Intraclass Consistency Research Articles

Vehicle Classification Algorithm Based on Improved Vision Transformer

Vehicle classification technology is one of the foundations in the field of automatic driving. With the development of deep learning technology, visual transformer structures based on attention mechanisms can represent global information quickly and effectively. However, due to direct image segmentation, local feature details and information will be lost. To solve this problem, we propose an improved vision transformer vehicle classification network (IND-ViT). Specifically, we first design a CNN-In D branch module to extract local features before image segmentation to make up for the loss of detail information in the vision transformer. Then, in order to solve the problem of misdetection caused by the large similarity of some vehicles, we propose a sparse attention module, which can screen out the discernible regions in the image and further improve the detailed feature representation ability of the model. Finally, this paper uses the contrast loss function to further increase the intra-class consistency and inter-class difference of classification features and improve the accuracy of vehicle classification recognition. Experimental results show that the accuracy of the proposed model on the datasets of vehicle classification BIT-Vehicles, CIFAR-10, Oxford Flower-102, and Caltech-101 is higher than that of the original vision transformer model. Respectively, it increased by 1.3%, 1.21%, 7.54%, and 3.60%; at the same time, it also met a certain real-time requirement to achieve a balance of accuracy and real time.

Identifying malicious traffic under concept drift based on intraclass consistency enhanced variational autoencoder

Identifying malicious traffic under concept drift based on intraclass consistency enhanced variational autoencoder

Deep conditional adversarial subdomain adaptation network for unsupervised mechanical fault diagnosis

In recent years, intelligent fault diagnosis technology has rapidly advanced, achieving remarkable results. Most of them assume that the source and target domains have similar distributions. However, the actual working conditions of rotating machinery are variable, leading to a significant distribution discrepancy between the source and target domains. The majority of existing domain adaptation methods mainly consider either the marginal distribution or the conditional distribution between the source and target domains, which limits the improvement of diagnostic performance in the target domain. Considering the discrepancy in domain distributions, a deep conditional adversarial subdomain adaptation network (DCASAN) is proposed in this paper for unsupervised mechanical fault diagnosis under unknown working conditions. In DCASAN, a backbone network based on the feature fusion of convolutional neural network (CNN) and graph convolutional network (GCN) is designed for feature extraction. Furthermore, a conditional adversarial subdomain adaptation strategy is proposed, which simultaneously considers both the marginal distribution and the conditional distribution. Under the joint constraints of marginal and conditional distribution alignment, the extracted features exhibit improved inter-class discriminability and intra-class consistency, effectively reducing the distribution discrepancy between different domains. Results from multiple transfer tasks on three rotating machinery datasets demonstrate that the proposed method can learn rich transferable features. The overall average accuracy of the proposed method on these three datasets is 88.07%, 89.17%, and 96.63%, respectively, significantly outperforming other methods in terms of robustness and generalization.

Boundary-enhanced dual-stream network for semantic segmentation of high-resolution remote sensing images

ABSTRACT Deep convolutional neural networks (DCNNs) have been successfully used in semantic segmentation of high-resolution remote sensing images (HRSIs). However, this task still suffers from intra-class inconsistency and boundary blur due to high intra-class heterogeneity and inter-class homogeneity, considerable scale variance, and spatial information loss in conventional DCNN-based methods. Therefore, a novel boundary-enhanced dual-stream network (BEDSN) is proposed, in which an edge detection branch stream (EDBS) with a composite loss function is introduced to compensate for boundary loss in semantic segmentation branch stream (SSBS). EDBS and SSBS are integrated by highly coupled encoder and feature extractor. A lightweight multilevel information fusion module guided by channel attention mechanism is designed to reuse intermediate boundary information effectively. For aggregating multiscale contextual information, SSBS is enhanced by multiscale feature extraction module and hybrid atrous convolution module. Extensive experiments have been tested on ISPRS Vaihingen and Potsdam datasets. Results show that BEDSN can achieve significant improvements in intra-class consistency and boundary refinement. Compared with 11 state-of-the-art methods, BEDSN exhibits higher-level performance in both quantitative and visual assessments with low model complexity. The code will be available at https://github.com/lixinghua5540/BEDSN.

