Masked Regions Research Articles

Search anything: segmentation-based similarity search via region prompts

AbstractSearch Anything is presented, a novel approach to perform similarity search in images. In contrast to other approaches to image similarity search, Search Anything enables users to utilize point, box, and text prompts to search for similar regions in a set of images. The region selected by a prompt is automatically segmented, and a binary feature vector is extracted. This feature vector is then used as a query for an image region index, and the images that contain the corresponding regions are returned. Search Anything is trained in a self-supervised manner on mask features extracted by the FastSAM foundation model and semantic features for masked image regions extracted by the CLIP foundation model to learn binary hash code representations for image regions. By coupling these two foundation models, images can be indexed and searched at a more fine-grained level than finding only entire similar images. Experiments on several datasets from different domains in a zero-shot setting demonstrate the benefits of Search Anything as a versatile region-based similarity search approach for images. The efficacy of the approach is further supported by qualitative results. Ablation studies are performed to evaluate how the proposed combination of semantic features and segmentation features together with masking improves the performance of Search Anything over the baseline using CLIP features alone. For large regions, relative improvements of up to 9.87% in mean average precision are achieved. Furthermore, considering context is beneficial for searching small image regions; a context of 3 times an object’s bounding box gives the best results. Finally, we measure computation time and determine storage requirements.

Cardiac Elastography with External Vibration for Quantification of Diastolic Myocardial Stiffness.

Heart failure is an increasing global health problem. Approximately 50% of patients with heart failure have preserved ejection fraction (HFpEF) and concomitant diastolic dysfunction (DD), in part caused by increased myocardial stiffness not detectable by standard echocardiography. While elastography can map tissue stiffness, cardiac applications are currently limited, especially in patients with a higher body mass index (BMI). Therefore, we developed cardiac time-harmonic elastography (THE) to detect abnormal diastolic myocardial stiffness associated with DD. Cardiac THE was developed using standard medical ultrasound and continuous external vibration for regionally resolved mapping of diastolic shear wave speed (SWS) as a proxy for myocardial stiffness. The method was prospectively applied to 54 healthy controls (HC) (26 women), 10 patients with moderate left ventricular hypertrophy (mLVH) (5 women) and 45 patients with wild-type transthyretin amyloidosis (wTTR) (4 women), 20 of whom were treated with tafamidis. 10 healthy participants were re-investigated after 2-6 months to analyze test-retest reproducibility by intraclass correlation coefficients (ICC). Myocardial SWS was measured with good reproducibility (ICC=0.82) and showed higher values in wTTR (3.0±0.7 m/s) than in mLVH (2.1±0.6 m/s) and HCs (1.8±0.3 m/s, all p<0.05). Area-under-the-curve values were 0.991 and 0.737 for discriminating wTTR and mLVH from HCs, respectively. SWS was reduced in patients after tafamidis treatment (2.6±0.6 m/s, p=0.04), suggesting the potential value of THE for therapy monitoring. SWS was quantified in the septum, posterior wall and an automatically masked region (here stated for the septal region). Cardiac THE detects abnormal myocardial stiffness in patients with DD with high penetration depth, independent of BMI and region selection. Based on standard ultrasound components, cardiac THE is cost effective and has the potential to become a point-of-care method for stiffness sensitive echocardiography.

Inequity in Population Exposure to Accelerated Warming

AbstractRecent temperature records have triggered debate about whether global warming is accelerating. Here, we examine for acceleration and explore possible causes for regional differences using gridded surface temperature data. We find that global and regional warming is accelerating, and on average, regions with low Human Development Index (HDI) experienced much higher accelerated warming in comparison to regions with high HDI. However, some regions of low HDI with a large population experienced slow acceleration due to high local aerosol emissions. Since aerosol negative forcing impacts are short‐lived and localized, rapid future reduction of aerosol emissions without a concurrent reduction in GHG emissions could have major compounding impacts. Such a pathway, similar to most 21st century scenarios, could expose a large fraction of the world's most vulnerable people to sudden warming acceleration and heat stress associated impacts. These results call for targeted climate adaptation strategies directing attention to low‐socioeconomic aerosol masked regions.

