Extensive Evaluation Research Articles

Shunting at Arbitrary Feature Levels via Spatial Disentanglement: Toward Selective Image Translation.

The past few years have witnessed considerable efforts devoted to translating images from one domain to another, mainly aiming at editing global style. Here, we focus on a more general case, selective image translation (SLIT), under an unsupervised setting. SLIT essentially operates through a shunt mechanism that involves learning gates to manipulate only the contents of interest (CoIs), which can be either local or global, while leaving the irrelevant parts unchanged. Existing methods typically rely on a flawed implicit assumption that CoIs are separable at arbitrary levels, ignoring the entangled nature of DNN representations. This leads to unwanted changes and learning inefficiency. In this work, we revisit SLIT from an information-theoretical perspective and introduce a novel framework, which equips two opposite forces to disentangle the visual features. One force encourages independence between spatial locations on the features, while the other force unites multiple locations to form a "block" that jointly characterizes an instance or attribute that a single location may not independently characterize. Importantly, this disentanglement paradigm can be applied to visual features of any layer, enabling shunting at arbitrary feature levels, which is a significant advantage not explored in existing works. Our approach has undergone extensive evaluation and analysis, confirming its effectiveness in significantly outperforming the state-of-the-art baselines.

On the Feasibility and Benefits of Extensive Evaluation

Benchmark and system parameters often have a significant impact on performance evaluation, which raises a long-lasting question about which settings we should use. This paper studies the feasibility and benefits of extensive evaluation. A full extensive evaluation, which tests all possible settings, is usually too expensive. This work investigates whether it is possible to sample a subset of the settings and, upon them, generate observations that match those from a full extensive evaluation. Towards this goal, we have explored the incremental sampling approach, which starts by measuring a small subset of random settings, builds a prediction model on these samples using the popular ANOVA approach, adds more samples if the model is not accurate enough, and terminates otherwise. To summarize our findings: 1) Enhancing a research prototype to support extensive evaluation mostly involves changing hard-coded configurations, which does not take much effort. 2) Some systems are highly predictable, which means that they can achieve accurate predictions with a low sampling rate, but some systems are less predictable. 3) We have not found a method that can consistently outperform random sampling + ANOVA. Based on these findings, we provide recommendations to improve artifact predictability and strategies for selecting parameter values during evaluation.

Image colorization: A survey and dataset

Image colorization estimates RGB colors for grayscale images or video frames to improve their aesthetic and perceptual quality. Over the last decade, deep learning techniques for image colorization have significantly progressed, necessitating a systematic survey and benchmarking of these techniques. This article presents a comprehensive survey of recent state-of-the-art deep learning-based image colorization techniques, describing their fundamental block architectures, inputs, optimizers, loss functions, training protocols, training data, etc. It categorizes the existing colorization techniques into seven classes and discusses important factors governing their performance, such as benchmark datasets and evaluation metrics. We highlight the limitations of existing datasets and introduce a new dataset specific to colorization. We perform an extensive experimental evaluation of existing image colorization methods using both existing datasets and our proposed one. Finally, we discuss the limitations of existing methods and recommend possible solutions and future research directions for this rapidly evolving topic of deep image colorization. The dataset and codes for evaluation are publicly available at https://github.com/saeed-anwar/ColorSurvey.

Tuberous sclerosis complex: a case report

Background. Tuberous sclerosis complex (TSC) is a rare genetic disorder diagnosed in 6000-10000 children annually, marked by hamartomas in various organs due to hyperactivity of the mTOR pathway. Case report. A 9-year-old male with TSC exhibited developmental delays, skin lesions, vision and hearing impairments, and neurological symptoms. Extensive evaluations confirmed the diagnosis, and treatment included mTOR inhibitors, symptomatic management, and psychotherapy, resulting in condition improvement. Conclusions. TSC, caused by mutations in TSC1 and TSC2, significantly impacts organ function and quality of life, requiring comprehensive, multidisciplinary care.

