A hybrid demultiplexing strategy that improves performance and robustness of cell hashing.

Cell hashing, a nucleotide barcode-based method that allows users to pool multiple samples and demultiplex in downstream analysis, has gained widespread popularity in single-cell sequencing due to its compatibility, simplicity, and cost-effectiveness. Despite these advantages, the performance of this method remains unsatisfactory under certain circumstances, especially in experiments that have imbalanced sample sizes or use many hashtag antibodies. Here, we introduce a hybrid demultiplexing strategy that increases accuracy and cell recovery in multi-sample single-cell experiments. This approach correlates the results of cell hashing and genetic variant clustering, enabling precise and efficient cell identity determination without additional experimental costs or efforts. In addition, we developed HTOreader, a demultiplexing tool for cell hashing that improves the accuracy of cut-off calling by avoiding the dominance of negative signals in experiments with many hashtags or imbalanced sample sizes. When compared to existing methods using real-world datasets, this hybrid approach and HTOreader consistently generate reliable results with increased accuracy and cell recovery.

MESPool: Molecular Edge Shrinkage Pooling for hierarchical molecular representation learning and property prediction.

Identifying task-relevant structures is important for molecular property prediction. In a graph neural network (GNN), graph pooling can group nodes and hierarchically represent the molecular graph. However, previous pooling methods either drop out node information or lose the connection of the original graph; therefore, it is difficult to identify continuous subtructures. Importantly, they lacked interpretability on molecular graphs. To this end, we proposed a novel Molecular Edge Shrinkage Pooling (MESPool) method, which is based on edges (or chemical bonds). MESPool preserves crucial edges and shrinks others inside the functional groups and is able to search for key structures without breaking the original connection. We compared MESPool with various well-known pooling methods on different benchmarks and showed that MESPool outperforms the previous methods. Furthermore, we explained the rationality of MESPool on some datasets, including a COVID-19 drug dataset.

Multi-task adaptive pooling enabled synergetic learning of RNA modification across tissue, type and species from low-resolution epitranscriptomes.

Post- and co-transcriptional RNA modifications are found to play various roles in regulating essential biological processes at all stages of RNA life. Precise identification of RNA modification sites is thus crucial for understanding the related molecular functions and specific regulatory circuitry. To date, a number of computational approaches have been developed for in silico identification of RNA modification sites; however, most of them require learning from base-resolution epitranscriptome datasets, which are generally scarce and available only for a limited number of experimental conditions, and predict only a single modification, even though there are multiple inter-related RNA modification types available. In this study, we proposed AdaptRM, a multi-task computational method for synergetic learning of multi-tissue, type and species RNA modifications from both high- and low-resolution epitranscriptome datasets. By taking advantage of adaptive pooling and multi-task learning, the newly proposed AdaptRM approach outperformed the state-of-the-art computational models (WeakRM and TS-m6A-DL) and two other deep-learning architectures based on Transformer and ConvMixer in three different case studies for both high-resolution and low-resolution prediction tasks, demonstrating its effectiveness and generalization ability. In addition, by interpreting the learned models, we unveiled for the first time the potential association between different tissues in terms of epitranscriptome sequence patterns. AdaptRM is available as a user-friendly web server from http://www.rnamd.org/AdaptRM together with all the codes and data used in this project.

Adaptive loss-guided multi-stage residual ASPP for lesion segmentation and disease detection in cucumber under complex backgrounds.

BACKGROUND: In complex agricultural environments, the presence of shadows, leaf debris, and uneven illumination can hinder the performance of leaf segmentation models for cucumber disease detection. This is further exacerbated by the imbalance in pixel ratios between background and lesion areas, which affects the accuracy of lesion extraction. RESULTS: An original image segmentation framework, the LS-ASPP model, which utilizes a two-stage Atrous Spatial Pyramid Pooling (ASPP) approach combined with adaptive loss to address these challenges has been proposed. The Leaf-ASPP stage employs attention modules and residual structures to capture multi-scale semantic information and enhance edge perception, allowing for precise extraction of leaf contours from complex backgrounds. In the Spot-ASPP stage, we adjust the dilation rate of ASPP and introduce a Convolutional Attention Block Module (CABM) to accurately segment lesion areas. CONCLUSIONS: The LS-ASPP model demonstrates improved performance in semantic segmentation accuracy under complex conditions, providing a robust solution for precise cucumber lesion segmentation. By focusing on challenging pixels and adapting to the specific requirements of agricultural image analysis, our framework has the potential to enhance disease detection accuracy and facilitate timely and effective crop management decisions.

