Augmentation Strategies Research Articles

Data augmentation via warping transforms for modeling natural variability in the corneal endothelium enhances semi-supervised segmentation.

Image segmentation of the corneal endothelium with deep convolutional neural networks (CNN) is challenging due to the scarcity of expert-annotated data. This work proposes a data augmentation technique via warping to enhance the performance of semi-supervised training of CNNs for accurate segmentation. We use a unique augmentation process for images and masks involving keypoint extraction, Delaunay triangulation, local affine transformations, and mask refinement. This approach accurately captures the natural variability of the corneal endothelium, enriching the dataset with realistic and diverse images. The proposed method achieved an increase in the mean intersection over union (mIoU) and Dice coefficient (DC) metrics of 17.2% and 4.8% respectively, for the segmentation task in corneal endothelial images on multiple CNN architectures. Our data augmentation strategy successfully models the natural variability in corneal endothelial images, thereby enhancing the performance and generalization capabilities of semi-supervised CNNs in medical image cell segmentation tasks.

Enhancing image-based diagnosis of gastrointestinal tract diseases through deep learning with EfficientNet and advanced data augmentation techniques.

The early detection and diagnosis of gastrointestinal tract diseases, such as ulcerative colitis, polyps, and esophagitis, are crucial for timely treatment. Traditional imaging techniques often rely on manual interpretation, which is subject to variability and may lack precision. Current methodologies leverage conventional deep learning models that, while effective to an extent, often suffer from overfitting and generalization issues on medical image datasets due to the intricate and subtle variations in disease manifestations. These models typically do not fully utilize the potential of transfer learning or advanced data augmentation, leading to less-than-optimal performance, especially in diverse real-world scenarios where data variability is high. This study introduces a robust model using the EfficientNetB5 architecture combined with a sophisticated data augmentation strategy. The model is tailored for the high variability and intricate details present in gastrointestinal tract disease images. By integrating transfer learning with maximal pooling and extensive regularization, the model aims to enhance diagnostic accuracy and reduce overfitting. The proposed model achieved a test accuracy of 98.89%, surpassing traditional methods by incorporating advanced regularization and augmentation techniques. The application of horizontal flipping and dynamic scaling during training significantly improved the model's ability to generalize, evidenced by a low-test loss of 0.230 and high precision metrics across all classes. The proposed deep learning framework demonstrates superior performance in the automated classification of gastrointestinal diseases from image data. By addressing key limitations of existing models through innovative techniques, this study contributes to the enhancement of diagnostic processes in medical imaging, potentially leading to more accurate and timely disease interventions.

AIRHF-Net: an adaptive interaction representation hierarchical fusion network for occluded person re-identification

To tackle the high resource consumption in occluded person re-identification, sparse attention mechanisms based on Vision Transformers (ViTs) have become popular. However, they often suffer from performance degradation with long sequences, omission of crucial information, and token representation convergence. To address these issues, we introduce AIRHF-Net: an Adaptive Interaction Representation Hierarchical Fusion Network, named AIRHF-Net, designed to enhance pedestrian identity recognition in occluded scenarios. Our approach begins with the development of an Adaptive Local-Window Interaction Encoder (AL-WIE), which aims to overcome the inherent subjective limitations of traditional sparse attention mechanisms. This innovative encoder merges window attention, adaptive local attention, and interaction attention, facilitating automatic localization and focusing on visible pedestrian regions within images. It effectively extracts contextual information from window-level features while minimizing the impact of occlusion noise. Additionally, recognizing that ViTs may lose spatial information in deeper structural layers, we implement a Local Hierarchical Encoder (LHE). This component segments the input sequence in the spatial dimension, integrating features from various spatial positions to construct hierarchical local representations that substantially enhance feature discriminability. To further augment the quality and breadth of datasets, we adopt an Occlusion Data Augmentation Strategy (ODAS), which bolsters the model’s capacity to extract critical information under occluded conditions. Extensive experiments demonstrate that our method achieves improved performance on the Occluded-DukeMTMC dataset, with a rank-1 accuracy of 69.6% and an mAP of 61.6%.