Challenges, Requirements and Strategies in Digital Business for MSMEs: A Systematic Literature Review

The current digital age is ushering in significant changes in how Micro, Small and Medium Enterprises (MSMEs) operate, particularly in competition and collaboration. This systematic literature review aims to examine the significance of Digital Business Entrepreneurs (DBEs) as drivers of collaborative value networks within Micro, Small and Medium Enterprises (MSMEs). This paper synthesizes a comprehensive understanding of the challenges, requirements, and strategies associated with DBEs in the context of MSMEs by analyzing 150 research journal articles. The research demonstrates that DBEs have emerged as a subject of considerable academic interest, eliciting various viewpoints regarding their consequences on MSMEs. The investigation encompasses various settings within MSMEs, introducing prospects and obstacles resulting from the incorporation of digital business entrepreneurs. The paper makes a valuable contribution to the literature by addressing this research gap regarding the transformative capacity of DBEs in the MSMEs sector. The literature review identifies eight strategies, nine challenges, and eight requirements for digital business entrepreneurs. These findings provide entrepreneurs and managers with actionable insights as they navigate the digital landscape. Furthermore, delineating five prospective research trends provides scholars with a strategic guide, ensuring sustained relevance in this ever-evolving domain. Practical challenges faced by administrators of MSMEs involved in digital business entrepreneurship are also emphasized, offering practical advice for making sound decisions. This extensive evaluation functions as a valuable asset for individuals involved in digital business entrepreneurship, scholars, and practitioners in the field. It promotes a nuanced understanding of digital business entrepreneurs' obstacles and prospects when operating within micro, small, and medium enterprises.

Time-dependent mechanical behavior analysis using Weibull models of cellulose hollow fiber membranes produced by green solvent

The mechanical behavior of sustainable (“green”), bio-based cellulose hollow fiber membranes (hereafter, hollow fiber) produced using green solvent, which is potential for desalination and solvent-resistant nanofiltration, can be evaluated either in dry or water-conditioned (wet) states. However, the effect of conditioning time on the mechanical behavior of hollow fibers has not been conclusive. In this work, an extensive evaluation involving an experimental campaign and rigorous application of statistical models for cellulose hollow fibers produced using green solvent (1-ethyl-3-methylimidazolium diethyl phosphate or [EMIM][DEP]) via a dry-jet spinning technique is reported. First, we evaluated the microstructures and separation performance (water permeation, solute rejection) of hollow fibers made of different cellulose concentrations (10–15 wt%) in both pristine and conditioned states. Then, the strength, stiffness, and ductility of hollow fiber samples of different gauge lengths (25 and 50 mm) were measured by a standard tensile test device. Here, the effect of conditioning time on mechanical properties was evaluated after the hollow fiber samples were water-immersed at different times (from 30 s to 2 months). The strength distribution of conditioned hollow fibers was modeled and analyzed using two-parameter and three-parameter Weibull models. Our results showed that the cellulose content of 15 wt% in the hollow fibers produced a denser microstructure, providing the lowest molecular weight cut-off (MWCO). The cellulose content and gauge length slightly modified the mechanical properties of hollow fibers when they were evaluated in pristine, dry conditions. The mechanical properties of hollow fibers were drastically reduced after 10 min of water immersion, beyond which their properties were stabilized. Weibull modeling of mechanical reliability showed that two- or three-parameter Weibull could estimate the failure probability of hollow fibers quite well. Nonetheless, the three-parameter Weibull is better than the two-parameter one in terms of accuracy in determining the threshold strength located at the “lower-end tail.” Our analysis provides a rigorous demonstration of Weibull modeling in evaluating the time-dependent mechanical behavior of ductile, cellulose-based hollow fiber membranes, which is essential to support the design and development of future hollow fiber membranes in desalination industries.