Protein-Protein Interaction Prediction via Structure-Based Deep Learning.

Protein-protein interactions (PPIs) play an essential role in life activities. Many artificial intelligence algorithms based on protein sequence information have been developed to predict PPIs. However, these models have difficulty dealing with various sequence lengths and suffer from low generalization and prediction accuracy. In this study, we proposed a novel end-to-end deep learning framework, RSPPI, combining residual neural network (ResNet) and spatial pyramid pooling (SPP), to predict PPIs based on the protein sequence physicochemistry properties and spatial structural information. In the RSPPI model, ResNet was employed to extract the structural and physicochemical information from the protein three-dimensional structure and primary sequence; the SPP layer was used to transform feature maps to a single vector and avoid the fixed-length requirement. The RSPPI model possessed excellent cross-species performance and outperformed several state-of-the-art methods based either on protein sequence or gene ontology in most evaluation metrics. The RSPPI model provides a novel strategy to develop an AI PPI prediction algorithm.

Cross-vendor multiparametric mapping of the human brain using 3D-QALAS: A multicenter and multivendor study.

PURPOSE: To evaluate a vendor-agnostic multiparametric mapping scheme based on 3D quantification using an interleaved Look-Locker acquisition sequence with a T2 preparation pulse (3D-QALAS) for whole-brain T1, T2, and proton density (PD) mapping. METHODS: This prospective, multi-institutional study was conducted between September 2021 and February 2022 using five different 3T systems from four prominent MRI vendors. The accuracy of this technique was evaluated using a standardized MRI system phantom. Intra-scanner repeatability and inter-vendor reproducibility of T1, T2, and PD values were evaluated in 10 healthy volunteers (6 men; mean age ± SD, 28.0 ± 5.6 y) who underwent scan-rescan sessions on each scanner (total scans = 100). To evaluate the feasibility of 3D-QALAS, nine patients with multiple sclerosis (nine women; mean age ± SD, 48.2 ± 11.5 y) underwent imaging examination on two 3T MRI systems from different manufacturers. RESULTS: Quantitative maps obtained with 3D-QALAS showed high linearity (R2 = 0.998 and 0.998 for T1 and T2, respectively) with respect to reference measurements. The mean intra-scanner coefficients of variation for each scanner and structure ranged from 0.4% to 2.6%. The mean structure-wise test-retest repeatabilities were 1.6%, 1.1%, and 0.7% for T1, T2, and PD, respectively. Overall, high inter-vendor reproducibility was observed for all parameter maps and all structure measurements, including white matter lesions in patients with multiple sclerosis. CONCLUSION: The vendor-agnostic multiparametric mapping technique 3D-QALAS provided reproducible measurements of T1, T2, and PD for human tissues within a typical physiological range using 3T scanners from four different MRI manufacturers.

Reduction of product composition variability using pooled microbiome ecosystem therapy and consequence in two infectious murine models.