The effect of the modifiable areal unit problem (MAUP) on spatial aggregation of COVID-19 wastewater surveillance data

Large wastewater-based epidemiology (WBE) projects often have wide coverage and multiple sampling sites, necessitating spatial aggregation for data reporting and interpretation. However, the outcome may be impacted by a type of statistical bias called the modifiable areal unit problem (MAUP). In this study, we examined the presence and extent of the MAUP scaling effect on a New York State COVID-19 wastewater surveillance project. Specifically, we investigated three metrics: 1) the difference in wastewater SARS-CoV-2 concentrations between sampling at city-level site (i.e., city's primary wastewater treatment plant influent stream) and at upstream sampling sites; 2) the correlation between WBE data and clinical indicators at the WWTP-level and the more aggregated county-level; and 3) the proportion of population affected by misalignment of COVID-19 community risk levels at different spatial scales. The results showed that the MAUP can have a negative impact on risk perception by masking regions with high wastewater viral load or COVID-19 community risk level. On the other hand, the MAUP improved the correlation between wastewater surveillance and clinical measures by an average of 26.02 %. This is the first study to investigate the MAUP in the context of WBE and may encourage future WBE projects to consider the implications of the MAUP when interpreting and reporting spatial data, ultimately leading to better data representativeness and accuracy.

Self-supervised learning for chest computed tomography: training strategies and effect on downstream applications.

Self-supervised pre-training can reduce the amount of labeled training data needed by pre-learning fundamental visual characteristics of the medical imaging data. We investigate several self-supervised training strategies for chest computed tomography exams and their effects on downstream applications. We benchmark five well-known self-supervision strategies (masked image region prediction, next slice prediction, rotation prediction, flip prediction, and denoising) on 15M chest computed tomography (CT) slices collected from four sites of the Mayo Clinic enterprise, United States. These models were evaluated for two downstream tasks on public datasets: pulmonary embolism (PE) detection (classification) and lung nodule segmentation. Image embeddings generated by these models were also evaluated for prediction of patient age, race, and gender to study inherent biases in models' understanding of chest CT exams. The use of pre-training weights especially masked region prediction-based weights, improved performance, and reduced computational effort needed for downstream tasks compared with task-specific state-of-the-art (SOTA) models. Performance improvement for PE detection was observed for training dataset sizes as large as with a maximum gain of 5% over SOTA. The segmentation model initialized with pre-training weights learned twice as fast as the randomly initialized model. While gender and age predictors built using self-supervised training weights showed no performance improvement over randomly initialized predictors, the race predictor experienced a 10% performance boost when using self-supervised training weights. We released self-supervised models and weights under an open-source academic license. These models can then be fine-tuned with limited task-specific annotated data for a variety of downstream imaging tasks, thus accelerating research in biomedical imaging informatics.

Small-sample cucumber disease identification based on multimodal self-supervised learning

It is difficult and costly to obtain large-scale, labeled crop disease data in the field of agriculture. How to use small samples of unlabeled data for feature learning has become an urgent problem that needs to be solved. The emergence of self-supervised contrastive learning methods and self-supervised mask learning methods can solve the problem of missing labels on the training data. However, each of these paradigms comes with its own advantages and drawbacks. At the same time, the features learned by dataset in a single modality are limited, ignoring the correlation with other modal information. Hence, this paper introduced an effective framework for multimodal self-supervised learning, denoted as MMSSL, to address the task of identifying cucumber diseases with small sample sizes. Integrating image self-supervised mask learning, image self-supervised contrastive learning, and multimodal image-text contrastive learning, the model can not only learn disease feature information from different modalities, but also capture global and local disease feature information. Simultaneously, the mask learning branch was enhanced by introducing a prompt learning module based on a cross-attention network. This module aided in approximately locating the masked regions in the image data in advance, facilitating the decoder in making accurate decoding predictions. Experimental results demonstrate that the proposed method achieves a 95% accuracy in cucumber disease identification in the absence of labels. The approach effectively uncovers high-level semantic features within multimodal small-sample cucumber disease data. GradCAM is also employed for visual analysis to further understand the decision-making process of the model in disease identification. In conclusion, the proposed method in this paper is advantageous for enhancing the classification accuracy of small-sample cucumber data in a multimodal, unlabeled context, demonstrating good generalization performance.

Transformer Based Pluralistic Image Completion With Reduced Information Loss.