Modeling and performance analysis of an electric two-wheeler on various driving cycles and validation using a performance real-time target machine

Compared with conventional two-wheelers, electric two-wheelers are gaining popularity owing to their potential to reduce emissions, their dependency on fossil fuels, and their enhanced economic benefits. However, the electric two-wheelers face key challenges such as inconsistent performance and driving range due to varying driving conditions. This study overcomes this challenge by developing a comprehensive system to investigate and predict the behavior of electric two-wheelers under various vehicle and battery parameters, driving conditions, and ambient conditions. The developed system, implemented in MATLAB Simulink, includes five subsections (the driving cycle, motor controller unit, electric motor, battery pack, and vehicle model) and evaluates the state of health, cell temperature, energy consumption, driving range, and state of charge. To validate the model, a simulation was conducted using a Speedgoat performance real-time target machine. An extensive evaluation is executed to validate the accuracy of the developed system against the real-time performance of an electric two-wheeler. For both simulated and standard driving cycles, the model offers an error of less than 1 %. The results of the analysis show that maintaining a mean speed between 18 km/h and 35 km/h results in the least energy consumption, a higher driving range, and a lower cell temperature. In addition, the research results show that driving aggressively consumes more energy. The results of this research indicate an innovative contribution toward the recognition and selection of appropriate electric two-wheelers.

Visceral Leishmaniasis Following A+AVD Treatment in a Patient with Classical Hodgkin's Lymphoma: A Case Report and Review of the Literature.

We present the case of a 43-year-old Caucasian man who developed visceral leishmaniasis (VL) following treatment with a combination of brentuximab vedotin and doxorubicin, vinblastine, and dacarbazine (A+AVD) for advanced-stage classical Hodgkin's lymphoma (cHL). The patient initially showed a favorable response to the treatment, but shortly after completing six cycles, he experienced recurrent fever, splenomegaly, and severe anemia. Extensive infectious disease evaluations led to a diagnosis of VL, confirmed by PCR testing. The patient was treated with amphotericin B, resulting in full clinical recovery. In addition to presenting this rare case, we conducted a full review of the literature on VL in the context of hematological disorders, including non-Hodgkin's lymphoma, splenic marginal zone lymphoma, and other lymphoproliferative diseases. This review highlights the increasing prevalence of VL in immunocompromised individuals, particularly those undergoing treatments like chemotherapy or immunotherapy, and underscores the importance of considering VL in differential diagnoses when such patients present with persistent fever and splenomegaly.

Animal Derived Bioplastic: An Environment Responsive Substitute to Combat Climate Change

Plastics derived from fossil fuels are an important part of modern life and it is the most commonly used material in every industrial sector. The use of plastics is increasing day by day and its degradation has become a great challenge. Moreover, non-degradable plastic polymers tend to accumulate as waste in the environment posing a major ecological threat and climate change issues. Therefore, the identification of microbes that can grow easily on plastic and the novel biological agents with exert degradative potential on plastic material have been reviewd herein. In light of these, the enzymatic process can lead to the conversion of plastic into water, carbon dioxide, and methane as a byproduct. Furthermore, fossil fuels utilized to make plastic items are going to be shortened, therefore scientists are finding novel biobased alternatives. In this regard, starch can be promising biopolymer for bioplastic synthesis after understanding underlysing the biological deterioration process and biotic as well as abiotic mechanisms. Hence, this review specifically presents an extensive evaluation of bioplastic from animal waste that can bring revolutionary changes in the environment to mitigate the climate changes.

SDCINet: A novel cross-task integration network for segmentation and detection of damaged/changed building targets with optical remote sensing imagery

