RESUMO
OBJECTIVES: To identify frailty trajectories and examine its association with allostatic load (AL) and mediating effect of physical activity (PA). METHODS: This study included 8,082 adults from the English Longitudinal Study of Aging over Waves 4-9. AL was calculated by 14 biological indicators, and a 53-item frailty index was used to evaluate frailty. Frailty trajectories were classified by group-based trajectory modeling, and the mediated effect of PA was tested by causal mediation analysis. RESULTS: Four frailty trajectories were identified: "Robustness" (n = 4,437, 54.9%), "Incident prefrailty" (n = 2,061, 25.5%), "Prefrailty to frailty" (n = 1,136, 14.1%), and "Frailty to severe frailty" (n = 448, 5.5%). High baseline AL was associated with increased odds of "Incident prefrailty," "Prefrailty to frailty," and "Frailty to severe frailty" trajectories. PA demonstrated significant mediated effects in aforementioned associations. CONCLUSIONS: AL is significantly associated with the onset and progression of frailty, and such associations are partially mediated by PA.
Assuntos
Alostase , Fragilidade , Idoso , Humanos , Estudos Longitudinais , Idoso Fragilizado , Exercício FísicoRESUMO
This study was conducted to assess the effects of dietary copper source and level on hematological parameters, copper accumulation and transport, resistance to low temperature, antioxidant capacity and immune response of white shrimp (Litopenaeus vannamei Boone, 1931). Seven experimental diets with different copper sources and levels were formulated: C, no copper supplementation; S, 30 mg/kg copper in the form of CuSO4·5H2O; SO, 15 mg/kg copper in CuSO4·5H2O + 7.5 mg/kg copper in Cu-proteinate; O1, O2, O3 and O4, 10, 20, 30 and 40 mg/kg copper in the form of Cu-proteinate, respectively. A total of 840 shrimp (5.30 ± 0.04 g) were randomly distributed to 21 tanks (3 tanks/diet, 40 shrimp/tank). An 8-week feeding trial was conducted. The results showed that there was no significant difference in growth performance and whole shrimp chemical compositions among all groups. Compared with inorganic copper, dietary organic copper (O2 and O3) increased total protein, albumin, and glucose content of plasma, while decreased triglyceride and total cholesterol of plasma. Copper concentration in plasma and muscle and gene expression of metallothionein and copper-transporting ATPase 2 like in hepatopancreas were higher in shrimp fed organic copper (SO, O2, O3 and O4). The lowest mortality after low temperature (10 °C) challenge test was observed in the O2 and O3 groups. Organic copper (SO, O2, O3 and O4) significantly enhanced the antioxidant capacity (in terms of higher activities of total superoxide dismutase, copper zinc superoxide dismutase, catalase, glutathione peroxidase and total antioxidant capacity, lower malondialdehyde concentration of plasma, and up-regulated gene expression of superoxide dismutase, copper zinc superoxide dismutase, catalase and glutathione peroxidase of hepatopancreas). Organic copper (SO, O2, O3 and O4) enhanced the immune response (in terms of higher number of total hemocytes, higher activities of acid phosphatase, alkaline phosphatase, phenoloxidase, hemocyanin and lysozyme in plasma, and higher gene expressions of alkaline phosphatase, lysozyme and hemocyanin in hepatopancreas). Inorganic copper (Diet S) also had positive effects on white shrimp compared with the C diet, but the SO, O2, O3 and O4 diets resulted in better results, among which the O2 diet appeared to be the best one. In conclusion, organic copper was more beneficial to shrimp health than copper sulfate.