Growing evidence demonstrates the key role of the gut microbiota in human health and disease. The recent success of microbiotherapy products to treat recurrent Clostridioides difficile infection has shed light on its potential in conditions associated with gut dysbiosis, such as acute graft-versus-host disease, intestinal bowel diseases, neurodegenerative diseases, or even cancer. However, the difficulty in defining a "good" donor as well as the intrinsic variability of donor-derived products' taxonomic composition limits the translatability and reproducibility of these studies. Thus, the pooling of donors' feces has been proposed to homogenize product composition and achieve higher taxonomic richness and diversity. In this study, we compared the metagenomic profile of pooled products to corresponding single donor-derived products. We demonstrated that pooled products are more homogeneous, diverse, and enriched in beneficial bacteria known to produce anti-inflammatory short chain fatty acids compared to single donor-derived products. We then evaluated pooled products' efficacy compared to corresponding single donor-derived products in Salmonella and C. difficile infectious mouse models. We were able to demonstrate that pooled products decreased pathogenicity by inducing a structural change in the intestinal microbiota composition. Single donor-derived product efficacy was variable, with some products failing to control disease progression. We further performed in vitro growth inhibition assays of two extremely drug-resistant bacteria, Enterococcus faecium vanA and Klebsiella pneumoniae oxa48, supporting the use of pooled microbiotherapies. Altogether, these results demonstrate that the heterogeneity of donor-derived products is corrected by pooled fecal microbiotherapies in several infectious preclinical models.IMPORTANCEGrowing evidence demonstrates the key role of the gut microbiota in human health and disease. Recent Food and Drug Administration approval of fecal microbiotherapy products to treat recurrent Clostridioides difficile infection has shed light on their potential to treat pathological conditions associated with gut dysbiosis. In this study, we combined metagenomic analysis with in vitro and in vivo studies to compare the efficacy of pooled microbiotherapy products to corresponding single donor-derived products. We demonstrate that pooled products are more homogeneous, diverse, and enriched in beneficial bacteria compared to single donor-derived products. We further reveal that pooled products decreased Salmonella and Clostridioides difficile pathogenicity in mice, while single donor-derived product efficacy was variable, with some products failing to control disease progression. Altogether, these findings support the development of pooled microbiotherapies to overcome donor-dependent treatment efficacy.

Method for high-plex analysis of immune cells in human skin using the GeoMx system.

Specific T cell populations in the skin have been demonstrated as important disease drivers in several dermatoses. Due to the unique skin architecture, these cells are not grouped together in structures but dispersedly spread out throughout the epidermis. Following tissue disruption and isolation, only about 10% of skin T cells are recovered and any in vitro expansion may alter their bona fide phenotype. The Nanostring GeoMx system was developed to address cellular phenotype and protein expression in a tissue spatial context. To do so, regions of interest (ROI) must exceed a certain area threshold (usually 100 µm in diameter) to generate a sufficient signal-to-noise ratio. Here, we present an approach that allows for the pooling of numerous smaller ROIs within the skin, enabling T cell and melanocyte phenotyping. Skin samples from healthy individuals and vitiligo patients were analysed using the GeoMx system and several immune profiling panels. A sufficient signal-to-noise ratio was achieved by pooling smaller ROIs and analysing them as a single group. While this prevents spatial analysis, this method allows for detailed analysis of cells as a population in the context of their physiological environment, making it possible to investigate in situ phenotype of rare cells in different tissue compartments.

Multi-well plate lid for single-step pooling of 96 samples for high-throughput barcode-based sequencing.

High-throughput transcriptomics is of increasing fundamental biological and clinical interest. The generation of molecular data from large collections of samples, such as biobanks and drug libraries, is boosting the development of new biomarkers and treatments. Focusing on gene expression, the transcriptomic market exploits the benefits of next-generation sequencing (NGS), leveraging RNA sequencing (RNA-seq) as standard for measuring genome-wide gene expression in biological samples. The cumbersome sample preparation, including RNA extraction, conversion to cDNA and amplification, prevents high-throughput translation of RNA-seq technologies. Bulk RNA barcoding and sequencing (BRB-seq) addresses this limitation by enabling sample preparation in multi-well plate format. Sample multiplexing combined with early pooling into a single tube reduces reagents consumption and manual steps. Enabling simultaneous pooling of all samples from the multi-well plate into one tube, our technology relies on smart labware: a pooling lid comprising fluidic features and small pins to transport the liquid, adapted to standard 96-well plates. Operated with standard fluidic tubes and pump, the system enables over 90% recovery of liquid in a single step in less than a minute. Large scale manufacturing of the lid is demonstrated with the transition from a milled polycarbonate/steel prototype into an injection molded polystyrene lid. The pooling lid demonstrated its value in supporting high-throughput barcode-based sequencing by pooling 96 different DNA barcodes directly from a standard 96-well plate, followed by processing within the single sample pool. This new pooling technology shows great potential to address medium throughput needs in the BRB-seq workflow, thereby addressing the challenge of large-scale and cost-efficient sample preparation for RNA-seq.

