Automatic Model Research Articles

Hybrid semantics-based vulnerability detection incorporating a Temporal Convolutional Network and Self-attention Mechanism

Context:Desirable characteristics in vulnerability-detection (VD) systems (VDSs) include both good detection capability (high accuracy, low false positive rate, low false negative rate, etc.) and low time overheads. The widely used VDSs based on models such as Recurrent Neural Networks (RNNs) have some problems, such as low time efficiency, failing to learn the vulnerability features better, and insufficient amounts of vulnerability features. Therefore, it is very important to construct an automatic detection model with high detection accuracy. Objective:This paper reports on training based on the source code to analyze and learn from the code’s patterns and structures by deep-learning techniques to generate an efficient VD model that does not require manual feature design. Method:We propose a software VD model based on multi-feature fusion and deep neural networks called AIdetectorX-SP. It first uses a Temporal Convolutional Network (TCN) and adds a Self-attention Mechanism (SaM) to the TCN to build a model for extracting vulnerability logic features, then transforms the source code into an image input to a Convolutional Neural Network (CNN) to extract structural and semantic information. Finally, we use feature-fusion technology to design and implement an improved deep-learning-based VDS, called AIdetectorX Sequence with Picturization (AIdetectorX-SP). Results:We report on experiments conducted using publicly-available and widely-used datasets to evaluate the effectiveness of AIdetectorX-SP, with results indicating that AIdetectorX-SP is an effective VDS; that the combination of TCN and SaM can effectively extract vulnerability logic features; and that the pictorial code can extract code structure features, which can further improve the VD capability. Conclusion:In this paper, we propose a novel detection model for software vulnerability based on TCNs, SaM, and software picturization. The proposed model solves some shortcomings and limitations of existing VDSs, and obtains a high software-VD accuracy with a high degree of stability.

Unveiling success determinants for AMB-assisted phase expansion of fusion proteins in ARP/wARP

Fusion proteins (FPs) are frequently utilized as a biotechnological tool in the determination of macromolecular structures using X-ray methods. Here, we explore the use of different protein tags in various FP, to obtain initial phases by using them in a partial molecular replacement (MR) and constructing the remaining FP structure with ARP/wARP. Usually, the tag is removed prior to crystallization, however leaving the tag on may facilitate crystal formation, and structural determination by expanding phases from known to unknown segments of the complex. In this study, the Protein Data Bank was mined for an up-to-date list of FPs with the most used protein tags, Maltose Binding Protein (MBP), Green Fluorescent Protein (GFP), Thioredoxin (TRX), Glutathione transferase (GST) and the Small Ubiquitin-like Modifier Protein (SUMO). Partial MR using the protein tag, followed by automatic model building, was tested on a subset of 116 FP. The efficiency of this method was analyzed and factors that influence the coordinate construction of a substantial portions of the fused protein were identified. Using MBP, GFP, and SUMO as phase generators it was possible to build at least 75 % of the protein of interest in 36 of the 116 cases tested. Our results reveal that tag selection has a significant impact; tags with greater structural stability, such as GFP, increase the success rate. Further statistical analysis identifies that resolution, Wilson B factor, solvent percentage, completeness, multiplicity, protein tag percentage in the FP (considering amino acids), and the linker length play pivotal roles using our approach. In cases where a structural homologous is absent, this method merits inclusion in the toolkit of protein crystallographers.

Argumentation and discourse analysis in the future intelligent systems of essay grading

Intelligent systems of essay grading constitute important tools for educational technologies. They can significantly replace the manual scoring efforts and provide instructional feedback as well. These systems typically include two main parts: feature extractor and automatic grading model. The latter is generally based on computational and artificial intelligent methods. In this work, we focus on the features extraction part. More precisely, we focus on argumentation and discourse related-features, which constitute high level features. We discuss some state-of-the-art systems and analyse how argumentation and discourse analysis are used for extracting features and providing feedback.