Validity and Reliability of the Nurse Manager Performance Assessment Scale

Background: The performance of nurse managers is significantly important in providing quality and safe patient care services in hospitals, as well as in retaining the nurse workforce. There are limited number of measurement instruments for which validity and reliability have been tested in order to assess nurse managers' level of performance. Objective: This study was conducted to examine the psychometric testing of the “Nurse Manager Performance Assessment Scale,” which is used to assess the annual performance of nurse managers working in a private chain hospital group in Turkey. Method: The sample of this methodological study was composed of 165 nurse managers. The data were obtained from the Hospital Information Management System, retrospectively. Results: The average score of the eight-item scale items ranged between 3.3 (0.8) and 3.7 (0.8). The Cronbach's alpha coefficient, indicating the internal consistency, was found to be 0.943, while the Spearman-Brown coefficient, indicating intraclass consistency, was found to be 0.910. The two-factor scale obtained using exploratory factor analysis was examined using confirmatory factor analysis, and the model was found to be significant. Conclusion: In this study, the results of psychometric analysis of the “Nurse Manager Performance Assessment Scale,” which is used to assess the annual performance of nurse managers, indicated that the scale is a valid and reliable instrument. It is recommended that the scale be applied in different institutions and that it be tested in practice based on pilot application results.

DECIDE: A decoupled semantic and boundary learning network for precise osteosarcoma segmentation by integrating multi-modality MRI

Automated Osteosarcoma Segmentation in Multi-modality MRI (AOSMM) holds clinical significance for effective tumor evaluation and treatment planning. However, the precision of AOSMM is challenged by the diverse characteristics of multi-modality MRI and the inherent heterogeneity and boundary ambiguity of osteosarcoma. While numerous methods have made significant strides in automated osteosarcoma segmentation, they primarily focused on the use of a single MRI modality and overlooked the potential benefits of integrating complementary information from other MRI modalities. Furthermore, they did not adequately model the long-range dependencies of complex tumor features, which may lead to insufficiently discriminative feature representations. To this end, we propose a decoupled semantic and boundary learning network (DECIDE) to achieve precise AOSMM with three functional modules. The Multi-modality Feature Fusion and Recalibration (MFR) module adaptively fuses and recalibrates multi-modality features by exploiting their channel-wise dependencies to compute low-rank attention weights for effectively aggregating useful information from different MRI modalities, which promotes complementary learning between multi-modality MRI and enables a more comprehensive tumor characterization. The Lesion Attention Enhancement (LAE) module employs spatial and channel attention mechanisms to capture global contextual dependencies over local features, significantly enhancing the discriminability and representational capacity of intricate tumor features. The Boundary Context Aggregation (BCA) module further enhances semantic representations by utilizing boundary information for effective context aggregation while also ensuring intra-class consistency in cases of boundary ambiguity. Substantial experiments demonstrate that DECIDE achieves exceptional performance in osteosarcoma segmentation, surpassing state-of-the-art methods in terms of accuracy and stability.

Diabetes-related instrument to assess preventive behaviors among adolescents (DIAPBA): a tool development and psychometric research

BackgroundType 2 diabetes is a chronic but preventable disease that is on the rise among adolescents. Evaluating adolescents’ behavior and planning to prevent it require a valid and reliable instrument. This study aims at designing a psychometric instrument to measure adolescents’ behavior with respect to type-2 diabetes.Research Design and methodsIn this methodological research, 770 students (adolescent boys and girls aged 13–15 years) participated through multistage sampling. The Inclusion criteria were: junior high school students, students’ willingness for participation and not suffering from type-1 or type-2 diabetes. The questionnaire was designed by examining the relevant literature and the existing questionnaires as well as considering the research team’s comments. The validity of the study was determined through face validity and content validity both quantitatively and qualitatively. The construct validity was determined through exploratory and confirmatory factor analysis. Reliability was measured via intraclass consistency coefficient (ICC) and internal consistency reliability was measured by Cronbach Alpha. SPSS 16 and Eq. 6.1 were used for data analysis.ResultsAt first, a list of 47 initial items was designed and compiled, and after by removing similar (10 questions) or inappropriate sentences (12 questions), a draft questionnaire with 25 questions was designed. No items were removed in the face validity phase. Based on exploratory factor analysis, the number of items in the questionnaire was reduced to 20 items and was categorized in five dimensions of stress management, healthy food/healthy diet, unhealthy food/unhealthy diet, high-risk behavior, and self-care. The results of confirmatory factor analysis confirmed the model. The internal consistency coefficient was confirmed measuring Cronbach Alpha at 0.70 with ICC = 0.80.ConclusionThe questionnaire designed has standard psychometric properties to assess adolescents’ behavior with respect to type-2 diabetes prevention. The reliability and the validity of the questionnaire as well as its general structure were confirmed.

