Domain Mapping Research Articles

Drosophila Adducin facilitates phase separation and function of a conserved spindle orientation complex.

Asymmetric cell division (ACD) allows stem cells to generate differentiating progeny while simultaneously maintaining their own pluripotent state. ACD involves coupling mitotic spindle orientation with cortical polarity cues to direct unequal segregation of cell fate determinants. In Drosophila neural stem cells (neuroblasts; NBs), spindles orient along an apical-basal polarity axis through a conserved complex of Partner of Inscuteable (Pins; human LGN) and Mushroom body defect (Mud; human NuMA). While many details of its function are well known, the molecular mechanics that drive assembly of the cortical Pins/Mud complex remain unclear, particularly with respect to the mutually exclusive Pins complex formed with the apical scaffold protein Inscuteable (Insc). Here we identify Hu li tai shao (Hts; human Adducin) as a direct Mud-binding protein, using an aldolase fold within its head domain (HtsHEAD) to bind a short Mud coiled-coil domain (MudCC) that is adjacent to the Pins-binding domain (MudPBD). Hts is expressed throughout the larval central brain and apically polarizes in mitotic NBs where it is required for Mud-dependent spindle orientation. In vitro analyses reveal that Pins undergoes liquid-liquid phase separation with Mud, but not with Insc, suggesting a potential molecular basis for differential assembly mechanics between these two competing apical protein complexes. Furthermore, we find that Hts binds an intact Pins/Mud complex, reduces the concentration threshold for its phase separation, and alters the liquid-like property of the resulting phase separated droplets. Domain mapping and mutational analyses implicate critical roles for both multivalent interactions (via MudCC oligomerization) and protein disorder (via an intrinsically disordered region in Hts; HtsIDR) in phase separation of the Hts/Mud/Pins complex. Our study identifies a new component of the spindle positioning machinery in NBs and suggests that phase separation of specific protein complexes might regulate ordered assembly within the apical domain to ensure proper signaling output.

The Story Behind the HL7 FHIR to CDISC Mapping Implementation Guide

BackgroundHealth data has become an abundant and rich source of information that can be leveraged for clinical trials. Health Level Seven (HL7) provides standards for health care data, while the Clinical Data Interchange Standards Consortium (CDISC) provides standards for research data. Bridging these worlds and leveraging health data has the potential to enhance knowledge and data quality, while reducing delays and cost in clinical trials.Objectives The aim was to provide an overview of the HL7 Fast Healthcare Interoperability Resources (FHIR®) to CDISC Joint Mapping Implementation Guide (IG) development. The ultimate aim is to increase awareness of this rich resource.MethodsA gap analysis was performed to assess the possibility and feasibility of mapping from FHIR to the CDISC’s Study Data Tabulation Model (SDTM) and Clinical Data Acquisition Standards Harmonization (CDASH) standards. The mapping of CDISC domains commenced using FHIRPath, a path-based navigation and extraction language. The domains mapped were Medical History (MH), Concomitant Medications (CM), Procedures (PR), Vital Signs (VS), Laboratory (LB), Adverse Events (AE), and Demographics (DM). The proposed mappings were evaluated through a formal review process.ResultsThe review process consisted of a CDISC Internal Review and a simultaneous CDISC Public Review and HL7 Ballot Review.  A total of 363 comments were obtained from the following reviews: 1) CDISC Internal Review (268), and 2) simultaneous Public Review (95) - CDISC (37), HL7 (58). The predominant gathered in the review included mapping updates, terminology, and requests for greater detail.ConclusionThe HL7 FHIR® to CDISC Joint Mapping Implementation Guide (IG) provides a rich resource for bridging health care and research standards that can be used with CDISC LB to LOINC mapping guide for leveraging real-world data for clinical trials. The guide assists stakeholders in utilizing health data through the HL7 FHIR® resources to CDISC, CDASH, and SDTM variables. As the community uses this resource, it will continue to mature and potentially expand into new domains.