Assuntos
Antioxidantes , Penaeidae , Animais , Fosfatase Alcalina , Ração Animal/análise , Antioxidantes/metabolismo , Catalase , Cobre/metabolismo , Dieta/veterinária , Glutationa Peroxidase/metabolismo , Hemocianinas/farmacologia , Imunidade Inata , Muramidase/farmacologia , Superóxido Dismutase/metabolismo , Temperatura , Zinco/farmacologiaRESUMO
BACKGROUND: The discovery of critical biomarkers is significant for clinical diagnosis, drug research and development. Researchers usually obtain biomarkers from microarray data, which comes from the dimensional curse. Feature selection in machine learning is usually used to solve this problem. However, most methods do not fully consider feature dependence, especially the real pathway relationship of genes. RESULTS: Experimental results show that the proposed method is superior to classical algorithms and advanced methods in feature number and accuracy, and the selected features have more significance. METHOD: This paper proposes a feature selection method based on a graph neural network. The proposed method uses the actual dependencies between features and the Pearson correlation coefficient to construct graph-structured data. The information dissemination and aggregation operations based on graph neural network are applied to fuse node information on graph structured data. The redundant features are clustered by the spectral clustering method. Then, the feature ranking aggregation model using eight feature evaluation methods acts on each clustering sub-cluster for different feature selection. CONCLUSION: The proposed method can effectively remove redundant features. The algorithm's output has high stability and classification accuracy, which can potentially select potential biomarkers.
Assuntos
Algoritmos , Redes Neurais de Computação , Biomarcadores , Análise por Conglomerados , Aprendizado de MáquinaRESUMO
OBJECTIVES: To evaluate whether radiomics signature of pericoronary adipose tissue (PCAT) based on coronary computed tomography angiography (CCTA) could improve the prediction of future acute coronary syndrome (ACS) within 3 years. METHODS: We designed a retrospective case-control study that patients with ACS (n = 90) were well matched to patients with no cardiac events (n = 1496) during 3 years follow-up, then which were randomly divided into training and test datasets with a ratio of 3:1. A total of 107 radiomics features were extracted from PCAT surrounding lesions and 14 conventional plaque characteristics were analyzed. Radiomics score, plaque score, and integrated score were respectively calculated via a linear combination of the selected features, and their performance was evaluated with discrimination, calibration, and clinical application. RESULTS: Radiomics score achieved superior performance in identifying patients with future ACS within 3 years in both training and test datasets (AUC = 0.826, 0.811) compared with plaque score (AUC = 0.699, 0.640), with a significant difference of AUC between two scores in the training dataset (p = 0.009); while the improvement of integrated score discriminating capability (AUC = 0.838, 0.826) was non-significant. The calibration curves of three predictive models demonstrated a good fitness respectively (all p > 0.05). Decision curve analysis suggested that integrated score added more clinical benefit than plaque score. Stratified analysis revealed that the performance of three predictive models was not affected by tube voltage, CT version, different sites of hospital. CONCLUSION: CCTA-based radiomics signature of PCAT could have the potential to predict the occurrence of subsequent ACS. Radiomics-based integrated score significantly outperformed plaque score in identifying future ACS within 3 years. KEY POINTS: ⢠Plaque score based on conventional plaque characteristics had certain limitations in the prediction of ACS. ⢠Radiomics signature of PCAT surrounding plaques could have the potential to improve the predictive ability of subsequent ACS. ⢠Radiomics-based integrated score significantly outperformed plaque score in the identification of future ACS within 3 years.