Learning Gravity Fields of Small Bodies: Self-adaptive Physics-informed Neural Networks

The reconstruction of the gravity field within the surface region of small bodies is crucial for the surface proximity operations of a probe. However, the irregular shape, uneven mass distribution, and sparse gravitational data of small bodies pose challenges in the reconstruction. We propose a self-adaptive physics-informed neural network (PINN) for the reconstruction of the gravity field within the surface region of irregular and heterogeneous small bodies. First, we introduce an auxiliary-point-based data augmentation strategy to reduce the model’s dependency on the quantity of data. Second, we incorporate a residual-based adaptive sampling strategy to enhance the prediction accuracy of the model in regions with significant variations in small-body density. Finally, we introduce an adaptive weight module based on gradient ascent to mitigate the balancing issue of loss terms in the PINN. Experiments indicate that our algorithm achieves improved accuracy for reconstructing the gravity field within the surface region of small bodies. This work is expected to contribute to the enhancement of safety in surface proximity operations around the surfaces of small bodies.

Side-Scan Sonar Image Generation Under Zero and Few Samples for Underwater Target Detection

The acquisition of side-scan sonar (SSS) images is complex, expensive, and time-consuming, making it difficult and sometimes impossible to obtain rich image data. Therefore, we propose a novel image generation algorithm to solve the problem of insufficient training datasets for SSS-based target detection. For zero-sample detection, we proposed a two-step style transfer approach. The ray tracing method was first used to obtain an optically rendered image of the target. Subsequently, UA-CycleGAN, which combines U-net, soft attention, and HSV loss, was proposed for generating high-quality SSS images. A one-stage image-generation approach was proposed for few-sample detection. The proposed ADA-StyleGAN3 incorporates an adaptive discriminator augmentation strategy into StyleGAN3 to solve the overfitting problem of the generative adversarial network caused by insufficient training data. ADA-StyleGAN3 generated high-quality and diverse SSS images. In simulation experiments, the proposed image-generation algorithm was evaluated subjectively and objectively. We also compared the proposed algorithm with other classical methods to demonstrate its advantages. In addition, we applied the generated images to a downstream target detection task, and the detection results further demonstrated the effectiveness of the image generation algorithm. Finally, the generalizability of the proposed algorithm was verified using a public dataset.

Advanced semantic segmentation of aircraft main components based on transfer learning and data-driven approach

Abstract The implementation of Smart Airport and Airport 4.0 visions relies on the integration of automation, artificial intelligence, data science, and aviation technology to enhance passenger experiences and operational efficiency. One essential factor in the integration is the semantic segmentation of the aircraft main components (AMC) perception, which is essential to maintenance, repair, and operations in aircraft and airport operations. However, AMC segmentation has challenges from low data availability, high-quality annotation scarcity, and categorical imbalance, which are common in practical applications, including aviation. This study proposes a novel AMC segmentation solution, employing a transfer learning framework based on a sophisticated DeepLabV3 architecture optimized with a custom-designed Focal Dice Loss function. The proposed solution remarkably suppresses the categorical imbalance challenge and increases the dataset variability with manually annotated images and dynamic augmentation strategies to train a robust AMC segmentation model. The model achieved a notable intersection over union of 84.002% and an accuracy of 91.466%, significantly advancing the AMC segmentation performance. These results demonstrate the effectiveness of the proposed AMC segmentation solution in aircraft and airport operation scenarios. This study provides a pioneering solution to the AMC semantic perception problem and contributes a valuable dataset to the community, which is fundamental to future research on aircraft and airport semantic perception. Graphical abstract

The Differential Effects of Augmented Reality and Product Presentation Strategies on Brand Recall: An Embodied Cognition Perspective

As augmented reality (AR) technology becomes more prevalent in marketing, its impact on consumer memory processes, particularly brand recall, remains underexplored. This study primarily employs an empirical research method, using two lab experiments to examine the interaction between product presentation formats (AR vs. non-AR) and presentation strategies (separate vs. collocation) in brand recall. Across two experiments, we showed that AR enhances brand recall only in collocation presentations, where multiple products are displayed together, but not in separate presentations of individual products. In single-product contexts, AR formats do not demonstrate a significant advantage over non-AR formats. These findings suggest that AR’s effectiveness is contingent on presentation strategy, highlighting the contextual boundaries of AR’s utility in influencing consumer memory. By integrating embodied cognition theory with associative network theory, this research advances our understanding of how immersive technologies shape brand recall, offering strategic insights for marketers seeking to leverage AR in diverse product presentation scenarios.