Transformer based methods have achieved great success in image inpainting recently. However, we find that these solutions regard each pixel as a token, thus suffering from an information loss issue from two aspects: 1) They downsample the input image into much lower resolutions for efficiency consideration. 2) They quantize 2563 RGB values to a small number (such as 512) of quantized color values. The indices of quantized pixels are used as tokens for the inputs and prediction targets of the transformer. To mitigate these issues, we propose a new transformer based framework called "PUT". Specifically, to avoid input downsampling while maintaining computation efficiency, we design a patch-based auto-encoder P-VQVAE. The encoder converts the masked image into non-overlapped patch tokens and the decoder recovers the masked regions from the inpainted tokens while keeping the unmasked regions unchanged. To eliminate the information loss caused by input quantization, an Un-quantized Transformer is applied. It directly takes features from the P-VQVAE encoder as input without any quantization and only regards the quantized tokens as prediction targets. Furthermore, to make the inpainting process more controllable, we introduce semantic and structural conditions as extra guidance. Extensive experiments show that our method greatly outperforms existing transformer based methods on image fidelity and achieves much higher diversity and better fidelity than state-of-the-art pluralistic inpainting methods on complex large-scale datasets (e.g., ImageNet).

A new perspective on the diffuse gamma-ray emission excess* *Supported by the National Natural Science Foundation of China (12105292, 12175248, 12393853)

The Large High-Altitude Air Shower Observatory (LHAASO) recently published measurements of diffuse Galactic gamma-ray emission (DGE) in the 10−1000 TeV energy range. The measured DGE flux is significantly higher than the expectation from hadronic interactions between cosmic rays (CRs) and the interstellar medium. This excess has been proposed to originate from unknown extended sources produced by electron radiation, such as pulsar wind nebulae or pulsar halos (PWNe/halos). In this paper, we propose a new perspective to explain the DGE excess observed by LHAASO. The masking regions used in the LHAASO DGE measurement may not fully encompass the extended signals of PWNe/halos. By employing a two-zone diffusion model for electrons around pulsars, we find that the DGE excess in most regions of the Galactic plane can be well explained by the signal leakage model under certain parameters. Our results indicate that this signal leakage from known sources and contributions from unresolved sources should be considered as complementary in explaining the DGE excess.

Automated Method for Growing Rod Length Measurement on Ultrasound Images in Children With Early Onset Scoliosis

ObjectiveTo develop and validate machine learning algorithms to automatically extract the rod length of the magnetically controlled growing rod from ultrasound images (US) in a pilot study. MethodsTwo machine-learning (ML) models, called the "Boundary model" and "Rod model," were developed to identify specific rod segments on ultrasound images. The models were developed utilizing Mask Regional Convolutional Neural Networks (Mask RCNN). Ninety US images were acquired from 23 participants who had early onset scoliosis (EOS) surgeries; among those, 70 were used for model development, including training and validation, and 20 were used for testing by comparing the AI-based vs. manual measurements. ResultsThe average precision (AP) of the ML models was 88.5% and 60.2%, respectively. The inter-method correlation coefficient (ICC) was 0.98, and the mean absolute difference ± standard deviation (MAD ± SD) between AI and manual measurements was 0.86 ± 1.0 mm. The Bland-Altman analysis showed no bias, and 90% of the data were within the 95% confidence interval. The automated method was reliable, accurate, and fast. Measurements were displayed in 4.6 seconds after the US image was inputted. ConclusionThis was the first AI-based method to measure the MCGR rod length on US images automatically.

Multimodal rapid identification of growth stages and discrimination of growth status for Morchella