Assuntos
Síndrome Coronariana Aguda , Doença da Artéria Coronariana , Placa Aterosclerótica , Síndrome Coronariana Aguda/diagnóstico por imagem , Tecido Adiposo/diagnóstico por imagem , Estudos de Casos e Controles , Angiografia por Tomografia Computadorizada , Angiografia Coronária , Doença da Artéria Coronariana/diagnóstico por imagem , Humanos , Placa Aterosclerótica/diagnóstico por imagem , Estudos Retrospectivos , Tomografia Computadorizada por Raios XRESUMO
Deoxynivalenol (DON) is one of the most common mycotoxins in animal feed worldwide and causes significant threats to the animal health. Increased use of plant ingredients in aquaculture feeds increased the risk of mycotoxin contamination. To evaluate the effects of dietary deoxynivalenol (DON) on growth performance, immune response and intestinal health of turbot and the mitigation efficacy of yeast cell wall extract (YCWE) toward DON, nine isonitrogenous and isolipidic diets were formulated: Diet 1 (control): No DON added; Diets 2-5 or Diets 6-9: 0.5 or 3.0 mg added DON/kg diet + 0%, 0.1%, 0.2%, or 0.4% YCWE, respectively. Results showed that Diet 6 (3 mg/kg DON, 0% YCWE) significantly decreased weight gain, specific growth rate and feed efficiency ratio of fish and reduced immunoglobulin M and complement 4 concentrations in serum. Fish fed Diet 6 presented morphological alterations, lower activity of superoxide dismutase, catalase and total antioxidant capacity but higher malondialdehyde content, lower claudin-4 and occludin expression but higher interleukin-1ß expression in intestine. Besides, Diet 6 decreased the abundance of potential helpful bacteria but increased the abundance of potential pathogens in intestine. While, dietary YCWE, especially Diet 8 (3 mg/kg DON, 0.2% YCWE) and 9 (3 mg/kg DON, 0.4% YCWE), markedly improved growth performance and immune response and enhanced the intestinal health of turbot. In conclusion, dietary YCWE could mitigate the toxic effects induced by DON in turbot, and could be used as an effective strategy to control DON contamination in fish feed.
RESUMO
BACKGROUND: The distribution of pulmonary vessels in computed tomography (CT) and computed tomography angiography (CTA) images of lung is important for diagnosing disease, formulating surgical plans and pulmonary research. PURPOSE: Based on the pulmonary vascular segmentation task of International Symposium on Image Computing and Digital Medicine 2020 challenge, this paper reviews 12 different pulmonary vascular segmentation algorithms of lung CT and CTA images and then objectively evaluates and compares their performances. METHODS: First, we present the annotated reference dataset of lung CT and CTA images. A subset of the dataset consisting 7,307 slices for training and 3,888 slices for testing was made available for participants. Second, by analyzing the performance comparison of different convolutional neural networks from 12 different institutions for pulmonary vascular segmentation, the reasons for some defects and improvements are summarized. The models are mainly based on U-Net, Attention, GAN, and multi-scale fusion network. The performance is measured in terms of Dice coefficient, over segmentation rate and under segmentation rate. Finally, we discuss several proposed methods to improve the pulmonary vessel segmentation results using deep neural networks. RESULTS: By comparing with the annotated ground truth from both lung CT and CTA images, most of 12 deep neural network algorithms do an admirable job in pulmonary vascular extraction and segmentation with the dice coefficients ranging from 0.70 to 0.85. The dice coefficients for the top three algorithms are about 0.80. CONCLUSIONS: Study results show that integrating methods that consider spatial information, fuse multi-scale feature map, or have an excellent post-processing to deep neural network training and optimization process are significant for further improving the accuracy of pulmonary vascular segmentation.
Assuntos
Angiografia por Tomografia Computadorizada , Processamento de Imagem Assistida por Computador , Humanos , Processamento de Imagem Assistida por Computador/métodos , Pulmão/diagnóstico por imagem , Redes Neurais de Computação , Tomografia Computadorizada por Raios XRESUMO
Precise segmentation of lung parenchyma is essential for effective analysis of the lung. Due to the obvious contrast and large regional area compared to other tissues in the chest, lung tissue is less difficult to segment. Special attention to details of lung segmentation is also needed. To improve the quality and speed of segmentation of lung parenchyma based on computed tomography (CT) or computed tomography angiography (CTA) images, the 4th International Symposium on Image Computing and Digital Medicine (ISICDM 2020) provides interesting and valuable research ideas and approaches. For the work of lung parenchyma segmentation, 9 of the 12 participating teams used the U-Net network or its modified forms, and others used the methods to improve the segmentation accuracy include attention mechanism, multi-scale feature information fusion. Among them, U-Net achieves the best results including that the final dice coefficient of CT segmentation is 0.991 and the final dice coefficient of CTA segmentation is 0.984. In addition, attention U-Net and nnU-Net network also performs well. In this paper, the methods chosen by 12 teams from different research groups are evaluated and their segmentation results are analyzed for the study and references to those involved.