Application of causal inference methods in individual-participant data meta-analyses in medicine: addressing data handling and reporting gaps with new proposed reporting guidelines.

Observational data provide invaluable real-world information in medicine, but certain methodological considerations are required to derive causal estimates. In this systematic review, we evaluated the methodology and reporting quality of individual-level patient data meta-analyses (IPD-MAs) conducted with non-randomized exposures, published in 2009, 2014, and 2019 that sought to estimate a causal relationship in medicine. We screened over 16,000 titles and abstracts, reviewed 45 full-text articles out of the 167 deemed potentially eligible, and included 29 into the analysis. Unfortunately, we found that causal methodologies were rarely implemented, and reporting was generally poor across studies. Specifically, only three of the 29 articles used quasi-experimental methods, and no study used G-methods to adjust for time-varying confounding. To address these issues, we propose stronger collaborations between physicians and methodologists to ensure that causal methodologies are properly implemented in IPD-MAs. In addition, we put forward a suggested checklist of reporting guidelines for IPD-MAs that utilize causal methods. This checklist could improve reporting thereby potentially enhancing the quality and trustworthiness of IPD-MAs, which can be considered one of the most valuable sources of evidence for health policy.

Pooling sputum samples for the Xpert MTB/RIF assay: a practical screening strategy for highly infectious tuberculosis cases.

The Xpert MTB/RIF test (Xpert) can help in the accurate screening of tuberculosis, however, its widespread use is limited by its high cost and lack of accessibility. Pooling of sputum samples for testing is a strategy to cut expenses and enhance population coverage but may result in a decrease in detection sensitivity due to the dilution of Mycobacterium tuberculosis (Mtb) by sample mixing. We investigated how the mixing ratio affected the detection performance of Xpert. We used frozen sputum samples that had been kept after individual Xpert assays of the sputa from Mtb-confirmed TB patients and non-TB patients. Our results showed that the overall sensitivity of the Xpert pooling assay remained higher than 80% when the mixing ratio was between 1/2 and 1/8. When the mixing ratio was raised to 1/16, the positive detection rate fell to 69.0%. For patients with either a high sputum Mtb smear score ≥ 2+, a time-to-positive culture ≤ 10 days, or an Xpert test indicating a high or medium abundance of bacteria, the pooling assay positivity rates were 93.3%, 96.8%, and 100% respectively, even at a 1/16 mixing ratio. For participants with cavities and cough, the pooling assay positivity rates were 86.2% and 90.0% at a 1/8 ratio, higher than for those without these signs. Our results show that the Xpert pooled assay has a high overall sensitivity, especially for highly infectious patients. This pooling strategy with lower reagent and labor costs could support TB screening in communities with limited resources, thereby facilitating reductions in the community transmission and incidence of TB worldwide.

Improved deep neural network (EnhanceNet) for real-time detection of some publicly prohibited items.

Public safety is a critical concern, typically addressed through security checks at entrances of public places, involving trained officers or X-ray scanning machines to detect prohibited items. However, many places like hospitals, schools, and event centres lack such resources, risking security breaches. Even with X-ray scanners or manual checks, gaps can be exploited by individuals with malicious intent, posing significant security risks. Additionally, traditional methods, relying on manual inspections and conventional image processing techniques, are often inefficient and prone to high error rates. To mitigate these risks, we propose a real-time detection model - EnhanceNet using a customized Scale-Enhanced Pooling Network (SEP-Net) integrated into the YOLOv4. The innovative SEP-Net enhances feature representation and localization accuracy, significantly contributing to the model's efficacy in detecting prohibited items. We annotated a custom dataset of nine classes and evaluated our models using different input sizes (608 and 416). The 608 input size achieved a mean Average Precision (mAP) of 74.10% with a detection speed of 22.3 Frames per Second (FPS). The 416 input size showed superior performance, achieving a mAP of 76.75% and a detection speed of 27.1 FPS. These demonstrate that our models are accurate and efficient, making them suitable for real-time applications.