Automatic quantitative stroke severity assessment based on Chinese clinical named entity recognition with domain-adaptive pre-trained large language model

Background:Stroke is a prevalent disease with a significant global impact. Effective assessment of stroke severity is vital for an accurate diagnosis, appropriate treatment, and optimal clinical outcomes. The National Institutes of Health Stroke Scale (NIHSS) is a widely used scale for quantitatively assessing stroke severity. However, the current manual scoring of NIHSS is labor-intensive, time-consuming, and sometimes unreliable. Applying artificial intelligence (AI) techniques to automate the quantitative assessment of stroke on vast amounts of electronic health records (EHRs) has attracted much interest. Objective:This study aims to develop an automatic, quantitative stroke severity assessment framework through automating the entire NIHSS scoring process on Chinese clinical EHRs. Methods:Our approach consists of two major parts: Chinese clinical named entity recognition (CNER) with a domain-adaptive pre-trained large language model (LLM) and automated NIHSS scoring. To build a high-performing CNER model, we first construct a stroke-specific, densely annotated dataset “Chinese Stroke Clinical Records” (CSCR) from EHRs provided by our partner hospital, based on a stroke ontology that defines semantically related entities for stroke assessment. We then pre-train a Chinese clinical LLM coined “CliRoberta” through domain-adaptive transfer learning and construct a deep learning-based CNER model that can accurately extract entities directly from Chinese EHRs. Finally, an automated, end-to-end NIHSS scoring pipeline is proposed by mapping the extracted entities to relevant NIHSS items and values, to quantitatively assess the stroke severity. Results:Results obtained on a benchmark dataset CCKS2019 and our newly created CSCR dataset demonstrate the superior performance of our domain-adaptive pre-trained LLM and the CNER model, compared with the existing benchmark LLMs and CNER models. The high F1 score of 0.990 ensures the reliability of our model in accurately extracting the entities for the subsequent automatic NIHSS scoring. Subsequently, our automated, end-to-end NIHSS scoring approach achieved excellent inter-rater agreement (0.823) and intraclass consistency (0.986) with the ground truth and significantly reduced the processing time from minutes to a few seconds. Conclusion:Our proposed automatic and quantitative framework for assessing stroke severity demonstrates exceptional performance and reliability through directly scoring the NIHSS from diagnostic notes in Chinese clinical EHRs. Moreover, this study also contributes a new clinical dataset, a pre-trained clinical LLM, and an effective deep learning-based CNER model. The deployment of these advanced algorithms can improve the accuracy and efficiency of clinical assessment, and help improve the quality, affordability and productivity of healthcare services.

RCPS: Rectified Contrastive Pseudo Supervision for Semi-Supervised Medical Image Segmentation.

Medical image segmentation methods are generally designed as fully-supervised to guarantee model performance, which requires a significant amount of expert annotated samples that are high-cost and laborious. Semi-supervised image segmentation can alleviate the problem by utilizing a large number of unlabeled images along with limited labeled images. However, learning a robust representation from numerous unlabeled images remains challenging due to potential noise in pseudo labels and insufficient class separability in feature space, which undermines the performance of current semi-supervised segmentation approaches. To address the issues above, we propose a novel semi-supervised segmentation method named as Rectified Contrastive Pseudo Supervision (RCPS), which combines a rectified pseudo supervision and voxel-level contrastive learning to improve the effectiveness of semi-supervised segmentation. Particularly, we design a novel rectification strategy for the pseudo supervision method based on uncertainty estimation and consistency regularization to reduce the noise influence in pseudo labels. Furthermore, we introduce a bidirectional voxel contrastive loss in the network to ensure intra-class consistency and inter-class contrast in feature space, which increases class separability in the segmentation. The proposed RCPS segmentation method has been validated on two public datasets and an in-house clinical dataset. Experimental results reveal that the proposed method yields better segmentation performance compared with the state-of-the-art methods in semi-supervised medical image segmentation. The source code is available at https://github.com/hsiangyuzhao/RCPS.