Assuntos
Aprendizado Profundo , Processamento de Imagem Assistida por Computador/métodos , Pulmão/diagnóstico por imagem , Tórax , Tomografia Computadorizada por Raios X/métodosRESUMO
Intercepting a moving object requires prediction of its future location. This complex task has been solved by dragonflies, who intercept their prey in midair with a 95% success rate. In this study, we show that a group of 16 neurons, called target-selective descending neurons (TSDNs), code a population vector that reflects the direction of the target with high accuracy and reliability across 360°. The TSDN spatial (receptive field) and temporal (latency) properties matched the area of the retina where the prey is focused and the reaction time, respectively, during predatory flights. The directional tuning curves and morphological traits (3D tracings) for each TSDN type were consistent among animals, but spike rates were not. Our results emphasize that a successful neural circuit for target tracking and interception can be achieved with few neurons and that in dragonflies this information is relayed from the brain to the wing motor centers in population vector form.
Assuntos
Voo Animal/fisiologia , Percepção de Movimento/fisiologia , Odonatos/fisiologia , Comportamento Predatório/fisiologia , Neurônios Retinianos/fisiologia , Animais , Isoquinolinas , Microscopia Confocal , Modelos Neurológicos , Condução Nervosa/fisiologia , Estimulação Luminosa , Tempo de Reação , Neurônios Retinianos/citologia , Temperatura , Campos Visuais/fisiologiaRESUMO
PURPOSE: Frailty is a common health state that is closely linked to adverse health outcomes in aging society. Although many inflammatory biomarkers have been cross-sectionally associated with frailty, knowledge on the longitudinal association is still limited. This study investigated the associations between inflammatory factors in clinical practice and frailty progression over time. METHODS: To investigate the associations of three common inflammatory markers (hypersensitive C-reactive protein [hsCRP], white blood cell [WBC] and fibrinogen) with the progression of frailty. METHODS: Data of 2316 participants (age 67.9 ± 6.1 years) were obtained from the English longitudinal study of aging (wave 4, 6 and 8) over an 8-year follow-up. The frailty index (FI) was calculated from 52 items. Mixed-effects models and Cox proportional hazards (Cox-PH) models were used to analyze the associations of hsCRP, WBC and fibrinogen with frailty progression. Values of inflammatory biomarkers were log-transformed. Age, sex and gross wealth were controlled. RESULTS: Mixed-effects models showed that at a cross-sectional level, higher levels of hsCRP (ß: 0.007, 95% CI 0.004-0.010), WBC (ß: 0.021, 95% CI 0.010-0.032) and fibrinogen (ß: 0.022, 95% CI 0.005-0.038) were associated with greater FI values while no significant time interaction was found. Cox-PH models showed that higher baseline levels of hsCRP (HR: 1.10, 95% CI 1.03-1.17) and WBC (HR: 1.23, 95% CI 1.10-1.37) were linked to a greater risk of developing frailty within 8 years. CONCLUSIONS: We concluded that hsCRP, WBC and fibrinogen can reflect frailty status at a cross-sectional level while only hsCRP and WBC are associated with frailty progression over an 8-year period.
RESUMO
Current state-of-the-art medical image segmentation techniques predominantly employ the encoder-decoder architecture. Despite its widespread use, this U-shaped framework exhibits limitations in effectively capturing multi-scale features through simple skip connections. In this study, we made a thorough analysis to investigate the potential weaknesses of connections across various segmentation tasks, and suggest two key aspects of potential semantic gaps crucial to be considered: the semantic gap among multi-scale features in different encoding stages and the semantic gap between the encoder and the decoder. To bridge these semantic gaps, we introduce a novel segmentation framework, which incorporates a Dual Attention Transformer module for capturing channel-wise and spatial-wise relationships, and a Decoder-guided Recalibration Attention module for fusing DAT tokens and decoder features. These modules establish a principle of learnable connection that resolves the semantic gaps, leading to a high-performance segmentation model for medical images. Furthermore, it provides a new paradigm for effectively incorporating the attention mechanism into the traditional convolution-based architecture. Comprehensive experimental results demonstrate that our model achieves consistent, significant gains and outperforms state-of-the-art methods with relatively fewer parameters. This study contributes to the advancement of medical image segmentation by offering a more effective and efficient framework for addressing the limitations of current encoder-decoder architectures. Code: https://github.com/McGregorWwww/UDTransNet.