Using natural language processing to facilitate the harmonisation of mental health questionnaires: a validation study using real-world data.

BACKGROUND: Pooling data from different sources will advance mental health research by providing larger sample sizes and allowing cross-study comparisons; however, the heterogeneity in how variables are measured across studies poses a challenge to this process. METHODS: This study explored the potential of using natural language processing (NLP) to harmonise different mental health questionnaires by matching individual questions based on their semantic content. Using the Sentence-BERT model, we calculated the semantic similarity (cosine index) between 741 pairs of questions from five questionnaires. Drawing on data from a representative UK sample of adults (N = 2,058), we calculated a Spearman rank correlation for each of the same pairs of items, and then estimated the correlation between the cosine values and Spearman coefficients. We also used network analysis to explore the model's ability to uncover structures within the data and metadata. RESULTS: We found a moderate overall correlation (r = .48, p < .001) between the two indices. In a holdout sample, the cosine scores predicted the real-world correlations with a small degree of error (MAE = 0.05, MedAE = 0.04, RMSE = 0.064) suggesting the utility of NLP in identifying similar items for cross-study data pooling. Our NLP model could detect more complex patterns in our data, however it required manual rules to decide which edges to include in the network. CONCLUSIONS: This research shows that it is possible to quantify the semantic similarity between pairs of questionnaire items from their meta-data, and these similarity indices correlate with how participants would answer the same two items. This highlights the potential of NLP to facilitate cross-study data pooling in mental health research. Nevertheless, researchers are cautioned to verify the psychometric equivalence of matched items.

Enhancing pooling levels strengthens the risk resilience of healthcare insurance: a case study of basic medical insurance fund operations data in Gansu, China.

BACKGROUND: In China, enhancing the pooling levels of basic health insurance has consistently been regarded as a pivotal measure to promote the refinement of the healthcare insurance system. From 2020 to 2022, the widespread outbreak of COVID-19 posed new challenges to China's basic health insurance. METHODS: The research utilizes Data Envelopment Analysis (DEA), Malmquist index assessment, and fixed-effects panel Tobit models to analyze panel data from 2020 to 2022, assessing the efficiency of basic health insurance in Gansu Province. RESULTS: From 2020 to 2022, the average overall efficiency of the municipal pooling of Basic Medical Insurance for Urban and Rural Residents was 0.941, demonstrating a stable trend with a modest increase. The efficiency frontier regions have expanded from 5 (35.71%) to 7 (50%). Operational efficiency exhibited a negative correlation with per capita hospitalization expenses and per capita fund balance but a positive correlation with per capita accumulated fund balance and reimbursement rates for hospitalized patients. In 2021, compared to 2020, the county-pooling Basic Medical Insurance for Urban Employees saw a decline of 0.126 in overall efficiency, reducing the efficiency frontier regions from 8 to 3. However, from 2021 to 2022, the municipal-coordinated Basic Medical Insurance for Urban Employees experienced a 0.069 increase in overall efficiency, with the efficiency frontier regions expanding from 3 to 5. Throughout 2020 to 2022, the operational efficiency of the Urban Employee Basic Medical Insurance showed a consistent negative correlation with per capita fund balance. CONCLUSION: From 2020 to 2022, the overall operational performance of basic health insurance in Gansu Province was satisfactory, and enhancing the pooling level is beneficial in addressing the impact of unforeseen events on the health insurance system.

High-risk pooling for mitigating risk selection incentives in health insurance markets with sophisticated risk equalization: an application based on health survey information.