An automatic humor identification model with novel features from Berger’s typology and ensemble models

Humor identification in text is essential for natural language understanding, impacting human–computer interactions and emotion recognition. This study introduces a novel approach to automatic humor identification in text using ensemble learning techniques. The objective is to classify text into two categories: humor and not humor. This research delves into humor detection in customer reviews, focusing on specific domains, and leverages diverse text features, including novel features derived from Berger’s typology. State-of-the-art machine learning models, such as Support Vector Machine, Multilayer Perceptron, and Naïve Bayes, are employed. The study conducts an in-depth analysis of the Yelp review dataset, evaluating the performance of various ensemble learning methods. The proposed approach demonstrates exceptional results, achieving an 83.32% F-score with the Support Vector Machine classifier and an 85.68% accuracy using the stacking-based ensemble learning method with Random Forest on the Yelp Review dataset. Furthermore, this research includes an ablation study to assess the effectiveness of Berger’s novel typology-based features in humor identification. This research contributes to the advancement of humor identification in text and highlights the effectiveness of ensemble learning techniques, especially when incorporating novel features inspired by Berger’s typology.

Development and application of financial statement filing robot based on RPA technology

The constant development and application of new technologies, such as big data, artificial intelligence and the mobile Internet, have profoundly changed the personal and professional spheres. Despite these advances, finance professionals are still faced with a multitude of routine, repetitive and error-prone tasks. At the same time, they are challenged by the shift to management accounting, resulting in reduced productivity. This paper addresses these issues by introducing a financial statement filing robot developed using Robotic Process Automation (RPA) technology. The application of this robot has been shown to provide superior efficiency and accuracy, reduce the heavy burden of routine tasks, and facilitate a smooth transition to management accounting practices. In addition, this research provides a valuable reference for the application and diffusion of RPA technology in the financial sector. Given the large amount of text data generated by financial processes, this paper proposes an automatic text categorization model. The effectiveness of the model is demonstrated as a response to address the challenges encountered in the consultation and archiving process. This contribution informs the development of text categorization robots tailored to the needs of finance professionals.

Abstract 7387: Fully automated segmentation and volumetric measurement of intracranial meningioma using deep learning

Abstract Most intracranial meningiomas are small, asymptomatic, and incidentally found tumors. Since the growth of meningioma is the principal indication of treatment, accurate and rapid measurement of the volume of intracranial meningiomas is essential in clinical practice to determine the growth rate of the tumor. It could be useful for the management of meningiomas given their increasing incidence and the wait-and-see policy currently in use for asymptomatic meningiomas. The aim of this study was to develop and validate a computational model for fully automated meningioma segmentation and volume measurement on contrast-enhanced MR scans using deep learning. The retrospectively collected axial contrast-enhanced T1-weighted section images from patients diagnosed with meningioma were manually segmented and used to construct automatic segmentation models with six U-Net- and nnU-Net-based architectures. The performance of each model was evaluated with the Sørensen-Dice similarity coefficient (DSC) with internal (IVS) and external validation sets (EVS), each consisting of 100 independent MRI examinations. A total of 12,909 section images from 459 patients were applied for the training (median age 58 [52-66] [IQR]; 385 women [83.9%]). The median tumor volume of the training set was 2.36 cm3. A 2D nnU-Net showed the highest median DSCs of 0.922 and 0.893 for the IVS and EVS, respectively. The nnU-Nets achieved superior performance in meningioma segmentation than the U-Nets. The DSCs of the 2D nnU-Net for small meningiomas less than 1 cm3 were 0.769 and 0.780 with the IVS and EVS, respectively. We successfully developed a fully automated and accurate volumetric measurement tool for meningioma using nnU-Net. The volumetry performance for small meningioma was significantly better than that achieved in previous studies. The results of this study are clinically applicable and are expected to be of great use in the management of monitored meningioma patients. Citation Format: Ho Kang, Joseph N. Witanto, Kevin Pratama, Doohee Lee, Kyu Sung Choi, Seung Hong Choi, Min-Sung Kim, Jin Wook Kim, Yong Hwy Kim, Sang Joon Park, Chul-Kee Park. Fully automated segmentation and volumetric measurement of intracranial meningioma using deep learning [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 7387.