Assuntos
Processamento de Imagem Assistida por Computador , Redes Neurais de Computação , Semântica , Humanos , Processamento de Imagem Assistida por Computador/métodos , Aprendizado Profundo , AlgoritmosRESUMO
BACKGROUND AND OBJECTIVE: Multi-label Chest X-ray (CXR) images often contain rich label relationship information, which is beneficial to improve classification performance. However, because of the intricate relationships among labels, most existing works fail to effectively learn and make full use of the label correlations, resulting in limited classification performance. In this study, we propose a multi-label learning framework that learns and leverages the label correlations to improve multi-label CXR image classification. METHODS: In this paper, we capture the global label correlations through the self-attention mechanism. Meanwhile, to better utilize label correlations for guiding feature learning, we decompose the image-level features into label-level features. Furthermore, we enhance label-level feature learning in an end-to-end manner by a consistency constraint between global and local label correlations, and a label correlation guided multi-label supervised contrastive loss. RESULTS: To demonstrate the superior performance of our proposed approach, we conduct three times 5-fold cross-validation experiments on the CheXpert dataset. Our approach obtains an average F1 score of 44.6% and an AUC of 76.5%, achieving a 7.7% and 1.3% improvement compared to the state-of-the-art results. CONCLUSION: More accurate label correlations and full utilization of the learned label correlations help learn more discriminative label-level features. Experimental results demonstrate that our approach achieves exceptionally competitive performance compared to the state-of-the-art algorithms.
Assuntos
Aprendizagem , Tórax , Tórax/diagnóstico por imagem , Algoritmos , Projetos de PesquisaRESUMO
Whole heart segmentation (WHS) has significant clinical value for cardiac anatomy, modeling, and analysis of cardiac function. This study aims to address the WHS accuracy on cardiac CT images, as well as the fast inference speed and low graphics processing unit (GPU) memory consumption required by practical clinical applications. Thus, we propose a multi-residual two-dimensional (2D) network integrating spatial correlation for WHS. The network performs slice-by-slice segmentation on three-dimensional cardiac CT images in a 2D encoder-decoder manner. In the network, a convolutional long short-term memory skip connection module is designed to perform spatial correlation feature extraction on the feature maps at different resolutions extracted by the sub-modules of the pre-trained ResNet-based encoder. Moreover, a decoder based on the multi-residual module is designed to analyze the extracted features from the perspectives of multi-scale and channel attention, thereby accurately delineating the various substructures of the heart. The proposed method is verified on a dataset of the multi-modality WHS challenge, an in-house WHS dataset, and a dataset of the abdominal organ segmentation challenge. The dice, Jaccard, average symmetric surface distance, Hausdorff distance, inference time, and maximum GPU memory of the WHS are 0.914, 0.843, 1.066 mm, 15.778 mm, 9.535 s, and 1905 MB, respectively. The proposed network has high accuracy, fast inference speed, minimal GPU memory consumption, strong robustness, and good generalization. It can be deployed to clinical practical applications for WHS and can be effectively extended and applied to other multi-organ segmentation fields. The source code is publicly available at https://github.com/nancy1984yan/MultiResNet-SC.