We introduce a multimodal rapid identification and growth status discrimination method for morchella. Based on the unique biological characteristics and growth environmental requirements of morchella, the efficient and accurate identification of key growth stages of morchella is achieved through the integration of multimodal information acquisition technology. During the rapid identification process of the growth stage of Morchella, the Multi Stage Vision Enhanced Position Encoding Vision Transformer (MS-EP ViT) model is adopted. By introducing multi-stage input embedding, enhanced position encoding, and optimized Transformer Encoder layers, the performance of the model in identifying different growth stages of Morchella mushrooms is significantly improved. In the multimodal Morchella growth state discrimination method, text and image modalities are integrated, a Non downsampled Contourlet Transform Mask Region based Convolutional Neural Network (NSCT Mask R-CNN) model is designed, and a multimodal feature extraction strategy combining Non downsampled Contourlet Transform (NSCT) features with environmental features is explored. This strategy effectively achieves the goals of object detection and instance segmentation, and thus we have accurately evaluated the growth status of Morchella in the later stages of mulberry, young mushroom, and mature. The experimental results show that both models have achieved significant improvements in recognition accuracy and stability, and the rationality of hyperparameter settings has been verified through convergence and parameter sensitivity experiments. Overall, we provide a more accurate and efficient identification method for monitoring the growth of Morchella, which helps to better understand the growth of Morchella and provides scientific basis for optimizing its growth environment.

Ordered Transfer from 3D-Oriented MOF Superstructures to Polymeric Films: Microfabrication, Enhanced Chemical Stability, and Anisotropic Fluorescent Patterns.

Films and patterns of 3D-oriented metal-organic frameworks (MOFs) afford well-ordered pore structures extending across centimeter-scale areas. These macroscopic domains of aligned pores are pivotal to enhance diffusion along specific pathways and orient functional guests. The anisotropic properties emerging from this alignment are beneficial for applications in ion conductivity and photonics. However, the structure of 3D-oriented MOF films and patterns can rapidly degrade under humid and acidic conditions. Thus, more durable 3D-ordered porous systems are desired for practical applications. Here, oriented porous polymer films and patterns are prepared by using heteroepitaxially oriented N3-functionalized MOF films as precursor materials. The film fabrication protocol utilizes an azide-alkyne cycloaddition on the Cu2(AzBPDC)2DABCO MOF. The micropatterning protocol exploits the X-ray sensitivity of azide groups in Cu2(AzBPDC)2DABCO, enabling selective degradation in the irradiated areas. The masked regions of the MOF film retain their N3-functionality, allowing for subsequent cross-linking through azide-alkyne coupling. Subsequent acidic treatment removes the Cu ions from the MOF, yielding porous polymer micro-patterns. The polymer has high chemical stability and shows an anisotropic fluorescent response. The use of 3D-oriented MOF systems as precursors for the fabrication of oriented porous polymers will facilitate the progress of optical components for photonic applications.

Detection of Straw Coverage under Conservation Tillage Based on an Improved Mask Regional Convolutional Neural Network (Mask R-CNN)

Conservation tillage, a crucial method for protecting soil fertility, depends heavily on maintaining adequate straw coverage. The current method of straw coverage detection relies primarily on manual measurement, which is both time-consuming and laborious. This paper introduces a novel straw coverage detection approach based on an improved mask regional convolutional neural network (Mask R-CNN) algorithm. Several images of wheat straw-covered fields were taken, and the dataset was augmented using techniques like image inversion, contrast enhancement, Gaussian noise addition, and translation after cropping the original images. These fields use a crop rotation cycle of wheat and corn. Subsequently, the straw images were annotated using the Labelme annotation tool to obtain the available straw instance segmentation dataset. The Mask R-CNN algorithm was improved by refining the mask generation network structure through a multi-feature fusion strategy, which interweaves features from both the encoder and the mask generation network, enhancing the model’s ability to capture detailed and shape information of the straw. Lastly, using the mask information output by the improved Mask R-CNN algorithm, the straw coverage was calculated by counting the proportion of pixels within each segmented region. In the results, compared to the original Mask R-CNN algorithm, our improved Mask R-CNN algorithm achieved an average improvement of 7.8% in segmentation accuracy, indicating that the improved Mask R-CNN algorithm offers superior segmentation performance. Thus, the new algorithm can achieve straw coverage detection with higher accuracy and can provide a reference for other agricultural applications.