GFSegNet: A multi-scale segmentation model for mining area ground fissures

Precise identification of ground fissures is of paramount importance for the safety and environmental management of coal mining areas. However, the surface environment in coal mining regions is complex, and, to date, the efficiency of artificial fissure detection has been relatively low. Therefore, we have proposed a ground fissure automatic identification model based on an encoder–decoder architecture known as the Ground Fissure Segmentation Network (GFSegNet). The encoder adopts a deep-shallow decoupled mode. The shallow network achieves spatial and spectral domain interaction by introducing adaptive Fourier convolution. The deep network adopts a hierarchical Transformer with an efficient self-attention mechanism for global modeling of fine-grained semantics. The decoder is designed as a multi-scale feature fusion structure embedded in pyramid pooling modules, aiming to efficiently utilize multi-scale ground fissure information. To advance the application of deep learning in ground fissure identification, we created a coal mining area ground fissure segmentation dataset from drone imagery, known as the mine ground fissure unmanned aerial vehicle dataset (MGF-UAV). On this dataset, the overall performance of GFSegNet surpasses the current leading segmentation models, and its reliability and generalization capabilities are further validated on additional datasets (Crack500, DeepCrack, CrackForest and ISPRS-Postdam). This research has brought expansion and innovation to the field of automatic ground fissure recognition in coal mining areas, offering new perspectives and methodologies for the application of deep learning techniques in this domain.

Abstract 887: Fast, interactive, AI-assisted 3D lung tumour segmentation

Abstract Segmentation of lung tumors is an important step in the planning of clinical treatment and operative procedures. Automatic segmentation of advanced lung tumors is challenging due to local invasion and heterogeneous metastasis. Fully automatic deep learning models often fail to accurately delineate advanced disease boundaries and do not allow the user to provide hints to improve segmentation performance. In contrast, interactive segmentation accepts user inputs and is an efficient way to segment lesions while reducing radiologist effort. This paper describes an interactive segmentation approach for lung lesion segmentation in CT scans. Our pipeline is built atop the SwinUNETR neural network architecture and can be expanded to support alternate models. The backbone model accepts radiologists' hints in the form of mouse clicks that indicate whether a location on the scan corresponds to a lesion. Our approach has the following novel contributions: (1) Context-aware encoding of guidance clicks by combining geodesic and Gaussian smoothing, resulting in improved segmentation of lesion boundaries. (2) An iterative prompting strategy to achieve higher accuracy with fewer clicks at inference time. (3) Guidance-aware Conditional Random Fields to refine the produced segmentation masks. (4) Volume cropping around guidance clicks at inference to improve segmentation precision and inference speed. (5) Linearly scaling our approach on multiple GPUs, to improve inference speed. On a public non-small cell lung cancer dataset predominantly containing advanced stage cancers (68\% stage III, and 27\% stage IV), our interactive approach delivers a Dice score of 0.74 with a single click, a 21\% improvement from the fully automatic approach (Dice Score = 0.61), and a Dice score of 0.81 with 5 clicks, which is a 33\% improvement. Inference speed is an important metric for an interactive pipeline. On a typical 350 $\times$ 350 $\times$ 150 voxel chest CT scan volume, our interactive approach infers 5 times faster than the original fully automated approach on a single GPU. After scaling to 4 GPUs, we infer in only 0.5 seconds; 20 times faster than the original approach. Qualitative evaluation from three independent radiologists indicates that our interactive pipeline significantly improved their standard clinical segmentation experience. Citation Format: Mayank Patwari, Yi Wei, Meng Xu, Zhenning Zhang, Konstantinos Sidiropoulos, Balaji Selvaraj, Georgia Hughes, Nadine Garibli, Kamsiriochukwu Ojiako, Mohan Lella, Leon Fedden, James Parkin, Michael Parker, Shaneil Patel, Qin Li, Kedar Patwardhan. Fast, interactive, AI-assisted 3D lung tumour segmentation [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 887.

An automatic diagnosis model of otitis media with high accuracy rate using transfer learning.