Addressing Skewed Heterogeneity via Federated Prototype Rectification With Personalization.

Federated learning (FL) is an efficient framework designed to facilitate collaborative model training across multiple distributed devices while preserving user data privacy. A significant challenge of FL is data-level heterogeneity, i.e., skewed or long-tailed distribution of private data. Although various methods have been proposed to address this challenge, most of them assume that the underlying global data are uniformly distributed across all clients. This article investigates data-level heterogeneity FL with a brief review and redefines a more practical and challenging setting called skewed heterogeneous FL (SHFL). Accordingly, we propose a novel federated prototype rectification with personalization (FedPRP) which consists of two parts: federated personalization and federated prototype rectification. The former aims to construct balanced decision boundaries between dominant and minority classes based on private data, while the latter exploits both interclass discrimination and intraclass consistency to rectify empirical prototypes. Experiments on three popular benchmarks show that the proposed approach outperforms current state-of-the-art methods and achieves balanced performance in both personalization and generalization.

Cross-Cultural Adaptation and Validation of the Russian-Language Version of the American Orthopaedic Foot and Ankle Society Ankle-Hindfoot Scale (AOFAS-AHS)

Background. Developed in 1994 by H. Kitaoka et al. the American Orthopaedic Foot and Ankle Society Ankle-Hindfoot scale (AOFAS-AHS) allows to assess pain, function, deformity and alignment of the foot and ankle. There is no Russian-language AOFAS-AHS questionnaire adapted according to current standards in the scientific literature.
 The aim of this paper is to perform the cross-cultural adaptation and to assess the validity of the Russian-language version of the AOFAS-AHS scale, including the evaluation of its psychometric properties.
 Methods. The original English version of the AOFAS-AHS scale was translated from English into Russian by a native Russian speaker. Then the questionnaire was back-translated into English by another translator whose native language is English. The next stage was the comparison of the original and back-translated versions, followed by the presentation of a pre-final cross-culturally adapted version, which was tested on 10 patients to ensure that the questions were comprehensible. The next step was the approval of the final version and its completion by patients to be operated on the hindfoot or ankle. The printed copy of the final version of the questionnaire was completed by the patients with an interval of 3 days. Total of 44 consecutive patients were enrolled, including 18 women (41%) and 26 men (59%), with a mean age of 61.7 (32-78) years. The psychometric properties of the Russian-language version of the AOFAS-AHS questionnaire (internal consistency, retest reliability, measurement error, responsiveness, and construct validity) were assessed based on the COSMIN (COnsensus-based Standards for the selection of health status Measurement INstruments) principles.
 Results. The mean score according to the AOFAS-AHS scale was 49.6 (min 2; max 82) out of a possible 100. The average time to complete the questionnaire was 4.2 minutes. All hypotheses formulated showed correlations of varying moderate to strong degrees. The Cronbach’s alpha coefficient was 0.76, which indicates a high level of internal consistency of the elements of the validated questionnaire. A good intra-class consistency of 0.83 was obtained, which shows a high degree of reliability of the questionnaire’s reproducibility. The ceiling and floor effects for the primary results of the questionnaires did not exceed 15%. The mean value of the Russian-language version of the AOFAS-AHS increased to 86.6 after surgical treatment. The values of standardized effect size (ES) and standardized response mean (SRM) were 5.56 and 4.83, respectively.
 Conclusion. The adapted Russian-language version of the AOFAS-AHS scale showed good psychometric properties and can be recommended for assessment of the physical activity in patients with ankle and hindfoot-related pathology and can also be used for monitoring the changes during the treatment.

Multicenter Study of the Utility of Convolutional Neural Network and Transformer Models for the Detection and Segmentation of Meningiomas.