African Lovegrass Segmentation with Artificial Intelligence Using UAS-Based Multispectral and Hyperspectral Imagery

The prevalence of the invasive species African Lovegrass (Eragrostis curvula, ALG thereafter) in Australian landscapes presents significant challenges for land managers, including agricultural losses, reduced native species diversity, and heightened bushfire risks. Uncrewed aerial system (UAS) remote sensing combined with AI algorithms offer a powerful tool for accurately mapping the spatial distribution of invasive species and facilitating effective management strategies. However, segmentation of vegetations within mixed grassland ecosystems presents challenges due to spatial heterogeneity, spectral similarity, and seasonal variability. The performance of state-of-the-art artificial intelligence (AI) algorithms in detecting ALG in the Australian landscape remains unknown. This study compared the performance of four supervised AI models for segmenting ALG using multispectral (MS) imagery at four sites and developed segmentation models for two different seasonal conditions. UAS surveys were conducted at four sites in New South Wales, Australia. Two of the four sites were surveyed in two distinct seasons (flowering and vegetative), each comprised of different data collection settings. A comparative analysis was also conducted between hyperspectral (HS) and MS imagery at a single site within the flowering season. Of the five AI models developed (XGBoost, RF, SVM, CNN, and U-Net), XGBoost and the customized CNN model achieved the highest validation accuracy at 99%. The AI model testing used two approaches: quadrat-based ALG proportion prediction for mixed environments and pixel-wise classification in masked regions where ALG and other classes could be confidently differentiated. Quadrat-based ALG proportion ground truth values were compared against the prediction for the custom CNN model, resulting in 5.77% and 12.9% RMSE for the seasons, respectively, emphasizing the superiority of the custom CNN model over other AI algorithms. The comparison of the U-Net demonstrated that the developed CNN effectively captures ALG without requiring the more intricate architecture of U-Net. Masked-based testing results also showed higher F1 scores, with 91.68% for the flowering season and 90.61% for the vegetative season. Models trained on single-season data exhibited decreased performance when evaluated on data from a different season with varying collection settings. Integrating data from both seasons during training resulted in a reduction in error for out-of-season predictions, suggesting improved generalizability through multi-season data integration. Moreover, HS and MS predictions using the custom CNN model achieved similar test results with around 20% RMSE compared to the ground truth proportion, highlighting the practicality of MS imagery over HS due to operational limitations. Integrating AI with UAS for ALG segmentation shows great promise for biodiversity conservation in Australian landscapes by facilitating more effective and sustainable management strategies for controlling ALG spread.

Face recognition with occluded face using improve intersection over union of region proposal network on Mask region convolutional neural network

Face recognition entails detecting and identifying facial attributes. Mask region convolutional neural network (R-CNN) method is a prominent approach, while prior research predominantly delved into refining loss functions and perfecting object and face detection, recognizing, and identifying faces using imperfect data remained relatively unexplored. This study focuses on an occluded dataset comprising Indonesian faces, wherein 'occluded' denotes facial data that lacks complete visibility-encompassing instances where objects obscure faces or are partially cropped. This investigation involves a deliberate experiment that tailors the intersection over union (IoU) of the region proposal network (RPN) to suit the nuances of occluded Indonesian faces, thereby augmenting accuracy in recognition and segmentation tasks. The innovation IoU in the strategic utilization of Anchors, which involves the exclusion of anchors falling beyond the image borders to optimize computational efficiency. The outcomes of this research are striking; it showcases a remarkable 14.75%, 10.9%, and 12.97% surge based on mean average precision (mAP), mean average recall (mAR), and F1-Scores compared to the conventional Mask R-CNN approach. Notably, our proposed model elevates the average accuracy by 10% to 15% and decreases running time by 21%, a noteworthy enhancement compared to the preceding model. This progress is substantiated by validation utilizing 300 instances dataset, reinforcing the robustness of our approach.

Comprehensive study on the development of an automatic helmet violator detection system (AHVDS) using advanced machine learning techniques

The number of motorcycle accidents has increased rapidly due to different causes. Helmet is a one of the major safety equipment that helps to reduce the fatal accidents even though many of the motorcyclists are not used that. Currently many researchers have focused on traffic violator detection but they are yet to identify the violated person details as it requires high resolution cameras and expensive sensors for number plate extraction. This research article is focused on comprehensive study on the development of an automated helmet violation detection with number plate extraction in real time. This study divides the dataset into rider with helmet, rider without helmet, passenger with helmet and passenger without helmet classes, and four training model was created to detect helmet in rider and passengers. The proposed model was constructed in three stages to attain high accuracy with a vast amount of training dataset. In the first stage, the helmet was detected in the input image using the deep learning object-detection model .In the second stage, if the helmet identification confirmed in the input image then the entire motorcyclist image is segmented based on object segmentation model. In the third stage, number plate training model is deployed into the same object detection and object segmentation model to identify and segment the license plates in the motorcyclist image. This study primarily incorporates the Mask Region based Convolution Neural Networks (Mask R-CNN) for object detection and segmentation Further, it incorporates the three different deep neural networks like Dense block Network (DenseNet-121), Residual Network (ResNet-101) and Inception Residual Network architecture V2layers (Inception Res Net V2) to create accurate helmet violator detections with more extensive information. The experimental results indicates that this comprehensive helmet violator detection study improves the helmet detection accuracy by 6.2 %.In addition, the above three comprehensive proposed models are evaluated under Wilcoxon rank test for better sensitive information. Further, the less object detection loss (2 %) and significant computational time variation (69 %) indicates the performance of the comprehensive helmet violator detection system was good compared to existing study.