BACKGROUND: Despite sophisticated risk equalization, insurers in regulated health insurance markets still face incentives to attract healthy people and avoid the chronically ill because of predictable differences in profitability between these groups. The traditional approach to mitigate such incentives for risk selection is to improve the risk-equalization model by adding or refining risk adjusters. However, not all potential risk adjusters are appropriate. One example are risk adjusters based on health survey information. Despite its predictiveness of future healthcare spending, such information is generally considered inappropriate for risk equalization, due to feasibility challenges and a potential lack of representativeness. METHODS: We study the effects of high-risk pooling (HRP) as a strategy for mitigating risk selection incentives in the presence of sophisticated- though imperfect- risk equalization. We simulate a HRP modality in which insurers can ex-ante assign predictably unprofitable individuals to a 'high risk pool' using information from a health survey. We evaluate the effect of five alternative pool sizes based on predicted residual spending post risk equalization on insurers' incentives for risk selection and cost control, and compare this to the situation without HRP. RESULTS: The results show that HRP based on health survey information can substantially reduce risk selection incentives. For example, eliminating the undercompensation for the top-1% with the highest predicted residual spending reduces selection incentives against the total group with a chronic disease (60% of the population) by approximately 25%. Overall, the selection incentives gradually decrease with a larger pool size. The largest marginal reduction is found moving from no high-risk pool to HRP for the top 1% individuals with the highest predicted residual spending. CONCLUSION: Our main conclusion is that HRP has the potential to considerably reduce remaining risk selection incentives at the expense of a relatively small reduction of incentives for cost control. The extent to which this can be achieved, however, depends on the design of the high-risk pool.

Spindle Detection Based on Elastic Time Window and Spatial Pyramid Pooling.

BACKGROUND: Sleep spindles have emerged as valuable biomarkers for assessing cognitive abilities and related disorders, underscoring the importance of their detection in clinical research. However, template matching-based algorithms using fixed templates may not be able to fully adapt to spindles of different durations. Moreover, inspired by the multiscale feature extraction of images, the use of multiscale feature extraction methods can be used to better adapt to spindles of different frequencies and durations. METHODS: Therefore, this study proposes a novel automatic spindle detection algorithm based on elastic time windows and spatial pyramid pooling (SPP) for extracting multiscale features. The algorithm utilizes elastic time windows to segment electroencephalogram (EEG) signals, enabling the extraction of features across multiple scales. This approach accommodates significant variations in spindle duration and polarization positioning during different EEG epochs. Additionally, spatial pyramid pooling is integrated into a depthwise separable convolutional (DSC) network to perform multiscale pooling on the segmented spindle signal features at different scales. RESULTS: Compared with existing template matching algorithms, this algorithm's spindle wave polarization positioning is more consistent with the real situation. Experimental results conducted on the public dataset DREAMS show that the average accuracy of this algorithm reaches 95.75%, with an average negative predictive value (NPV) of 96.55%, indicating its advanced performance. CONCLUSIONS: The effectiveness of each module was verified through thorough ablation experiments. More importantly, the algorithm shows strong robustness when faced with changes in different experimental subjects. This feature makes the algorithm more accurate at identifying sleep spindles and is expected to help experts automatically detect spindles in sleep EEG signals, reduce the workload and time of manual detection, and improve efficiency.

Additive partially linear model for pooled biomonitoring data.

Human biomonitoring involves monitoring human health by measuring the accumulation of harmful chemicals, typically in specimens like blood samples. The high cost of chemical analysis has led researchers to adopt a cost-effective approach. This approach physically combines specimens and subsequently analyzes the concentration of toxic substances within the merged pools. Consequently, there arises a need for innovative regression techniques to effectively interpret these aggregated measurements. To address this need, a new regression framework is proposed by extending the additive partially linear model (APLM) to accommodate the pooling context. The APLM is well-known for its versatility in capturing the complex association between outcomes and covariates, which is particularly valuable in assessing the complex interplay between chemical bioaccumulation and potential risk factors. Consistent estimators of the APLM are obtained through an iterative process that disaggregates information from the pooled observations. The performance is evaluated through simulations and an environmental health study focused on brominated flame retardants using data from the National Health and Nutrition Examination Survey.