Experimental study of a distributed active noise control system with multi-device nodes based on augmented diffusion strategy.

Recently, distributed active noise control (DANC) algorithms have been explored as a way to reduce computational complexity while ensuring system stability, thereby outperforming conventional centralized and decentralized algorithms. Most existing DANC algorithms assume that each node has only one pair of loudspeaker and microphone, limiting their flexibility in practical applications. In contrast, this paper proposes a DANC algorithm with general multi-device nodes based on the recently developed augmented diffusion strategy, allowing flexible and scalable ANC applications. A real-time distributed ANC system based on a multi-core digital signal processor platform is developed in order to compare the control performance of the proposed extended augmented diffusion algorithm with that of existing centralized, decentralized and augmented diffusion algorithms. Real-time experiments demonstrate that the proposed algorithm exhibits noise reduction performance consistent with that of the centralized algorithm while achieving lower global computational complexity and avoiding the system instability risk of the decentralized algorithm. Further, the new algorithm improves convergence speed and reduces the global communication cost compared to the previous augmented diffusion algorithm. Experimental results indicate the application potential of the proposed DANC algorithm for a generalized system configuration.

Mixed data augmentation and osprey search strategy for enhancing YOLO in tomato disease, pest, and weed detection

Mixed data augmentation and osprey search strategy for enhancing YOLO in tomato disease, pest, and weed detection

POLYCORE: Polygon-based contour refinement for improved Intravascular Ultrasound Segmentation

Segmentation of the coronary vessel wall in intravascular ultrasound is a fundamental step in guiding coronary intervention. However, it is an challenging task, even for highly skilled cardiologists, due to image artefacts and shadowed regions caused by calcified plaque, guide wires and vessel side branches. Recently, dense-based neural networks have been applied to this task, however, they often fail to predict anatomically plausible contours in these low-signal areas. We propose a novel methodology called Polygon-based Contour Refiner (POLYCORE) that addresses topological error in dense-based segmentation networks using a relational inductive bias through higher-order connections between vertices to learn anatomically rational contours. Our approach remedies the over-smoothing phenomena common in polygon networks by introducing a new vector field refinement module which enables pixel-level detail to be added in an iterative process. POLYCORE is enhanced with augmented polygon aggregation which we show is more effective than typical dense-based test-time augmentation strategies. We achieve state-of-the-art results on two diverse datasets, observing particular improvements when segmenting the lumen structure and in topologically-challenging regions containing shadow artefacts. Our source code is available here: http://orcid.org/https://github.com/kitbransby/POLYCORE.

Synergistic acetyl-CoA augmentation strategy (SATS) for improved terpenoid biosynthesis in Saccharomyces cerevisiae

Terpenoids are widely applied in pharmaceuticals, fragrances and biofuels. Acetyl-CoA, as a crucial precursor in the mevalonate pathway, is stringently regulated intracellularly, thereby limiting the biosynthesis of terpenoids. This study develops a synergistic acetyl-CoA augmentation strategy (SATS) to establish a robust platform for terpenoid biosynthesis in Saccharomyces cerevisiae. Optimizing coenzyme A biosynthesis via global regulation of the pantothenic acid module improved intracellular acetyl-CoA levels by 3.26-fold. Enhancing acetyl phosphate supply was achieved by constructing a PPP-PK-PTA pathway, which improved intracellular acetyl-CoA by 1.92-fold. By combining these techniques, acetyl-CoA levels in the SATS-engineered strain increased by 6.03-fold. The titer of amorpha-4,11-diene, a representative terpenoid, rose by 37.77-fold to 188.45mg/L in shake-flask fermentation and reached 13g/L in a 5L bioreactor. Furthermore, the modified strain exhibited enhanced production of other terpenoids. Our research indicates SATS is an effective approach for synthesizing terpenoids and other acetyl-CoA-derived compounds, demonstrating broad applicability.

A New Augmentation Strategy against Depression Combining SSRIs and the N-terminal Fragment of Galanin (1-15).