This study aimed to investigate the effectiveness and practicality of using models like convolutional neural network and transformer in detecting and precise segmenting meningioma from magnetic resonance images. The retrospective study on T1-weighted and contrast-enhanced images of 523 meningioma patients from 3 centers between 2010 and 2020. A total of 373 cases split 8:2 for training and validation. Three independent test sets were built based on the remaining 150 cases. Six convolutional neural network detection models trained via transfer learning were evaluated using 4 metrics and receiver operating characteristic analysis. Detected images were used for segmentation. Three segmentation models were trained for meningioma segmentation and were evaluated via 4 metrics. In 3 test sets, intraclass consistency values were used to evaluate the consistency of detection and segmentation models with manually annotated results from 3 different levels of radiologists. The average accuracies of the detection model in the 3 test sets were 97.3%, 93.5%, and 96.0%, respectively. The model of segmentation showed mean Dice similarity coefficient values of 0.884, 0.834, and 0.892, respectively. Intraclass consistency values showed that the results of detection and segmentation models were highly consistent with those of intermediate and senior radiologists and lowly consistent with those of junior radiologists. The proposed deep learning system exhibits advanced performance comparable with intermediate and senior radiologists in meningioma detection and segmentation. This system could potentially significantly improve the efficiency of the detection and segmentation of meningiomas.

Agreement between measured energy expenditure and predictive energy equations in paediatric oncology

Purpose: Optimal nutritional support in childhood cancer relies on the adequate provision of energy. This study investigated the impact of chemotherapy on resting energy expenditure (REE) during the first six months of treatment and the accuracy of predictive equations in calculating said requirements of newly diagnosed children with cancer. Methods: REE was measured at diagnosis utilising a validated bioelectrical impedance analysis (BIA) mobile unit and compared with three predictive equations (Schofield 1985, World Health Organization [WHO] 1985 and the Recommended Dietary Allowance [RDA] 1989). Agreement and accuracy of these equations were tested by determining bias and agreement rates and displayed using the Bland–Altman plot. Baseline values were plotted against monthly follow-up measurements over time. Statistical significance was 5% and a priori limits of agreement set between 90% and 110% of measured REE. Results: Forty-three newly diagnosed children with median age 4 years (IQR 2.0–7.6) were measured prior to chemotherapy initiation. Compared with measured REE (mean ± SD) 719.53 ± 206.29 kcal/day, all predictive equations significantly overestimated REE: WHO 1985 (889.75 ± 323.31 kcal/day; 23% overestimation), Schofield 1985 (899.62 ± 336.10 kcal/day; 25% overestimation) and RDA (1647.67 ± 481.06 kcal/day; 129% overestimation) (p < 0.001). Despite significant proportionate bias in all three equations (p < 0.001), the intra-class consistency coefficient showed good reliability for the Schofield 1985 (0.864) and WHO 1985 (0.849) equations. Though statistically significant (chi-square = 23.11, p < 0.003), the overall 1 kcal/kg (1.3%) increase for all cancer types at six months may not be clinically significant. Conclusion: Existing predictive equations are unable to calculate REE accurately at childhood cancer diagnosis, highlighting the need for future investigations into the development of cancer-specific equations.

An AI-Based Image Quality Control Framework for Knee Radiographs

Image quality control (QC) is crucial for the accurate diagnosis of knee diseases using radiographs. However, the manual QC process is subjective, labor intensive, and time-consuming. In this study, we aimed to develop an artificial intelligence (AI) model to automate the QC procedure typically performed by clinicians. We proposed an AI-based fully automatic QC model for knee radiographs using high-resolution net (HR-Net) to identify predefined key points in images. We then performed geometric calculations to transform the identified key points into three QC criteria, namely, anteroposterior (AP)/lateral (LAT) overlap ratios and LAT flexion angle. The proposed model was trained and validated using 2212 knee plain radiographs from 1208 patients and an additional 1572 knee radiographs from 753 patients collected from six external centers for further external validation. For the internal validation cohort, the proposed AI model and clinicians showed high intraclass consistency coefficients (ICCs) for AP/LAT fibular head overlap and LAT knee flexion angle of 0.952, 0.895, and 0.993, respectively. For the external validation cohort, the ICCs were also high, with values of 0.934, 0.856, and 0.991, respectively. There were no significant differences between the AI model and clinicians in any of the three QC criteria, and the AI model required significantly less measurement time than clinicians. The experimental results demonstrated that the AI model performed comparably to clinicians and required less time. Therefore, the proposed AI-based model has great potential as a convenient tool for clinical practice by automating the QC procedure for knee radiographs.