A Novel Mapper Machine Learning Algorithm for Semantic Domain Mapping for Domain Database Updation

A Novel Mapper Machine Learning Algorithm for Semantic Domain Mapping for Domain Database Updation

Mechanism of orphan subunit recognition during assembly quality control

Cells contain numerous abundant molecular machines assembled from multiple subunits. Imbalances in subunit production and failed assembly generate orphan subunits that are eliminated by poorly defined pathways. Here, we determined how orphan subunits of the cytosolic chaperonin CCT are recognized. Several unassembled CCT subunits recruited the E3 ubiquitin ligase HERC2 using ZNRD2 as an adaptor. Both factors were necessary for orphan CCT subunit degradation in cells, sufficient for CCT subunit ubiquitination with purified factors, and necessary for optimal cell fitness. Domain mapping and structure prediction defined the molecular features of a minimal HERC2-ZNRD2-CCT module. The structural model, whose key elements were validated in cells using point mutants, shows why ZNRD2 selectively recognizes multiple orphaned CCT subunits without engaging assembled CCT. Our findings reveal how failures during CCT assembly are monitored and provide a paradigm for the molecular recognition of orphan subunits, the largest source of quality control substrates in cells.

A glycomic workflow for LC–MS/MS analysis of urine glycosaminoglycan biomarkers in mucopolysaccharidoses

In recent years, several rational designed therapies have been developed for treatment of mucopolysaccharidoses (MPS), a group of inherited metabolic disorders in which glycosaminoglycans (GAGs) are accumulated in various tissues and organs. Thus, improved disease-specific biomarkers for diagnosis and monitoring treatment efficacy are of paramount importance. Specific non-reducing end GAG structures (GAG-NREs) have become promising biomarkers for MPS, as the compositions of the GAG-NREs depend on the nature of the lysosomal enzyme deficiency, thereby creating a specific pattern for each subgroup. However, there is yet no straightforward clinical laboratory platform which can assay all MPS-related GAG-NREs in one single analysis. Here, we developed and applied a GAG domain mapping approach for analyses of urine samples of ten MPS patients with various MPS diagnoses and corresponding aged-matched controls. We describe a nano-LC–MS/MS method of GAG-NRE profiling, utilizing 2-aminobenzamide reductive amination labeling to improve the sensitivity and the chromatographic resolution. Diagnostic urinary GAG-NREs were identified for MPS types IH/IS, II, IIIc, IVa and VI, corroborating GAG-NRE as biomarkers for these known enzyme deficiencies. Furthermore, a significant reduction of diagnostic urinary GAG-NREs in MPS IH (n = 2) and MPS VI (n = 1) patients under treatment was demonstrated. We argue that this straightforward glycomic workflow, designed for the clinical analysis of MPS-related GAG-NREs in one single analysis, will be of value for expanding the use of GAG-NREs as biomarkers for MPS diagnosis and treatment monitoring.

Parameterized Domain Mapping for Order Tracking of Rotating Machinery

Because of the periodicity of vibration signals from the cyclic motion of rotating machinery, many spectrum-based methods are widely applied. However, frequency distortion often occurs under non-stationary conditions, which weakens the effectiveness of spectrum-based methods. Order tracking can overcome the frequency distortion problem, but the instantaneous angular speed is hard to detect, especially under strong noise or with close-spaced frequencies. In this paper, we map the signal into a new domain called the pseudo time domain to eliminate the non-stationarity based on the mechanism of rotating machinery. A parameterized domain mapping function (PDMF) is used to represent the relationship between the time and pseudo time domains. Instead of conducting order tracking after detecting the instantaneous angular speed, we directly optimize the parameter set of the PDMF to construct an appropriate pseudo time domain. A new spectrum concentration indicator considering the continuity of the spectrum is built as the optimization objective. The Legendre polynomial, which shows good approximation property, is applied as the general kernel function of PDMF. Numerical and experimental verification shows good anti-noise performance and the ability to deal with complex and close-spaced frequencies under speed variation or speed fluctuation conditions.

Human Activity Recognition With Low-Resolution Infrared Array Sensor Using Semi-Supervised Cross-Domain Neural Networks for Indoor Environment

Low-resolution infrared-based human activity recognition (HAR) attracted enormous interests due to its low-cost and private. In this paper, a novel semi-supervised crossdomain neural network (SCDNN) based on 8 × 8 low-resolution infrared sensor is proposed for accurately identifying human activity despite changes in the environment at a low-cost. The SCDNN consists of feature extractor, domain discriminator and label classifier. In the feature extractor, the unlabeled and minimal labeled target domain data are trained for domain adaptation to achieve a mapping of the source domain and target domain data. The domain discriminator employs the unsupervised learning to migrate data from the source domain to the target domain. The label classifier obtained from training the source domain data improves the recognition of target domain activities due to the semi-supervised learning utilized in training the target domain data. Experimental results show that the proposed method achieves 92.12% accuracy for recognition of activities in the target domain by migrating the source and target domains. The proposed approach adapts superior to cross-domain scenarios compared to the existing deep learning methods, and it provides a low-cost yet highly adaptable solution for cross-domain scenarios.