Depression is one of the most disabling mental disorders, with the second highest social burden; its prevalence has grown by more than 27% in recent years, affecting 246 million in 2021. Despite the wide range of antidepressants available, more than 50% of patients show treatment-resistant depression. In this review, we summarized the progress in developing a new augmentation strategy based on combining the N-terminal fragment of Galanin (1-15) and SSRI-type antidepressants in animal models.

A Picture May Be Worth a Hundred Words for Visual Question Answering

How far can textual representations go in understanding images? In image understanding, effective representations are essential. Deep visual features from object recognition models currently dominate various tasks, especially Visual Question Answering (VQA). However, these conventional features often struggle to capture image details in ways that match human understanding, and their decision processes lack interpretability. Meanwhile, the recent progress in language models suggests that descriptive text could offer a viable alternative. This paper investigated the use of descriptive text as an alternative to deep visual features in VQA. We propose to process description–question pairs rather than visual features, utilizing a language-only Transformer model. We also explored data augmentation strategies to enhance training set diversity and mitigate statistical bias. Extensive evaluation shows that textual representations using approximately a hundred words can effectively compete with deep visual features on both the VQA 2.0 and VQA-CP v2 datasets. Our qualitative experiments further reveal that these textual representations enable clearer investigation of VQA model decision processes, thereby improving interpretability.

Multi-vendor validation of automated left ventricular analysis from 3D echocardiography using artificial intelligence

Abstract Background Accurate echocardiographic assessment of left ventricular (LV) function is dependent on both image acquisition and analysis. Although 3D echocardiography (3DE) is increasingly recommended for volume quantification, manually derived volumes are limited by operator subjectivity, variable image quality, and the lengthy duration of analysis. Consequently, several automated approaches based on artificial intelligence (AI) have been proposed to segment the LV cavity from 3DE and have demonstrated better accuracy and reproducibility compared to human experts. While the utility of AI models in the clinic depends on their ability to generalise to different populations and ultrasound vendors, the external validation of developed models remains limited. Purpose This study evaluates the ability of an existing AI model trained using data from a single vendor to accurately estimate routine 3DE LV indices in an independent external dataset acquired using equipment from a different vendor. Methods A previously published and internally validated deep learning model for segmentation of the LV cavity and myocardium from 3DE was used to automatically derive LV indices including end-diastolic volume (EDV), end-systolic volume (ESV), LV mass, and ejection fraction (EF) [1]. A second independent dataset consisting of paired 3DE and CMR images from 65 marathon runners from a different centre (using equipment from a different vendor) was subsequently used for external validation. Images from both datasets were subjectively scored from 1 (poor) to 5 (excellent) as a measure of image quality. Agreement with CMR as the reference was assessed using a two-way mixed effects intraclass correlation coefficient (ICC), supplemented by Bland-Altman analysis, to determine the model bias (between 3DE and CMR) and 95% limits of agreement (LOA). To assess whether performance could be improved by inclusion of multi-vendor data during training, the initial model was fine-tuned using a small subset (n=9) of images from the second centre. Results The mean image quality score from the second dataset was 2.5 (± 1.1), which was significantly lower than the mean of 3.4 (± 1.0) from the first dataset. Despite vendor and image quality differences, the initial model produced good agreement with CMR in EDV, ESV, and LV mass but only poor agreement in EF (Fig 1). Fine tuning greatly improved agreement in EF with reduced bias and narrower 95% LOA (Fig 2). Conclusion With the addition of a small number of cases for fine-tuning, AI models for automated LV analysis can achieve good performance analysing 3DE images acquired from a different vendor and population. Advancing model generalisability through more sophisticated data augmentation strategies may enable truly vendor-agnostic automated LV analysis from 3DE.