Buildings are primary locations for human activities and key focuses in the military domain. Rapidly detecting damaged/changed buildings (DCB) and conducting detailed assessments can effectively aid urbanization monitoring, disaster response, and humanitarian assistance. Currently, the tasks of object detection (OD) and change detection (CD) for DCB are almost independent of each other, making it difficult to simultaneously determine the location and details of changes. Based on this, we have designed a cross-task network called SDCINet, which integrates OD and CD, and have created four dual-task datasets focused on disasters and urbanization. SDCINet is a novel deep learning dual-task framework composed of a consistency encoder, differentiation decoder, and cross-task global attention collaboration module (CGAC). It is capable of modeling differential feature relationships based on bi-temporal images, performing end-to-end pixel-level prediction, and object bounding box regression. The bi-direction traction function of CGAC is used to deeply couple OD and CD tasks. Additionally, we collected bi-temporal images from 10 locations worldwide that experienced earthquakes, explosions, wars, and conflicts to construct two datasets specifically for damaged building OD and CD. We also constructed two datasets for changed building OD and CD based on two publicly available CD datasets. These four datasets can serve as data benchmarks for dual-task research on DCB. Using these datasets, we conducted extensive performance evaluations of 18 state-of-the-art models from the perspectives of OD, CD, and instance segmentation. Benchmark experimental results demonstrated the superior performance of SDCINet. Ablation experiments and evaluative analyses confirmed the effectiveness and unique value of CGAC.

MixFuse: An iterative mix-attention transformer for multi-modal image fusion

Multi-modal image fusion plays a crucial role in various visual systems. However, existing methods typically involve a multi-stage pipeline, i.e., feature extraction, integration, and reconstruction, which limits the effectiveness and efficiency of feature interaction and aggregation. In this paper, we propose MixFuse, a compact multi-modal image fusion framework based on Transformers. It smoothly unifies the process of feature extraction and integration, As its core, the Mix Attention Transformer Block (MATB) integrates the Cross-Attention Transformer Module (CATM) and the Self-Attention Transformer Module (SATM). The CATM introduces a symmetrical cross-attention mechanism to identify modality-specific and general features, filtering out irrelevant and redundant information. Meanwhile, the SATM is designed to refine the combined features via a self-attention mechanism, enhancing the internal consistency and proper preservation of the features. This successive cross and self-attention modules work together to enhance the generation of more accurate and refined feature maps, which are essential for later reconstruction. Extensive evaluation of MixFuse on five public datasets shows its superior performance and adaptability over state-of-the-art methods. The code and model will be released at https://github.com/Bitlijinfu/MixFuse.

Occupancy Map Guided Attributes Artifacts Removal for Video-based Point Cloud Compression

Point clouds offer realistic three-dimensional (3-D) representations of objects and scenes at the expense of large data volumes. To represent such data compactly in real-world applications, Video-based Point Cloud Compression (V-PCC) converts their texture into two-dimensional (2-D) attributes and occupancy maps before applying lossy video compression. Unfortunately, the coding artifacts introduced in the decoded attribute maps eventually degrade the quality of the reconstructed point cloud, thereby influencing its immersive experience. This paper proposes a deep learning-based attribute map enhancement method that fully leverages the occupancy map's guidance. The design philosophy is that the cross-modality guidance from occupancy can be leveraged as critical information to enhance the attribute. Therefore, instead of treating attribute and occupancy as two separate sources of signals, occupancy serves as an indispensable auxiliary, such that the proposed framework explicitly provides the model with abundant clues by conducting local feature modification and global dependencies aggregation. In particular, the proposed framework is compatible with existing V-PCC bitstreams and can be feasibly incorporated into the standardized decoder pipeline. Extensive evaluations show the effectiveness of the proposed framework in attribute enhancement, with equivalently 6.0% Bjontegaard Delta-rate (BD-rate) savings obtained.

Vessel Trajectory Prediction Based on Automatic Identification System Data: Multi-Gated Attention Encoder Decoder Network

Utilizing time-series data from ship trajectories to forecast their subsequent movement is crucial for enhancing the safety within maritime traffic environments. The application of deep learning techniques, leveraging Automatic Identification System (AIS) data, has emerged as a pivotal area in maritime traffic studies. Within this domain, the precise forecasting of ship trajectories stands as a central challenge. In this study, we propose the multi-gated attention encoder decoder (MGAED) network, a model based on an encoder–decoder structure specialized for predicting ship trajectories in canals. The model employs a long short-term memory network (LSTM) as an encoder, combined with multiple Gated Recurrent Units (GRUs) and an attention mechanism for the decoder. Long-term dependencies in time-series data are captured through GRUs, while the attention mechanism is used to strengthen the model’s ability to capture key information, and a soft threshold residual structure is introduced to handle sparse features, thus enhancing the model’s generalization ability and robustness. The efficacy of our model is substantiated by an extensive evaluation against current deep learning benchmarks. Through comprehensive comparison experiments with existing deep learning methods, our model shows significant improvements in prediction accuracy, with an at least 9.63% reduction in the mean error (MAE) and an at least 20.0% reduction in the mean square error (MSE), providing a new solution to improve the accuracy and efficiency of ship trajectory prediction.