Incremental Image De-raining via Associative Memory

While deep learning models have achieved the state-of-the-art performance on single-image rain removal, most methods only consider learning fixed mapping rules on the single synthetic dataset for lifetime. This limits the real-life application as iterative optimization may change mapping rules and training samples. However, when models learn a sequence of datasets in multiple incremental steps, they are susceptible to catastrophic forgetting that adapts to new incremental episodes while failing to preserve previously acquired mapping rules. In this paper, we argue the importance of sample diversity in the episodes on the iterative optimization, and propose a novel memory management method, Associative Memory, to achieve incremental image de-raining. It bridges connections between current and past episodes for feature reconstruction by sampling domain mappings of past learning steps, and guides the learning to trace the current pathway back to the historical environment without storing extra data. Experiments demonstrate that our method can achieve better performance than existing approaches on both inhomogeneous and incremental datasets within the spectrum of highly compact systems.

An Adaptive Parameterized Domain Mapping Method and Its Application in Wheel-Rail Coupled Fault Diagnosis for Rail Vehicles.

The rapid development of cities in recent years has increased the operational pressure of rail vehicles, and due to the characteristics of rail vehicles, including harsh operating environment, frequent starting and braking, resulting in rails and wheels being prone to rail corrugation, polygons, flat scars and other faults. These faults are coupled in actual operation, leading to the deterioration of the wheel-rail contact relationship and causing harm to driving safety. Hence, the accurate detection of wheel-rail coupled faults will improve the safety of rail vehicles' operation. The dynamic modeling of rail vehicles is carried out to establish the character models of wheel-rail faults including rail corrugation, polygonization and flat scars to explore the coupling relationship and characteristics under variable speed conditions and to obtain the vertical acceleration of the axle box. An APDM time-frequency analysis method is proposed in this paper based on the PDMF adopting Rényi entropy as the evaluation index and employing a WOA to optimize the parameter set. The number of iterations of the WOA adopted in this paper is decreased by 26% and 23%, respectively, compared with PSO and SSA, which means that the WOA performs at faster convergence speed and with a more accurate Rényi entropy value. Additionally, TFR obtained using APDM realizes the localization and extraction of the coupled fault characteristics under rail vehicles' variable speed working conditions with higher energy concentration and stronger noise resistance corresponding to prominent ability of fault diagnosis. Finally, the effectiveness of the proposed method is verified using simulation and experimental results that prove the engineering application value of the proposed method.

Clinical Impact of Deep Learning Reconstruction in MRI

Deep learning has been recognized as a paradigm-shifting tool in radiology. Deep learning reconstruction (DLR) has recently emerged as a technology used in the image reconstruction process of MRI, which is an essential procedure in generating MR images. Denoising, which is the first DLR application to be realized in commercial MRI scanners, improves signal-to-noise ratio. When applied to lower magnetic field-strength scanners, the signal-to-noise ratio can be increased without extending the imaging time, and image quality is comparable to that of higher-field-strength scanners. Shorter imaging times decrease patient discomfort and reduce MRI scanner running costs. The incorporation of DLR into accelerated acquisition imaging techniques, such as parallel imaging or compressed sensing, shortens the reconstruction time. DLR is based on supervised learning using convolutional layers and is divided into the following three categories: image domain, k-space learning, and direct mapping types. Various studies have reported other derivatives of DLR, and several have shown the feasibility of DLR in clinical practice. Although DLR efficiently reduces Gaussian noise from MR images, denoising makes image artifacts more prominent, and a solution to this problem is desired. Depending on the training of the convolutional neural network, DLR may change the imaging features of lesions and obscure small lesions. Therefore, radiologists may need to adopt the habit of questioning whether any information has been lost on images that appear clean. ©RSNA, 2023 Quiz questions for this article are available in the supplemental material.