Introduction: Chronic Suppurative Otitis Media (CSOM) and Middle Ear Cholesteatoma are two common chronic otitis media diseases that often cause confusion among physicians due to their similar location and shape in clinical CT images of the internal auditory canal. In this study, we utilized the transfer learning method combined with CT scans of the internal auditory canal to achieve accurate lesion segmentation and automatic diagnosis for patients with CSOM and middle ear cholesteatoma. Methods: We collected 1019 CT scan images and utilized the nnUnet skeleton model along with coarse grained focal segmentation labeling to pre-train on the above CT images for focal segmentation. We then fine-tuned the pre-training model for the downstream three-classification diagnosis task. Results: Our proposed algorithm model achieved a classification accuracy of 92.33% for CSOM and middle ear cholesteatoma, which is approximately 5% higher than the benchmark model. Moreover, our upstream segmentation task training resulted in a mean Intersection of Union (mIoU) of 0.569. Discussion: Our results demonstrate that using coarse-grained contour boundary labeling can significantly enhance the accuracy of downstream classification tasks. The combination of deep learning and automatic diagnosis of CSOM and internal auditory canal CT images of middle ear cholesteatoma exhibits high sensitivity and specificity.

Adversarial Attacks on Medical Segmentation Model via Transformation of Feature Statistics

Deep learning-based segmentation models have made a profound impact on medical procedures, with U-Net based computed tomography (CT) segmentation models exhibiting remarkable performance. Yet, even with these advances, these models are found to be vulnerable to adversarial attacks, a problem that equally affects automatic CT segmentation models. Conventional adversarial attacks typically rely on adding noise or perturbations, leading to a compromise between the success rate of the attack and its perceptibility. In this study, we challenge this paradigm and introduce a novel generation of adversarial attacks aimed at deceiving both the target segmentation model and medical practitioners. Our approach aims to deceive a target model by altering the texture statistics of an organ while retaining its shape. We employ a real-time style transfer method, known as the texture reformer, which uses adaptive instance normalization (AdaIN) to change the statistics of an image’s feature.To induce transformation, we modify the AdaIN, which typically aligns the source and target image statistics. Through rigorous experiments, we demonstrate the effectiveness of our approach. Our adversarial samples successfully pass as realistic in blind tests conducted with physicians, surpassing the effectiveness of contemporary techniques. This innovative methodology not only offers a robust tool for benchmarking and validating automated CT segmentation systems but also serves as a potent mechanism for data augmentation, thereby enhancing model generalization. This dual capability significantly bolsters advancements in the field of deep learning-based medical and healthcare segmentation models.

Reliable automatic sleep stage classification based on hybrid intelligence

Sleep staging is a vital aspect of sleep assessment, serving as a critical tool for evaluating the quality of sleep and identifying sleep disorders. Manual sleep staging is a laborious process, while automatic sleep staging is seldom utilized in clinical practice due to issues related to the inadequate accuracy and interpretability of classification results in automatic sleep staging models. In this work, a hybrid intelligent model is presented for automatic sleep staging, which integrates data intelligence and knowledge intelligence, to attain a balance between accuracy, interpretability, and generalizability in the sleep stage classification. Specifically, it is built on any combination of typical electroencephalography (EEG) and electrooculography (EOG) channels, including a temporal fully convolutional network based on the U-Net architecture and a multi-task feature mapping structure. The experimental results show that, compared to current interpretable automatic sleep staging models, our model achieves a Macro-F1 score of 0.804 on the ISRUC dataset and 0.780 on the Sleep-EDFx dataset. Moreover, we use knowledge intelligence to address issues of excessive jumps and unreasonable sleep stage transitions in the coarse sleep graphs obtained by the model. We also explore the different ways knowledge intelligence affects coarse sleep graphs by combining different sleep graph correction methods. Our research can offer convenient support for sleep physicians, indicating its significant potential in improving the efficiency of clinical sleep staging.

Meibomian glands segmentation in infrared images with limited annotation.

To investigate a pioneering framework for the segmentation of meibomian glands (MGs), using limited annotations to reduce the workload on ophthalmologists and enhance the efficiency of clinical diagnosis. Totally 203 infrared meibomian images from 138 patients with dry eye disease, accompanied by corresponding annotations, were gathered for the study. A rectified scribble-supervised gland segmentation (RSSGS) model, incorporating temporal ensemble prediction, uncertainty estimation, and a transformation equivariance constraint, was introduced to address constraints imposed by limited supervision information inherent in scribble annotations. The viability and efficacy of the proposed model were assessed based on accuracy, intersection over union (IoU), and dice coefficient. Using manual labels as the gold standard, RSSGS demonstrated outcomes with an accuracy of 93.54%, a dice coefficient of 78.02%, and an IoU of 64.18%. Notably, these performance metrics exceed the current weakly supervised state-of-the-art methods by 0.76%, 2.06%, and 2.69%, respectively. Furthermore, despite achieving a substantial 80% reduction in annotation costs, it only lags behind fully annotated methods by 0.72%, 1.51%, and 2.04%. An innovative automatic segmentation model is developed for MGs in infrared eyelid images, using scribble annotation for training. This model maintains an exceptionally high level of segmentation accuracy while substantially reducing training costs. It holds substantial utility for calculating clinical parameters, thereby greatly enhancing the diagnostic efficiency of ophthalmologists in evaluating meibomian gland dysfunction.

