as in conjunction with intelligent machine learning algorithms, and sophisticated architectures of dental radiograph analysis employ deep learning techniques. This study provides a detailed summary of several tasks, including anatomical segmentation, identification, and categorization of different dental anomalies with their shortfalls as well as future perspectives in this field.

Characterization of DmToll and DmToll7 homologue in Litopenaeus vannamei based on structure analysis.

Toll-like receptors (TLRs) are a family of pattern recognition receptors (PRRs) that recognize invading pathogens and activate downstream signaling pathways. The number of 10 Tolls is found in Litopenaeus vannamei but have not yet been identified as the corresponding Toll homologue of model animal. In this study, we predicted the three-dimensional (3D) structures of 10 LvTolls (LvToll1-10) with AlphaFold2 program. The per-residue local distance difference test (pLDDT) scores of LvTolls showed the predicted structure of LvTolls had high accuracy (pLDDT>70). By structural analysis, 3D structures of LvToll2 and LvToll3 had high similarity with Drosophila melanogaster Toll and Toll7, respectively. 3D structure of LvToll7 and LvToll10 were not similar to that of other LvTolls. Moreover, we also predicted that LvSpätzle4 had high structural similarity to DmSpätzle. There were 9 potential hydrogen bonds in LvToll2-LvSpätzle4 complex. Importantly, co-immunoprecipitation assay showed that LvToll2 could bind with LvSpätzle4. Collectively, this study provides new insight for researching invertebrate immunity by identifying the protein of model animal homologue.

Predicting changes in brain metabolism and progression from mild cognitive impairment to dementia using multitask Deep Learning models and explainable AI.

BACKGROUND: The prediction of Alzheimer's disease (AD) progression from its early stages is a research priority. In this context, the use of Artificial Intelligence (AI) in AD has experienced a notable surge in recent years. However, existing investigations predominantly concentrate on distinguishing clinical phenotypes through cross-sectional approaches. This study aims to investigate the potential of modeling additional dimensions of the disease, such as variations in brain metabolism assessed via [18F]-fluorodeoxyglucose positron emission tomography (FDG-PET), and utilize this information to identify patients with mild cognitive impairment (MCI) who will progress to dementia (pMCI). METHODS: We analyzed data from 1,617 participants from the Alzheimer's Disease Neuroimaging Initiative (ADNI) who had undergone at least one FDG-PET scan. We identified the brain regions with the most significant hypometabolism in AD and used Deep Learning (DL) models to predict future changes in brain metabolism. The best-performing model was then adapted under a multi-task learning framework to identify pMCI individuals. Finally, this model underwent further analysis using eXplainable AI (XAI) techniques. RESULTS: Our results confirm a strong association between hypometabolism, disease progression, and cognitive decline. Furthermore, we demonstrated that integrating data on changes in brain metabolism during training enhanced the models' ability to detect pMCI individuals (sensitivity=88.4%, specificity=86.9%). Lastly, the application of XAI techniques enabled us to delve into the brain regions with the most significant impact on model predictions, highlighting the importance of the hippocampus, cingulate cortex, and some subcortical structures. CONCLUSION: This study introduces a novel dimension to predictive modeling in AD, emphasizing the importance of projecting variations in brain metabolism under a multi-task learning paradigm.