Intelligent Manufacturing in Wine Barrel Production: Deep Learning-Based Wood Stave Classification

Innovative wood inspection technology is crucial in various industries, especially for determining wood quality by counting rings in each stave, a key factor in wine barrel production. (1) Background: Traditionally, human inspectors visually evaluate staves, compensating for natural variations and characteristics like dirt and saw-induced aberrations. These variations pose significant challenges for automatic inspection systems. Several techniques using classical image processing and deep learning have been developed to detect tree-ring boundaries, but they often struggle with woods exhibiting heterogeneity and texture irregularities. (2) Methods: This study proposes a hybrid approach combining classical computer vision techniques for preprocessing with deep learning algorithms for classification, designed for continuous automated processing. To enhance performance and accuracy, we employ a data augmentation strategy using cropping techniques to address intra-class variability in individual staves. (3) Results: Our approach significantly improves accuracy and reliability in classifying wood with irregular textures and heterogeneity. The use of explainable AI and model calibration offers a deeper understanding of the model’s decision-making process, ensuring robustness and transparency, and setting confidence thresholds for outputs. (4) Conclusions: The proposed system enhances the performance of automatic wood inspection technologies, providing a robust solution for industries requiring precise wood quality assessment, particularly in wine barrel production.

Advancing ketamine in the treatment hierarchy for refractory depression.

Evidence indicates that ketamine is highly effective, has a lower side effect profile and is better tolerated compared to many augmentation strategies for refractory depression. This, combined with data on psychiatric treatment outcome mediators, suggests that earlier intervention with ketamine could improve outcomes for patients suffering from refractory depression.

Comorbidity, Treatment, and Service Utilization Patterns in Difficult-to-Treat Depression Patients: A Retrospective Study in a Portuguese Community Mental Health Team

Background and Objectives: Observational studies with data from real-world clinical practice with patients with difficult-to-treat depression (DTD) are rare. This study aims to collect observational data from the real-world clinical practice of a Portuguese community mental health team (CMHT) on the prevalence of DTD and to explore differences between DTD and non-DTD groups. Materials and Methods: We conducted a retrospective chart review study using data from Electronic Health Records (EHRs) of adult patients with psychiatric disorders followed by a CMHT from the Department of Psychiatry of the Coimbra Local Health Unit (between 1 December 2020–31 December 2022). The Dutch Measure for quantification of Treatment Resistance in Depression (DM-TRD) was used to assess the degree of treatment resistance and the Charlson Comorbidity Index (CCI) to measure medical comorbidity. Results: A quantity of 473 patients were referred to Cantanhede CMHT for a first assessment. Of these, 219 patients met the criteria for a primary diagnosis of any depressive disorder. Assistant psychiatrists identified 57 patients with DTD during follow-up (approximately 26%). The DTD group had higher rates of depressive episodes, greater depression severity, increased service use, higher DM-TRD scores, and a higher prevalence of comorbid anxiety symptoms, personality disorders, and severe medical comorbidities. The DTD group also had a higher prescription rate of antidepressants. Differences were observed in the use of antidepressant augmentation strategies and in the prescription of anticoagulant/antiplatelet drugs and analgesics, with higher prescription rates in the DTD group. We found correlations between DM-TRD and CCI scores, and between DM-TRD scores and all service use variables. Conclusions: Our results are consistent with a similar study in the United Kingdom, highlighting the need for a different approach to the management of DTD patients, who continue to live with a significant burden despite usual pharmacological and non-pharmacological treatments.

Deep learning-powered efficient characterization and quantification of microplastics

Characterizing and quantifying microplastics (MPs) are time-consuming and labor-intensive tasks traditionally. This paper presents an artificial intelligence (AI) framework aiming to automate these tasks by integrating computer vision and deep learning techniques. The approach leverages Fourier Transform Infrared (FTIR) spectra and visual images. Primary novelties of this research involve the development of: (1) an AI framework integrating efforts of data processing, analytics, visualization, and human-computer interaction; (2) a method for transforming FTIR data into contour images; (3) data augmentation strategies for resolving data scarcity and imbalance issues; (4) deep learning models for identifying MPs; (5) computer vision algorithms for quantifying MPs; and (6) an engineer-friendly graphic user interface (GUI) for enhancing data accessibility. The AI framework has been applied to polyethylene, polypropylene, polystyrene, polyamide, ethylene-vinyl acetate, and cellulose acetate. Results confirmed the efficacy of the framework, exhibiting high accuracy scores in classification (98 %), segmentation (99 %), and quantification (96 %) tasks. This research advances the capability of automatic assessment of MPs.

Child, family and professional views on valued communication outcomes for non-verbal children with neurodisability: A qualitative meta-synthesis.