FVCNet: Detection obstacle method based on feature visual clustering network in power line inspection

AbstractPower line inspection is an important means to eliminate hidden dangers of power lines. It is a difficult research problem how to solve the low accuracy of power line inspection based on deep neural network (DNN) due to the problems of multi‐view‐shape, small‐size object. In this paper, an automatic detection model based on Feature visual clustering network (FVCNet) for power line inspection is established. First, an unsupervised clustering method for power line inspection is proposed, and applied to construct a detection model which can recognize multi‐view‐shape objects and enhanced object features. Then, the bilinear interpolation method is used to Feature enhancement method, and the enhanced high‐level semantics and low‐level semantics are fused to solve the problems of small object size and single sample. In this paper, FVCNet is applied to the MS‐COCO 2017 data set and self‐made power line inspection data set, and the test accuracy is increased to 61.2% and 82.0%, respectively. Compared with other models, especially for the categories that are greatly affected by multi‐view‐shape, the test accuracy has been improved significantly.

Advertisement Synthesis Network for Automatic Advertisement Image Synthesis

Image advertising is widely used by companies to advertise their products and increase awareness of their brands. With the constant development of image generation techniques, automatic compositing of advertisement images has also been widely studied. However, the existing algorithms cannot synthesise consistent-looking advertisement images for a given product. The key challenge is to stitch a given product into a scene that matches the style of the product while maintaining a consistent-looking. To solve this problem, this paper proposes a new two-stage automatic advertisement image generation model, called Advertisement Synthesis Network (ASNet), which explores a two-stage generation framework to synthesise consistent-looking product advertisement images. Specifically, ASNet first generates a preliminary target product scene using Pre-Synthesis and then extracts scene features using Pseudo-Target Object Encoder (PTOE) and true target features using Real Target Object Encoder (RTOE), respectively. Finally, we inject the acquired features into the pretrained diffusion model and reconstruct them in the preliminary generated target goods scene. Extensive experiments have shown that the method achieves better results in all three performance metrics related to the quality of the synthesised image compared to other methods. In addition, we have done a simple and preliminary study on the effect of synthetic advertisement images on real consumers’ purchase intention and brand perception. The results of the study show that the advertisement images synthesised by the model proposed in this paper have a positive impact on consumer purchase intention and brand perception.

Diffusion-/perfusion-weighted imaging fusion to automatically identify stroke within 4.5 h

ObjectivesWe aimed to develop machine learning (ML) models based on diffusion- and perfusion-weighted imaging fusion (DP fusion) for identifying stroke within 4.5 h, to compare them with DWI- and/or PWI-based ML models, and to construct an automatic segmentation-classification model and compare with manual labeling methods.MethodsML models were developed from multimodal MRI datasets of acute stroke patients within 24 h of clear symptom onset from two centers. The processes included manual segmentation, registration, DP fusion, feature extraction, and model establishment (logistic regression (LR) and support vector machine (SVM)). A segmentation-classification model (X-Net) was proposed for automatically identifying stroke within 4.5 h. The area under the receiver operating characteristic curve (AUC), sensitivity, Dice coefficients, decision curve analysis, and calibration curves were used to evaluate model performance.ResultsA total of 418 patients (≤ 4.5 h: 214; > 4.5 h: 204) were evaluated. The DP fusion model achieved the highest AUC in identifying the onset time in the training (LR: 0.95; SVM: 0.92) and test sets (LR: 0.91; SVM: 0.90). The DP fusion-LR model displayed consistent positive and greater net benefits than other models across a broad range of risk thresholds. The calibration curve demonstrated the good calibration of the DP fusion-LR model (average absolute error: 0.049). The X-Net model obtained the highest Dice coefficients (DWI: 0.81; Tmax: 0.83) and achieved similar performance to manual labeling (AUC: 0.84).ConclusionsThe automatic segmentation-classification models based on DWI and PWI fusion images had high performance in identifying stroke within 4.5 h.Clinical relevance statementPerfusion-weighted imaging (PWI) fusion images had high performance in identifying stroke within 4.5 h. The automatic segmentation-classification models based on DWI and PWI fusion images could provide clinicians with decision-making guidance for acute stroke patients with unknown onset time.Key Points• The diffusion/perfusion-weighted imaging fusion model had the best performance in identifying stroke within 4.5 h.• The X-Net model had the highest Dice and achieved performance close to manual labeling in segmenting lesions of acute stroke.• The automatic segmentation-classification model based on DP fusion images performed well in identifying stroke within 4.5 h.