Corpus-Based Metaphorical Framing Analysis: WAR Metaphors in Hong Kong Public Discourse

ABSTRACT This study proposes an operational approach to a metaphorical framing analysis using large-scale data. We conducted a case analysis of how war metaphors are framed to address various societal issues in a corpus of public speeches by Hong Kong government officials. By investigating patterns of lexical choices under the source domain of WAR and the underlying reasons for the source-target domain mappings (i.e. Mapping Principles), we found that the target domain of social issues in Hong Kong is primarily conceptualized in terms of a combat frame, and governmental issues are primarily talked about in terms of a protection frame, both of which are positively evaluated. Additionally, economic issues are primarily addressed in terms of a strategy frame, which is both positively and negatively evaluated. We show that analyzing the Mapping Principles of these conceptual metaphors captures the “selection” process of framing at the dimensions of frame frequency and frame sentiment, allowing for a principled way to propose a metaphorical framing analysis in corpora-based studies. The proposed approach enriches Critical Discourse Analysis studies of metaphorical framing and bridges the link between metaphor analysis at a conceptual level and framing analysis at a communication level.

A novel federated deep learning scheme for glioma and its subtype classification.

Deep learning (DL) has shown promising results in molecular-based classification of glioma subtypes from MR images. DL requires a large number of training data for achieving good generalization performance. Since brain tumor datasets are usually small in size, combination of such datasets from different hospitals are needed. Data privacy issue from hospitals often poses a constraint on such a practice. Federated learning (FL) has gained much attention lately as it trains a central DL model without requiring data sharing from different hospitals. We propose a novel 3D FL scheme for glioma and its molecular subtype classification. In the scheme, a slice-based DL classifier, EtFedDyn, is exploited which is an extension of FedDyn, with the key differences on using focal loss cost function to tackle severe class imbalances in the datasets, and on multi-stream network to exploit MRIs in different modalities. By combining EtFedDyn with domain mapping as the pre-processing and 3D scan-based post-processing, the proposed scheme makes 3D brain scan-based classification on datasets from different dataset owners. To examine whether the FL scheme could replace the central learning (CL) one, we then compare the classification performance between the proposed FL and the corresponding CL schemes. Furthermore, detailed empirical-based analysis were also conducted to exam the effect of using domain mapping, 3D scan-based post-processing, different cost functions and different FL schemes. Experiments were done on two case studies: classification of glioma subtypes (IDH mutation and wild-type on TCGA and US datasets in case A) and glioma grades (high/low grade glioma HGG and LGG on MICCAI dataset in case B). The proposed FL scheme has obtained good performance on the test sets (85.46%, 75.56%) for IDH subtypes and (89.28%, 90.72%) for glioma LGG/HGG all averaged on five runs. Comparing with the corresponding CL scheme, the drop in test accuracy from the proposed FL scheme is small (-1.17%, -0.83%), indicating its good potential to replace the CL scheme. Furthermore, the empirically tests have shown that an increased classification test accuracy by applying: domain mapping (0.4%, 1.85%) in case A; focal loss function (1.66%, 3.25%) in case A and (1.19%, 1.85%) in case B; 3D post-processing (2.11%, 2.23%) in case A and (1.81%, 2.39%) in case B and EtFedDyn over FedAvg classifier (1.05%, 1.55%) in case A and (1.23%, 1.81%) in case B with fast convergence, which all contributed to the improvement of overall performance in the proposed FL scheme. The proposed FL scheme is shown to be effective in predicting glioma and its subtypes by using MR images from test sets, with great potential of replacing the conventional CL approaches for training deep networks. This could help hospitals to maintain their data privacy, while using a federated trained classifier with nearly similar performance as that from a centrally trained one. Further detailed experiments have shown that different parts in the proposed 3D FL scheme, such as domain mapping (make datasets more uniform) and post-processing (scan-based classification), are essential.

A Survey of Methods and Input Data Types for House Price Prediction

Predicting house prices is a challenging task that many researchers have attempted to address. As accurate house prices allow better informing parties in the real estate market, improving housing policies and real estate appraisal, a comprehensive overview of house price prediction strategies is valuable for both research and society. In this work, we present a systematic literature review in order to provide insights with regard to the data types and modeling approaches that have been utilized in the current body of research. As such, we identified 93 articles published between 1992 and 2021 presenting a particular technique for house price prediction. Subsequently, we scrutinized these works and scored them according to model and data novelty. A cluster analysis allowed mapping of the property valuation domain and identification of trends. Although conventional methods and traditional input data remain predominant, house price prediction research is slowly adopting more advanced techniques and innovative data sources. In addition, we identify opportunities to include more advanced input data types such as unstructured data and complex spatial data and to introduce deep learning and tailored methods, which could guide further research.