Machine Learning Prediction of Fuel Cell Remaining Life Enhanced by Variational Mode Decomposition and Improved Whale Optimization Algorithm

In predicting the remaining lifespan of Proton Exchange Membrane Fuel Cells (PEMFC), it is crucial to accurately capture the multi-scale variations in cell performance. This study employs Variational Mode Decomposition (VMD) to decompose performance data into intrinsic modes, elucidating critical multi-scale dynamics vital for understanding the complex degradation processes in fuel cells. In addition to VMD, this research utilizes an Improved Whale Optimization Algorithm (IWOA) to optimize a Back Propagation (BP) Neural Network. The IWOA focuses on precise adjustments of weights and biases, enabling the BP network to effectively interpret complex nonlinear relationships within the dataset. This optimization enhances the predictive model’s reliability and stability. Extensive experimental evaluations demonstrate that the integration of VMD, and the learning capabilities of the IWOA-optimized BP network significantly improves the model’s accuracy and stability across multiple predictions, thereby increasing the reliability of lifespan predictions for PEMFCs. This methodology offers a robust framework for extending the operational life and efficiency of fuel cells.

‘It is absolutely unnecessary, even detrimental, to embellish the façades’

Following World War I, Belgium faced a severe housing crisis, necessitating a comprehensive reform of social housing policy. Established in 1919, the National Society for Cheap Housing (Nationale Maatschappij voor Goedkope Woningen en Woonvertrekken, nmgww) aimed not only to repair material damage but also to address new social and societal demands. However, financial resources were limited, while there was also a severe shortage of (traditional) building materials and skilled labour. Progressive architects attempted to create a new, socially engaged architecture with a modernist vocabulary through the nmgww. They also advocated for the application of alternative building methods that had the added advantage of being financially favourable. The lack of expertise and experience with these alternative methods prompted the nmgww to set up an experimental project at Het Rad in Anderlecht in 1920. It entailed the construction of some sixty houses, employing eighteen different building systems. While most of these systems used concrete blocks, three utilized a prefabricated skeleton, and two opted for cast-in-situ concrete using monolithic casting systems. Nearly all utilized ‘lean concrete’, a type of concrete with a low cement content. Furthermore, in most cases part of the aggregate was replaced with industrial waste products to reduce costs and improve thermal properties. The intention was to perform an extensive evaluation and objective comparison of the different building systems. Yet even before the experiments had been concluded, the nmgww started to actively promote the German casting system Non Plus. For example, it invited local housing associations to participate in a study trip to Merseburg near Berlin to familiarize themselves with the system. Successfully, as it turns out as the system was subsequently used in the garden suburbs of Klein Rusland in Zelzate (1920-1923) and La Cité Moderne in Sint-Agatha-Berchem (1922-1925). The two districts were designed respectively by the architects Huib Hoste and Victor Bourgeois in a modernist idiom. The literature often refers to the economic benefits of the Non Plus system and to the impact of construction techniques on the aesthetics of these garden suburbs. However, in-depth research shows that the relationship between economic, technical and aesthetic aspects is not so straightforward: concrete was not necessarily cheaper than brick, while the plaster exterior often concealed a variety of systems. Moreover, both garden suburbs were initially designed in brick, indicating that there is no causal link between the material and the design language. It was not long, however, before the alternative building systems in lean concrete, particularly the monolithic casting systems, were abandoned. After 1926, as a result of political power shifts, the focus switched to small-scale projects and alternative building systems lost their scale-based economic advantage. Yet the experiment with alternative building practices, however brief, was an important phase in Belgian architectural and construction history. Projects like Het Rad and the modernist garden suburbs in cast-in-situ concrete show the interrelationship between societal, social, political, cultural and economic ambitions on the one hand, and the evolution of building culture on the other.