Real-time segmentation of short videos under VR technology in dynamic scenes

Abstract This work addresses the challenges of scene segmentation and low segmentation accuracy in short videos by employing virtual reality (VR) technology alongside a 3D DenseNet model for real-time segmentation in dynamic scenes. First, this work extracted short videos by frame and removed redundant background information. Then, the volume rendering algorithm in VR technology was used to reconstruct short videos in dynamic scenes in 3D. It enriched the detailed information of short videos, and finally used the 3D DenseNet model for real-time segmentation of short videos in dynamic scenes, improving the accuracy of segmentation. The experiment compared the performance of High resolution network, Mask region based convolutional neural network, 3D U-Net, Efficient neural network models on the Densely annotation video segmentation dataset. The experimental results showed that the segmentation accuracy of the 3D DenseNet model has reached 99.03%, which was 15.11% higher than that of the ENet model. The precision rate reached 98.33%, and the average segmentation time reached 0.64 s, improving the segmentation accuracy and precision rate. It can adapt to various scene situations and has strong robustness. The significance of this research lies in its innovative approach in tackling these issues. By integrating VR technology with advanced deep learning models, we can achieve more precise segmentation of dynamic scenes in short videos, enabling real-time processing. This has significant practical implications for fields such as video editing, VR applications, and intelligent surveillance. Furthermore, the outcomes of this research contribute to advancing computer vision in video processing, providing valuable insights for the development of future intelligent video processing systems.

ABANet: Attention boundary‐aware network for image segmentation

AbstractDeep learning techniques have attained substantial progress in various face‐related tasks, such as face recognition, face inpainting, and facial expression recognition. To prevent infection or the spread of the virus, wearing of masks in public places has been mandated following the COVID‐19 epidemic, which has led to face occlusion and posed significant challenges for face recognition systems. Most prominent masked face recognition solutions rely on mask segmentation tasks. Therefore, segmentation can be used to mitigate the negative impacts of wearing a mask and improve recognition accuracy. Mask region segmentation suffers from two main problems: there is no standard type of masks that people wear, they come in different colours and designs, and there is no publicly available masked face dataset with appropriate ground truth for the mask region. In order to address these issues, we propose an encoder–decoder framework that utilizes a boundary‐aware attention network combined with a new hybrid loss to provide a map, patch, and pixel‐level supervision. We also introduce a dataset called MFSD, with 11,601 images and 12,758 masked faces for masked face segmentation. Furthermore, we compare the performance of different cutting‐edge deep learning semantic segmentation models on the presented dataset. Experimental results on the MSFD dataset reveal that the suggested approach outperforms state‐of‐the‐art, algorithms with 97.623% accuracy, 93.814% IoU, and 96.817% F1‐score rate. Our dataset of masked faces with mask region labels and source code will be available online.

Enhanced thyroid nodule segmentation through U-Net and VGG16 fusion with feature engineering: A comprehensive study