Data-driven segmentation of cortical calcium dynamics.

Demixing signals in transcranial videos of neuronal calcium flux across the cerebral hemispheres is a key step before mapping features of cortical organization. Here we demonstrate that independent component analysis can optimally recover neural signal content in widefield recordings of neuronal cortical calcium dynamics captured at a minimum sampling rate of 1.5×106 pixels per one-hundred millisecond frame for seventeen minutes with a magnification ratio of 1:1. We show that a set of spatial and temporal metrics obtained from the components can be used to build a random forest classifier, which separates neural activity and artifact components automatically at human performance. Using this data, we establish functional segmentation of the mouse cortex to provide a map of ~115 domains per hemisphere, in which extracted time courses maximally represent the underlying signal in each recording. Domain maps revealed substantial regional motifs, with higher order cortical regions presenting large, eccentric domains compared with smaller, more circular ones in primary sensory areas. This workflow of data-driven video decomposition and machine classification of signal sources can greatly enhance high quality mapping of complex cerebral dynamics.

Free vibration analysis of laminated doubly-curved shells with arbitrary material orientation distribution employing higher order theories and differential quadrature method

In the present work, the dynamic behaviour of laminated anisotropic doubly-curved shells characterized by a generalized distribution of the material orientation angle is investigated employing higher order theories. The structural problem is developed following the Equivalent Single Layer (ESL) methodology, setting up a unified approach for the assessment of the displacement field variable with higher order theories. Accordingly, a generalized three-dimensional distribution of the material orientation angle is associated to each layer of the stacking sequence, accounting for an in-plane bivariate power distribution and out-of-plane symmetric and unsymmetric profiles described with both polynomial and non-polynomial analytical expressions. The fundamental equations are derived from the Hamiltonian Principle, and they are numerically tackled employing the Generalized Differential Quadrature (GDQ) method directly in the strong form. Moreover, a generalized three-dimensional set of linear elastic springs is implemented for the assessment of con-conventional boundary conditions. Furthermore, a generalized isogeometric mapping of the physical domain accounts for arbitrarily-shaped structures. The model is validated successfully with respect to refined three-dimensional classical models, and it is, then, applied systematically to check for the sensitivity of the mechanical response to the structural curvature, external constraints, and material orientation angle distributions.

Mutational screens highlight glycosylation as a modulator of colony-stimulating factor 3 receptor (CSF3R) activity

The colony-stimulating factor 3 receptor (CSF3R) controls the growth of neutrophils, the most abundant type of white blood cell. In healthy neutrophils, signaling is dependent on CSF3R binding to its ligand, CSF3. A single amino acid mutation in CSF3R, T618I, instead allows for constitutive, ligand-independent cell growth and leads to a rare type of cancer called chronic neutrophilic leukemia. However, the disease mechanism is not well understood. Here, we investigated why this threonine to isoleucine substitution is the predominant mutation in chronic neutrophilic leukemia and how it leads to uncontrolled neutrophil growth. Using protein domain mapping, we demonstrated that the single CSF3R domain containing residue 618 is sufficient for ligand-independent activity. We then applied an unbiased mutational screening strategy focused on this domain and found that activating mutations are enriched at sites normally occupied by asparagine, threonine, and serine residues-the three amino acids which are commonly glycosylated. We confirmed glycosylation at multiple CSF3R residues by mass spectrometry, including the presence of GalNAc and Gal-GalNAc glycans at WT threonine 618. Using the same approach applied to other cell surface receptors, we identified an activating mutation, S489F, in the interleukin-31 receptor alpha chain. Combined, these results suggest a role for glycosylated hotspot residues in regulating receptor signaling, mutation of which can lead to ligand-independent, uncontrolled activity and human disease.

Large-scale mapping and mutagenesis of human transcriptional effector domains.