There are many children with neurodisability who are unable to rely on speech to communicate and so use a range of augmentative and alternative communication (AAC) methods and strategies to get their message across. Current instruments designed to measure the outcomes of speech and language therapy interventions lack specific attention to communication outcomes that are valued by non-verbal children with neurodisability, their families and support networks. This qualitative meta-synthesis was conducted to identify valued communication outcomes to inform the next stage of developing a novel outcome measure. To systematically identify and synthesise the qualitative evidence about which communication outcomes non-verbal children with neurodisability, their family members, healthcare professionals and educators think are important to achieve, specifically which communication outcomes are most valued by: (1) non-verbal children with neurodisability; (2) parents or other family members of non-verbal children with neurodisability; and (3) professionals who work with non-verbal children with neurodisability. A systematic search of bibliographic databases and the grey literature was undertaken to identify qualitative studies that included evidence of views expressed by children, family members, healthcare professionals and educators on outcomes in relation to the communication of non-verbal children with neurodisability. All papers meeting the inclusion criteria were quality appraised using the Critical Appraisal Skills Programme Qualitative checklist, although none were excluded on this basis. The data synthesis involved organising coded data into descriptive themes which were then synthesised into analytical themes. We found 47 papers containing qualitative data meeting the inclusion criteria from research situated in 14 countries. The views of 35 children, 183 parents, six other family members, 42 healthcare professionals and 18 educators are represented in the review. The included studies contained very few data reported by children themselves; most data were provided by adults, especially parents. Three main analytical themes were identified: Experiences of communication and expectations; adapting to and acceptance of AAC; and becoming an autonomous communicator. This meta-synthesis brings together the limited qualitative research findings about what parents, professionals and children consider are important communication outcomes for non-verbal children with neurodisability. The synthesis identifies key gaps in our knowledge about the perspectives of children and their siblings. This synthesis will inform primary research to understand valued communication outcomes in this group, and ultimately the development of a patient-reported outcome measure (PROM) that can be used to demonstrate the effect of interventions, at both clinical and service levels. What is already known on the subject Studies of children with cerebral palsy and autism spectrum disorder indicate that at least 25% of children with these conditions are non-verbal. Studies on the health outcomes of children with neurodisability have identified that communication is rated as important by parents and health professionals. There is an evidence gap about which communication outcomes are important to non-verbal children, their families and the people who work with them. What this paper adds to the existing knowledge This is the first synthesis of data that relates to communication outcomes for non-verbal children with neurodisability. This qualitative meta-synthesis identifies from previous research studies the communication outcomes valued by children who are non-verbal, their parents or other family members, and the professionals who work with them. The findings will be used to shape further primary research and the development of a novel patient-reported communication outcome measure for non-verbal children with neurodisability. It is anticipated that this will be used by clinicians to measure the effect of their interventions. What are the practical and clinical implications of this work? Clinicians should reflect on parents' experiences of communication with their child before discussing potential outcomes with them. Gaining insight into the lived experience of communication for non-verbal children and their families will help healthcare professionals to understand which goals are important to them and why. Few studies have specifically asked which communication outcomes are important for non-verbal children with neurodisability. Further exploration is needed to determine which communication outcomes non-verbal children and their families would like to see included in outcome measures used by clinicians.

Assessment of Computer-Aided Translation Quality Based on Large-Scale Corpora

CAT technology, utilizing translation memory and quality control tools, boosts translation efficiency and consistency. Yet, it faces challenges with cultural nuances, context, and creativity, requiring human intervention. This study explores leveraging large-scale corpora to enhance machine translation quality assessment accuracy and efficiency. Automated evaluation models surpass manual limitations, enhancing translation system performance and decision-making. Supervised and unsupervised machine translation quality assessment methods, coupled with data augmentation strategies, reduce model bias by reinforcing the connection between source and target languages. The proposed model achieves 94.8% and 92.6% correctness on Google Translate and Wikipedia datasets, slightly surpassing manual rates. Data augmentation and cascade evaluation notably improve translation evaluation accuracy, especially with large-scale corpora. Future research targets higher-quality pseudo-labeled data, refined evaluation models, and advanced assessment methods for diverse translation needs.