Background and ObjectiveThe thyroid gland, a key component of the endocrine system, is pivotal in regulating bodily functions. Thermography, a non-invasive imaging technique utilizing infrared cameras, has emerged as a diagnostic tool for thyroid-related conditions, offering advantages such as early detection and risk stratification. Artificial intelligence (AI) has demonstrated success in medical diagnostics, and its integration into thermal imaging analysis holds promise for improving diagnostic capabilities. This study aims to explore the potential of AI, specifically convolutional neural networks (CNNs), in enhancing the analysis of thyroid thermograms for the detection of nodules and abnormalities. MethodsArtificial intelligence (AI) and machine learning techniques are integrated to enhance thyroid thermal image analysis. Specifically, a fusion of U-Net and VGG16, combined with feature engineering (FE), is proposed for accurate thyroid nodule segmentation. The novelty of this research lies in leveraging feature engineering in transfer learning for the segmentation of thyroid nodules, even in the presence of a limited dataset. ResultsThe study presents results from four conducted studies, demonstrating the efficacy of this approach even with a limited dataset. It's observed that in study 4, using FE has led to a significant improvement in the value of the dice coefficient. Even for the small size of the masked region, incorporating radiomics with FE resulted in significant improvements in the segmentation dice coefficient. It's promising that one can achieve higher dice coefficients by employing different models and refining them. ConclusionThe findings here underscore the potential of AI for precise and efficient segmentation of thyroid nodules, paving the way for improved thyroid health assessment.

Large-scale Structures in COSMOS2020: Evolution of Star Formation Activity in Different Environments at 0.4 < z < 4

To study the role of environment in galaxy evolution, we reconstruct the underlying density field of galaxies based on COSMOS2020 (The Farmer catalog) and provide the density catalog for a magnitude-limited (K s < 24.5) sample of ∼210,000 galaxies at 0.4 < z < 5 within the COSMOS field. The environmental densities are calculated using a weighted kernel density estimation approach with the choice of a von Mises–Fisher kernel, an analog of the Gaussian kernel for periodic data. Additionally, we make corrections for the edge effect and masked regions in the field. We utilize physical properties extracted by LePhare to investigate the connection between star formation activity and the environmental density of galaxies in six mass-complete subsamples at different cosmic epochs within 0.4 < z < 4. Our findings confirm a strong anticorrelation between star formation rate (SFR)/specific SFR (sSFR) and environmental density out to z ∼ 1.1. At 1.1 < z < 2, there is no significant correlation between SFR/sSFR and density. At 2 < z < 4, we observe a reversal of the SFR/sSFR–density relation such that both SFR and sSFR increase by a factor of ∼10 with increasing density contrast, δ, from −0.4 to 5. This observed reversal at higher redshifts supports the scenario where an increased availability of gas supply, along with tidal interactions and a generally higher star formation efficiency in dense environments, could potentially enhance star formation activity in galaxies located in rich environments at z > 2.

Automated instance segmentation of asphalt pavement patches based on deep learning

The location and pixel-level information of the patch are all critical data for the quantitative evaluation of pavement conditions. However, obtaining both parch location and pixel-level information simultaneously is a challenge in intelligent pavement patch surveys. This paper proposes a deep-learning-based patch instance segmentation network (PISNet) that employs you only look once (YOLO)v5 as the baseline and adds a semantic segmentation branch to provide an effective solution for this challenge. The proposed PISNet replaces the original backbone CSPDarknet53 and neck of YOLOv5 with a novel feature extractor named symmetrical pyramid network (SPN). The proposed SPN aims at repeating fusion and transfer of shallow semantic features and deep spatial localization features in the order of “FPN-PAN-FPN” such that the multi-scale semantic expression and localization ability of the feature map could be enhanced. Moreover, a modified feature selection module is also incorporated into the SPN as a skip connection to aggregate more spatial details of the feature map while suppressing redundant features. Experimental results show that compared with Mask region convolutional neural network (R-CNN), You only look at coefficients (YOLACT), YOLACT++, EfficientDet, Fully convolutional one stage object detector (FCOS), You only look once version 5m (YOLOv5m), U-Net, DeepLabv3+, and High resolution network-object contextual representations (HRNet-OCR), the proposed PISNet has the best detection performance. Meanwhile, the proposed PISNet achieves superior accuracy/frames per second trade-offs compared to Mask R-CNN, YOLACT, and YOLACT++. Particularly, the proposed PISNet has certain promising potential in supporting pavement patch detection in real-time scenarios and potentially degraded pavement patch detection. Moreover, the proposed PISNet can yield superior segmentation results compared with Mask R-CNN, YOLACT, YOLACT++, U-Net, HRNet-OCR, and DeepLabv3+ on public CRACK500 datasets. Code has been made available at: https://github.com/716HAZ/PISNet .