Human gene expression is regulated by more than 2,000 transcription factors and chromatin regulators1,2. Effector domains within these proteins can activate or repress transcription. However, for many of these regulators we do not know what type of effector domains they contain, their location in the protein, their activation and repression strengths, and the sequences that are necessary for their functions. Here, we systematically measure the effector activity of more than 100,000 protein fragments tiling across most chromatin regulators and transcription factors in human cells (2,047 proteins). By testing the effect they have when recruited at reporter genes, we annotate 374 activation domains and 715 repression domains, roughly 80% of which are new and have not been previously annotated3-5. Rational mutagenesis and deletion scans across all the effector domains reveal aromatic and/or leucine residues interspersed with acidic, proline, serine and/or glutamine residues are necessary for activation domain activity. Furthermore, most repression domain sequences contain sites for small ubiquitin-like modifier (SUMO)ylation, short interaction motifs for recruiting corepressors or are structured binding domains for recruiting other repressive proteins. We discover bifunctional domains that can both activate and repress, some of which dynamically split a cell population into high- and low-expression subpopulations. Our systematic annotation and characterization of effector domains provide a rich resource for understanding the function of human transcription factors and chromatin regulators, engineering compact tools for controlling gene expression and refining predictive models of effector domain function.

Rigidity and continuous extension for conformal maps of circle domains

We present sufficient conditions so that a conformal map between planar domains whose boundary components are Jordan curves or points has a continuous or homeomorphic extension to the closures of the domains. Our conditions involve the notions of cofat domains and C N E D CNED sets, i.e., countably negligible for extremal distances, recently introduced by the author. We use this result towards establishing conformal rigidity of a class of circle domains. A circle domain is conformally rigid if every conformal map onto another circle domain is the restriction of a Möbius transformation. We show that circle domains whose point boundary components are C N E D CNED are conformally rigid. This result is the strongest among all earlier works and provides substantial evidence towards the rigidity conjecture of He–Schramm [Invent. Math. 115 (1994), no. 2, 297–310], relating the problems of conformal rigidity and removability.

Co-phase separation of Y14 and RNA in vitro and its implication for DNA repair.

The multifunctional RNA recognition motif-containing protein Y14/RBM8A participates in mRNA metabolism and is essential for the efficient repair of DNA double-strand breaks (DSBs). Y14 contains highly charged, low-complexity sequences in both the amino- and carboxy-terminal domains. The feature of charge segregation suggests that Y14 may undergo liquid-liquid phase separation (LLPS). Recombinant Y14 formed phase-separated droplets, which were sensitive to pH and salt concentration. Domain mapping suggested that LLPS of Y14 involves multivalent electrostatic interactions and is partly determined by the net charge of its low-complexity regions. Phospho-mimicry of the carboxy-terminal arginine-serine dipeptides of Y14 suppressed phase separation. Moreover, RNA could phase separate into Y14 droplets and modulate Y14 LLPS in a concentration-dependent manner. Finally, the capacity of Y14 in LLPS and coacervation with RNA in vitro correlated with its activity in DSB repair. These results reveal a molecular rule for LLPS of Y14 in vitro and an implication for its co-condensation with RNA in genome stability.

A domain specific knowledge extraction transformer method for multisource satellite-borne SAR images ship detection

Multisource satellite-borne synthetic aperture radar (SAR) images have different probability distributions. Traditional supervised learning, consequently, cannot achieve good test performance on one novel satellite-borne SAR dataset while training a good model on another existing satellite-borne SAR dataset. In this article, a domain adaptation (DA) Transformer object detection method is proposed to solve the unlabeled multisource satellite-borne SAR image object detection problem. Unlike existing DA methods based on convolutional neural network (CNN) that focus more on multi-level local feature extraction, we choose to use Vision Transformer (ViT) Faster region CNN (FRCNN) as the baseline network to cope with the extraction of global features of SAR images. Then, two classification tokens are used to learn the mapping of different domains and fully extract domain-specific knowledge, generating two different feature spaces that rely on the original label and pseudo-label to train the source and target domains feature spaces, respectively. Besides, the pseudo-label of target domain is also refined and reconstructed by feature clustering in order to improve the accuracy of target domain knowledge. Finally, the original detection head of FRCNN is employed to detect the target domain SAR image objects. Extensive experiments on image datasets from multisource satellite-borne SAR such as Gaofen-3, TerraSAR-X, Sentinel-1, and RadarSAT-2 show that compared to the other state of the art (SOTA) methods, the proposed method can achieve the greatest object detection accuracy. Especially, taking the recently proposed Transformer-based method as an example, our method has more than 5% improvement in accuracy and more than 16% reduction in training time.