MetaDegron: multimodal feature-integrated protein language model for predicting E3 ligase targeted degrons.

Protein degradation through the ubiquitin proteasome system at the spatial and temporal regulation is essential for many cellular processes. E3 ligases and degradation signals (degrons), the sequences they recognize in the target proteins, are key parts of the ubiquitin-mediated proteolysis, and their interactions determine the degradation specificity and maintain cellular homeostasis. To date, only a limited number of targeted degron instances have been identified, and their properties are not yet fully characterized. To tackle on this challenge, here we develop a novel deep-learning framework, namely MetaDegron, for predicting E3 ligase targeted degron by integrating the protein language model and comprehensive featurization strategies. Through extensive evaluations using benchmark datasets and comparison with existing method, such as Degpred, we demonstrate the superior performance of MetaDegron. Among functional features, MetaDegron allows batch prediction of targeted degrons of 21 E3 ligases, and provides functional annotations and visualization of multiple degron-related structural and physicochemical features. MetaDegron is freely available at http://modinfor.com/MetaDegron/. We anticipate that MetaDegron will serve as a useful tool for the clinical and translational community to elucidate the mechanisms of regulation of protein homeostasis, cancer research, and drug development.

Digraph k-Coloring Games: New Algorithms and Experiments

We study digraph k-coloring games where strategic agents are vertices of a digraph and arcs represent agents' mutual unidirectional conflicts/idiosyncrasies. Each agent can select, as strategy, one of k different colors, and her payoff in a given state (a k-coloring) is given by the number of outgoing neighbors with a color different from her one. Such games model lots of strategic real-world scenarios and are related to several fundamental classes of anti-coordination games. Unfortunately, the problem of understanding whether an instance of the game admits a pure Nash equilibrium (NE), i.e., a state where no agent can improve her payoff by changing strategy, is NP-complete. Thus, in this paper, we focus on algorithms to compute an approximate NE: informally, a coloring is an approximate γ-NE, for some γ ≥ 1, if no agent can improve her payoff, by changing strategy, by a multiplicative factor of γ. Our contribution is manifold and of both theoretical and experimental nature. First, we characterize the hardness of finding pure and approximate equilibria in both general and special classes of digraphs. Second, we design and analyze three approximation algorithms with different theoretical guarantees on the approximation ratio, under different conditions; (i) algorithm APPROX-1 which computes, for any k ≥ 3, a Δo-NE for any n vertex graph having a maximum outdegree of Δo, in polynomial time; (ii) algorithm LLL-SPE, a randomized algorithm that, for any constant k ≥ 2, determines a γ-NE for some constant γ but only in digraphs whose minimum outdegree is sufficiently large, in polynomial time in expectation; (iii) algorithm APPROX-3 which, for any ε, computes a (1+ε)-NE by using O(log(n)/ε) colors, for any n-vertex digraph. Note that, the latter shows that a (1+ε)-NE exists and can be computed in polynomial time for k = O(log(n)). Finally, to assess how proposed algorithms behave in the typical case, we complete our study with an extensive experimental evaluation showing that, while newly introduced algorithms achieve bounded worst case behavior, they generally perform poorly in practice. Motivated by such unsatisfactory performance, we shift our attention to the best-response paradigm, successfully applied to other classes of games, and design and experimentally evaluate it a heuristic based on such paradigm. Our experiments provide strong evidences of such approach outperforming, in terms of approximation and computational time, all other methods and hence identify it as the most suited candidate for practical usage. More remarkably, it is also able to compute exact, pure NE in the great majority of cases. This suggests that, while these games are known to not always possess a pure NE, such an equilibrium often exists and can be efficiently computed, even by a distributed uncoordinated interaction of the agents.