A Novel Remote Sensing Image Enhancement Method, the Pseudo-Tasseled Cap Transformation: Taking Buildings and Roads in GF-2 as an Example

With the improvements in sensor accuracy, the spectral features of high-resolution remote sensing images become more complex. As a result, the classification accuracy for land cover classification decreases. Remote sensing image enhancements can improve the visual effect and the intra-class consistency and enhance the characteristics of ground objects. These enhancements are important for both image interpretation and improving image segmentation accuracy. In this study, we propose a pseudo-tasseled cap transformation (pseudo-TCT) through an orthogonal linear transformation of Gaofen-2 (GF-2) images using the untransposed tasseled cap transformation (TCT) coefficients, and further, enhance the visual effect and the separability among ground objects by linear stretching and percentage truncation stretching. To examine the separability among ground objects in the pseudo-TCT image, we used K-Means clustering, ISODATA clustering and 3D visualization of the spectral features of typical ground objects. The results show that the separability of buildings and roads from background objects is better than in the original image and the TCT image, and typical ground objects are effectively distinguished. Additionally, we visualized intra-class consistency by calculating the mean Euclidean distance between the pixel values of each point and the pixel values of its eight neighboring points and calculated the standard deviation of the intra-class consistency images. The results indicate that the secondary textures of the objects were weakened, and edges were made clearer, enhancing intra-class consistency. The pseudo-TCT is effective, at least in our work, and could be a candidate for image enhancement under certain applications.

Semantic-gap-oriented feature selection in hierarchical classification learning

Semantic gap is common issues in classification tasks. Different from traditional classification tasks, the semantic gap problem can introduce serious error propagation for hierarchical classification. In this paper, we propose a hierarchical feature selection method with label enhancement (HFSLE) to solve this challenge, which estimates the label distribution and selects subsets of features for each subtask. Firstly, HFSLE combines the label enhancement and hierarchical feature selection process so that the label enhancement benefits from the feedback of the loss function. Then, the label enhancement is constrained by the consistency of the parent-child distribution to obtain a plausible label distribution. Finally, feature selection is optimized based on intra-class consistency hierarchical regularization terms, which unifies feature subsets with hierarchical semantic descriptions to narrow the semantic gap. HFSLE gives a new perspective on the hierarchical feature selection based on label distribution rather than the original logical label. To demonstrate the superiority of the method, we compared it with six well-established feature selection methods on eight hierarchical data sets, and analyzed the convergence and robustness of the method. Extensive experiments demonstrate that the proposed method can perform favorably against advanced hierarchical feature selection approaches.

Intra-class consistency and inter-class discrimination feature learning for automatic skin lesion classification.

Automated skin lesion classification has been proved to be capable of improving the diagnostic performance for dermoscopic images. Although many successes have been achieved, accurate classification remains challenging due to the significant intra-class variation and inter-class similarity. In this article, a deep learning method is proposed to increase the intra-class consistency as well as the inter-class discrimination of learned features in the automatic skin lesion classification. To enhance the inter-class discriminative feature learning, a CAM-based (class activation mapping) global-lesion localization module is proposed by optimizing the distance of CAMs for the same dermoscopic image generated by different skin lesion tasks. Then, a global features guided intra-class similarity learning module is proposed to generate the class center according to the deep features of all samples in one class and the history feature of one sample during the learning process. In this way, the performance can be improved with the collaboration of CAM-based inter-class feature discriminating and global features guided intra-class feature concentrating. To evaluate the effectiveness of the proposed method, extensive experiments are conducted on the ISIC-2017 and ISIC-2018 datasets. Experimental results with different backbones have demonstrated that the proposed method has good generalizability and can adaptively focus on more discriminative regions of the skin lesion.