Convolutional neural network model for the qualitative evaluation of geometric shape of carrot root

The main objective of the study is the development of an automatic carrot root classification model, marked as CR-NET, with the use of a Convolutional Neural Network (CNN). CNN with a constant architecture was built, consistingof an alternating arrangement of five Conv2D, MaxPooling2D and Dropout classes, for which in the Python 3.9 programming language a calculation algorithm was developed. It was found that the classification process of the carrot root images was carried out with an accuracy of 89.06%, meaning that 50 images were misclassified. The highest number of 21 erroneously classified photographs were from the extra class, of which 15 to the first class, thus not resulting in significant loss. However, assuming the number of refuse as the classification basis, the model accuracy greatly increases to 98.69%, as only 6 photographs were erroneously assigned.

Emotion recognition based on microstate analysis from temporal and spatial patterns of electroencephalogram.

Recently, the microstate analysis method has been widely used to investigate the temporal and spatial dynamics of electroencephalogram (EEG) signals. However, most studies have focused on EEG at resting state, and few use microstate analysis to study emotional EEG. This paper aims to investigate the temporal and spatial patterns of EEG in emotional states, and the specific neurophysiological significance of microstates during the emotion cognitive process, and further explore the feasibility and effectiveness of applying the microstate analysis to emotion recognition. We proposed a KLGEV-criterion-based microstate analysis method, which can automatically and adaptively identify the optimal number of microstates in emotional EEG. The extracted temporal and spatial microstate features then served as novel feature sets to improve the performance of EEG emotion recognition. We evaluated the proposed method on two publicly available emotional EEG datasets: the SJTU Emotion EEG Dataset (SEED) and the Database for Emotion Analysis using Physiological Signals (DEAP). For the SEED dataset, 10 microstates were identified using the proposed method. These temporal and spatial features were fed into AutoGluon, an open-source automatic machine learning model, yielding an average three-class accuracy of 70.38% (±8.03%) in subject-dependent emotion recognition. For the DEAP dataset, the method identified 9 microstates. The average accuracy in the arousal dimension was 74.33% (±5.17%) and 75.49% (±5.70%) in the valence dimension, which were competitive performance compared to some previous machine-learning-based studies. Based on these results, we further discussed the neurophysiological relationship between specific microstates and emotions, which broaden our knowledge of the interpretability of EEG microstates. In particular, we found that arousal ratings were positively correlated with the activity of microstate C (anterior regions of default mode network) and negatively correlated with the activity of microstate D (dorsal attention network), while valence ratings were positively correlated with the activity of microstate B (visual network) and negatively correlated with the activity of microstate D (dorsal attention network). In summary, the findings in this paper indicate that the proposed KLGEV-criterion-based method can be employed to research emotional EEG signals effectively, and the microstate features are promising feature sets for EEG-based emotion recognition.