Novel discretized gravitational search algorithm for effective medical hyperspectral band selection

Medical hyperspectral imaging present a promising avenue for non-invasive diagnostic methods for diseases. Nonetheless, the sparsity of medical hyperspectral data within high-dimensional spaces introduces the “curse of dimensionality”, which diminishes the efficiency and accuracy of data processing efforts. Therefore, spectral dimensionality reduction emerges as an essential process in the analysis and utilization of MHSIs data. To retain the intrinsic properties of the spectral bands, an effective unsupervised band selection algorithm is proposed leveraging the gravitational search algorithm (GSA-UBS) to identify the optimal band subset. Taking into account the informational content and redundancy among candidate bands, a comprehensive evaluation criterion is established that incorporates a band distance matrix and an information entropy vector. Additionally, a straightforward discrete search strategy is developed that enables gravitational search algorithm to directly retrieve the original sequence numbers of the selected bands, bypassing the conventional 0–1 band weighting approach. The extensive evaluation of GSA-UBS on three publicly available invivo brain cancer MHSIs datasets and a remote sensing hyperspectral image demonstrates its superior performance compared to various state-of-the-art methods. The source code for GSA-UBS can be accessed at https://github.com/zhangchenglong1116/GSA_UBS.

Multimodal contrastive learning for spatial gene expression prediction using histology images.

In recent years, the advent of spatial transcriptomics (ST) technology has unlocked unprecedented opportunities for delving into the complexities of gene expression patterns within intricate biological systems. Despite its transformative potential, the prohibitive cost of ST technology remains a significant barrier to its widespread adoption in large-scale studies. An alternative, more cost-effective strategy involves employing artificial intelligence to predict gene expression levels using readily accessible whole-slide images stained with Hematoxylin and Eosin (H&E). However, existing methods have yet to fully capitalize on multimodal information provided by H&E images and ST data with spatial location. In this paper, we propose mclSTExp, a multimodal contrastive learning with Transformer and Densenet-121 encoder for Spatial Transcriptomics Expression prediction. We conceptualize each spot as a "word", integrating its intrinsic features with spatial context through the self-attention mechanism of a Transformer encoder. This integration is further enriched by incorporating image features via contrastive learning, thereby enhancing the predictive capability of our model. We conducted an extensive evaluation of highly variable genes in two breast cancer datasets and a skin squamous cell carcinoma dataset, and the results demonstrate that mclSTExp exhibits superior performance in predicting spatial gene expression. Moreover, mclSTExp has shown promise in interpreting cancer-specific overexpressed genes, elucidating immune-related genes, and identifying specialized spatial domains annotated by pathologists. Our source code is available at https://github.com/shizhiceng/mclSTExp.

Diagnosis of ophthalmologic diseases in canines based on images using neural networks for image segmentation

The primary challenge in diagnosing ocular diseases in canines based on images lies in developing an accurate and reliable machine learning method capable of effectively segmenting and diagnosing these conditions through image analysis. Addressing this challenge, the study focuses on developing and rigorously evaluating a machine learning model for diagnosing ocular diseases in canines, employing the U-Net neural network architecture as a foundational element of this investigation.Through this extensive evaluation, the authors identified a model that exhibited good reliability, achieving prediction scores with an Intersection over Union (IoU) exceeding 80 %, as measured by the Jaccard index. The research methodology encompassed a systematic exploration of various neural network backbones (VGG, ResNet, Inception, EfficientNet) and the U-Net model, combined with an extensive model selection process and an in-depth analysis of a custom training dataset consisting of historical images of different medical symptoms and diseases in dog eyes.The results indicate a fairly high degree of accuracy in the segmentation and diagnosis of ocular diseases in canines, demonstrating the model's effectiveness in real-world applications. In conclusion, this potentially makes a significant contribution to the field by utilizing advanced machine-learning techniques to develop image-based diagnostic routines in veterinary ophthalmology. This model's successful development and validation offer a promising new tool for veterinarians and pet owners, enhancing early disease detection and improving health outcomes for canine patients.