Learning Features of Intra-Consistency and Inter-Diversity: Keys Toward Generalizable Deepfake Detection

Public concerns about deepfake face forgery are continually rising in recent years. Most deepfake detection approaches attempt to learn discriminative features between real and fake faces through end-to-end trained deep neural networks. However, the majorities of them suffer from the problem of poor generalization across different data sources, forgery methods, and/or post-processing operations. In this paper, following the simple but effective principle in discriminative representation learning, i.e., towards learning features of intra-consistency within classes and inter-diversity between classes, we leverage a novel transformer-based self-supervised learning method and an effective data augmentation strategy towards generalizable deepfake detection. Considering the differences between the real and fake images are often subtle and local, the proposed method firstly utilizes Self Prediction Learning (SPL) to learn rich hidden representations by predicting masked patches at a pre-training stage. Intra-class consistency clues in images can be mined without deepfake labels. After pre-training, the discrimination model is then fine-tuned via multi-task learning, including a deepfake classification task and a forgery mask estimation task. It is facilitated by our new data augmentation method called Adjustable Forgery Synthesizer (AFS), which can conveniently simulate the process of synthesizing deepfake images with various levels of visual reality in an explicit manner. AFS greatly prevents overfitting due to insufficient diversity in training data. Comprehensive experiments demonstrate that our method outperforms the state-of-the-art competitors on several popular benchmark datasets in terms of generalization to unseen forgery methods and untrained datasets.

SupCAM: Chromosome cluster types identification using supervised contrastive learning with category-variant augmentation and self-margin loss.

Chromosome segmentation is a crucial analyzing task in karyotyping, a technique used in experiments to discover chromosomal abnormalities. Chromosomes often touch and occlude with each other in images, forming various chromosome clusters. The majority of chromosome segmentation methods only work on a single type of chromosome cluster. Therefore, the pre-task of chromosome segmentation, the identification of chromosome cluster types, requires more focus. Unfortunately, the previous method used for this task is limited by the small-scale chromosome cluster dataset, ChrCluster, and needs the help of large-scale natural image datasets, such as ImageNet. We realized that semantic differences between chromosomes and natural objects should not be ignored, and thus developed a novel two-step method called SupCAM, which could avoid overfitting only using ChrCluster and achieve a better performance. In the first step, we pre-trained the backbone network on ChrCluster following the supervised contrastive learning framework. We introduced two improvements to the model. One is called the category-variant image composition method, which augments samples by synthesizing valid images and proper labels. The other introduces angular margin into large-scale instance contrastive loss, namely self-margin loss, to increase the intraclass consistency and decrease interclass similarity. In the second step, we fine-tuned the network and obtained the final classification model. We validated the effectiveness of modules through massive ablation studies. Finally, SupCAM achieved an accuracy of 94.99% with the ChrCluster dataset, which outperformed the method used previously for this task. In summary, SupCAM significantly supports the chromosome cluster type identification task to achieve better automatic chromosome segmentation.

Novel Platform for Quantitative Assessment of Functional Object Interactions After Stroke.

Many persons with stroke exhibit upper extremity motor impairments. These impairments often lead to dysfunction and affect performance in activities of daily living, where successful manipulation of objects is essential. Hence, understanding how upper extremity motor deficits manifest in functional interactions with objects is critical for rehabilitation. However, quantifying skill in these tasks has been a challenge. Traditional rehabilitation assessments require highly trained clinicians, are time-consuming, and yield subjective scores. This paper introduces a custom-designed device, the "MAGIC Table", that can record real-time kinematics of persons with stroke during interaction with objects, specifically a 'cup of coffee'. The task and its quantitative assessments were derived from previous basic-science studies. Six participants after stroke and six able-bodied participants moved a 3D-printed cup with a rolling ball inside, representing sloshing coffee, with 3 levels of difficulty. Movements were captured via a high-resolution camera above the table. Conventional kinematic metrics (movement time and smoothness) and novel kinematic metrics accounting for object interaction (risk and predictability) evaluated performance. Expectedly, persons with stroke moved more slowly and less smoothly than able-bodied participants, in both simple reaches and during transport of the cup-and-ball system. However, the more sensitive metric was mutual information, which captured the predictability of interactions, essential in cup transport as shown in previous theoretical research. Predictability sensitively measured differences in performance with increasing levels of difficulty. It also showed the best intraclass consistency, promising sensitive differentiation between different levels of impairment. This study highlights the feasibility of this new device and indicates that examining dynamic object interaction may provide valuable insights into upper extremity function after stroke useful for assessment and rehabilitation.