A conceptual design approach for mega-latticed structures based on combinatorial equilibrium modelling

In this paper, a novel equilibrium-based form-finding approach for a mega-latticed structure is presented based on vector-based 3D graphic statics and the Combinatorial Equilibrium Modelling (CEM). This approach can be effectively applied to the conceptual design phase of the structures with various design objectives under conservative loads. It allows us to adjust the design parameters in real time during the design phase and to obtain the resultant forms immediately. Based on a certain selection strategy, the forms have a better state of internal membrane forces compared to the original spherical structure. An ANSYS Parameter Design Language (APDL)-based automatic geometric modelling method for mega-latticed structures with various surface forms is developed. The proposed method solves the problem that the existing modelling methods are only available for spherical structures. It is highly applicable for modelling mega-latticed structures with spherical, cylindrical, and other heterogeneous surfaces. Furthermore, a complete design workflow that combines the proposed form-finding approach (for conceptual design), the automatic geometric modelling method (for transformation), and the finite element method (for deepening design and analysis), is discussed. This paper provides a reference for the design of mega-latticed structures and similar truss-based spatial structures.

A new strategy for prestack time migration velocity analysis to assess and mitigate structural uncertainty

Velocity uncertainty represents a significant contributor to structural uncertainty in seismic imaging. Therefore, improving velocities and enhancing the resolution of velocity spectra are crucial for reducing structural uncertainty. In the present study, a novel approach is introduced to increase velocity resolution and mitigate structural uncertainty. The methodology's impact on spatial and temporal uncertainty of image points is compared with the improved velocity continuation method. The proposed strategy involves modifying the equations of the weighted semblance method and integrating them into the equations of the velocity continuation method. Specifically, the vertical analysis window of the weighted semblance, typically applied on coherency panels is changed to a horizontal window that is applied on common-image gathers. Correspondingly, the weighting factor is adjusted using a time-adaptive function. The velocity uncertainty equation in the velocity continuation method is then replaced by the new weighted semblance eq. A similar substitution can be performed for structural uncertainty equations. These new equations are then used on common-image gathers obtained by the velocity continuation method to increase the accuracy of the velocity model and then investigate changes in structural uncertainty. In the proposed strategy, prestack time migration is initially conducted on seismic common-offset sections using various constant velocities within a predefined range. Subsequently, the weighted semblance technique is used for automatic velocity model updating in all common-image gathers. The new velocity model is then used for final prestack time migration. In the equations pertaining to velocity uncertainty, a width equivalent to one standard deviation on both sides of the picked velocity value is considered as the uncertainty range. By narrowing this width through the proposed method, it is expected to mitigate subsequent structural uncertainty, specifically for 1D media. Results from applying the presented method on synthetic and marine seismic data demonstrate its effectiveness in reducing structural uncertainty for 1D time migrated images compared to the velocity continuation method. It is also shown that horizontal structural uncertainty is significantly more sensitive to velocity errors rather than vertical uncertainty. An added benefit is that the increased resolution in velocity spectra also provides appropriate panels for automatic velocity picking.

Deep learning-based automated lesion segmentation on pediatric focal cortical dysplasia II preoperative MRI: a reliable approach

ObjectivesFocal cortical dysplasia (FCD) represents one of the most common causes of refractory epilepsy in children. Deep learning demonstrates great power in tissue discrimination by analyzing MRI data. A prediction model was built and verified using 3D full-resolution nnU-Net for automatic lesion detection and segmentation of children with FCD II.MethodsHigh-resolution brain MRI structure data from 65 patients, confirmed with FCD II by pathology, were retrospectively studied. Experienced neuroradiologists segmented and labeled the lesions as the ground truth. Also, we used 3D full-resolution nnU-Net to segment lesions automatically, generating detection maps. The algorithm was trained using fivefold cross-validation, with data partitioned into training (N = 200) and testing (N = 15). To evaluate performance, detection maps were compared to expert manual labels. The Dice-Sørensen coefficient (DSC) and sensitivity were used to assess the algorithm performance.ResultsThe 3D nnU-Net showed a good performance for FCD lesion detection at the voxel level, with a sensitivity of 0.73. The best segmentation model achieved a mean DSC score of 0.57 on the testing dataset.ConclusionThis pilot study confirmed that 3D full-resolution nnU-Net can automatically segment FCD lesions with reliable outcomes. This provides a novel approach to FCD lesion detection.Critical relevance statementOur fully automatic models could process the 3D T1-MPRAGE data and segment FCD II lesions with reliable outcomes.Key points• Simplified image processing promotes the DL model implemented in clinical practice.• The histopathological confirmed lesion masks enhance the clinical credibility of the AI model.• The voxel-level evaluation metrics benefit lesion detection and clinical decisions.Graphical