Research on Person Re-Identification through Local and Global Attention Mechanisms and Combination Poolings.

This research proposes constructing a network used for person re-identification called MGNACP (Multiple Granularity Network with Attention Mechanisms and Combination Poolings). Based on the MGN (Multiple Granularity Network) that combines global and local features and the characteristics of the MGN branch, the MGNA (Multiple Granularity Network with Attentions) is designed by adding a channel attention mechanism to each global and local branch of the MGN. The MGNA, with attention mechanisms, learns the most identifiable information about global and local features to improve the person re-identification accuracy. Based on the constructed MGNA, a single pooling used in each branch is replaced by combination pooling to form MGNACP. The combination pooling parameters are the proportions of max pooling and average pooling in combination pooling. Through experiments, suitable combination pooling parameters are found, the advantages of max pooling and average pooling are preserved and enhanced, and the disadvantages of both types of pooling are overcome, so that poolings can achieve optimal results in MGNACP and improve the person re-identification accuracy. In experiments on the Market-1501 dataset, MGNACP achieved competitive experimental results; the values of mAP and top-1 are 88.82% and 95.46%. The experimental results demonstrate that MGNACP is a competitive person re-identification network, and that the attention mechanisms and combination poolings can significantly improve the person re-identification accuracy.

Semantic Segmentation Network Based on Adaptive Attention and Deep Fusion Utilizing a Multi-Scale Dilated Convolutional Pyramid.

Deep learning has recently made significant progress in semantic segmentation. However, the current methods face critical challenges. The segmentation process often lacks sufficient contextual information and attention mechanisms, low-level features lack semantic richness, and high-level features suffer from poor resolution. These limitations reduce the model's ability to accurately understand and process scene details, particularly in complex scenarios, leading to segmentation outputs that may have inaccuracies in boundary delineation, misclassification of regions, and poor handling of small or overlapping objects. To address these challenges, this paper proposes a Semantic Segmentation Network Based on Adaptive Attention and Deep Fusion with the Multi-Scale Dilated Convolutional Pyramid (SDAMNet). Specifically, the Dilated Convolutional Atrous Spatial Pyramid Pooling (DCASPP) module is developed to enhance contextual information in semantic segmentation. Additionally, a Semantic Channel Space Details Module (SCSDM) is devised to improve the extraction of significant features through multi-scale feature fusion and adaptive feature selection, enhancing the model's perceptual capability for key regions and optimizing semantic understanding and segmentation performance. Furthermore, a Semantic Features Fusion Module (SFFM) is constructed to address the semantic deficiency in low-level features and the low resolution in high-level features. The effectiveness of SDAMNet is demonstrated on two datasets, revealing significant improvements in Mean Intersection over Union (MIOU) by 2.89% and 2.13%, respectively, compared to the Deeplabv3+ network.

A Semantic Segmentation Method Based on AS-Unet++ for Power Remote Sensing of Images.

In order to achieve the automatic planning of power transmission lines, a key step is to precisely recognize the feature information of remote sensing images. Considering that the feature information has different depths and the feature distribution is not uniform, a semantic segmentation method based on a new AS-Unet++ is proposed in this paper. First, the atrous spatial pyramid pooling (ASPP) and the squeeze-and-excitation (SE) module are added to traditional Unet, such that the sensing field can be expanded and the important features can be enhanced, which is called AS-Unet. Second, an AS-Unet++ structure is built by using different layers of AS-Unet, such that the feature extraction parts of each layer of AS-Unet are stacked together. Compared with Unet, the proposed AS-Unet++ automatically learns features at different depths and determines a depth with optimal performance. Once the optimal number of network layers is determined, the excess layers can be pruned, which will greatly reduce the number of trained parameters. The experimental results show that the overall recognition accuracy of AS-Unet++ is significantly improved compared to Unet.