Assuntos
Coração , Software , Coração/diagnóstico por imagem , Tomografia Computadorizada por Raios XRESUMO
Accurate landmark detection in medical imaging is essential for quantifying various anatomical structures and assisting in diagnosis and treatment planning. In ultrasound cine, landmark detection is often associated with identifying keyframes, which represent the occurrence of specific events, such as measuring target dimensions at specific temporal phases. Existing methods predominantly treat landmark and keyframe detection as separate tasks without harnessing their underlying correlations. Additionally, owing to the intrinsic characteristics of ultrasound imaging, both tasks are constrained by inter-observer variability, leading to potentially higher levels of uncertainty. In this paper, we propose a Bayesian network to achieve simultaneous keyframe and landmark detection in ultrasonic cine, especially under highly sparse training data conditions. We follow a coarse-to-fine landmark detection architecture and propose an adaptive Bayesian hypergraph for coordinate refinement on the results of heatmap-based regression. In addition, we propose Order Loss for training bi-directional Gated Recurrent Unit to identify keyframes based on the relative likelihoods within the sequence. Furthermore, to exploit the underlying correlation between the two tasks, we use a shared encoder to extract features for both tasks and enhance the detection accuracy through the interaction of temporal and motion information. Experiments on two in-house datasets (multi-view transesophageal and transthoracic echocardiography) and one public dataset (transthoracic echocardiography) demonstrate that our method outperforms state-of-the-art approaches. The mean absolute errors for dimension measurements of the left atrial appendage, aortic annulus, and left ventricle are 2.40 mm, 0.83 mm, and 1.63 mm, respectively. The source code is available at github.com/warmestwind/ABHG.
RESUMO
Landmark detection is a crucial task in medical image analysis, with applications across various fields. However, current methods struggle to accurately locate landmarks in medical images with blurred tissue boundaries due to low image quality. In particular, in echocardiography, sparse annotations make it challenging to predict landmarks with position stability and temporal consistency. In this paper, we propose a spatio-temporal graph convolutional network tailored for echocardiography landmark detection. We specifically sample landmark labels from the left ventricular endocardium and pre-calculate their correlations to establish structural priors. Our approach involves a graph convolutional neural network that learns the interrelationships among landmarks, significantly enhancing landmark accuracy within ambiguous tissue contexts. Additionally, we integrate gate recurrent units to grasp the temporal consistency of landmarks across consecutive images, augmenting the model's resilience against unlabeled data. Through validation across three echocardiography datasets, our method demonstrates superior accuracy when contrasted with alternative landmark detection models.
RESUMO
Person re-identification (ReID) has made good progress in stationary domains. The ReID model must be retrained to adapt to new scenarios (domains) as they emerge unexpectedly, which leads to catastrophic forgetting. Continual learning trains the model in the order of domain emergence to alleviate catastrophic forgetting. However, generalization ability of the model is still limited due to the distribution difference between training and testing domains. To address the above problem, we propose the generalized continual person re-Identification (GCReID) model to continuously train an anti-forgetting and generalizable model. We endeavor to increase the diversity of samples by prior to simulate unseen domains. Meta-train and meta-test are adopted to enhance generalization of the model. Universal knowledge extracted from all seen domains and the simulated domains is stored in a set of feature embeddings. The knowledge is continually updated and applied to guide meta-train and meta-test via a graph attention network. Extensive experiments on 12 benchmark datasets and comparisons with 6 representative models demonstrate the effectiveness of the proposed model GCReID in enhancing generalization performance on unseen domains and alleviating catastrophic forgetting of seen domains. The code will be available at https://github.com/DFLAG-NEU/GCReID if our work is accepted.
RESUMO
Regional wall motion abnormality (RWMA) is a common manifestation of ischemic heart disease detected through echocardiography. Currently, RWMA diagnosis heavily relies on visual assessment by doctors, leading to limitations in experience-based dependence and suboptimal reproducibility among observers. Several RWMA diagnosis models were proposed, while RWMA diagnosis with more refined segments can provide more comprehensive wall motion information to better assist doctors in the diagnosis of ischemic heart disease. In this paper, we proposed the STGA-MS model which consists of three modules, the spatial-temporal grouping attention (STGA) module, the segment feature extraction module, and the multiscale downsampling module, for the diagnosis of RWMA for multiple myocardial segments. The STGA module captures global spatial and temporal information, enhancing the representation of myocardial motion characteristics. The segment feature extraction module focuses on specific segment regions, extracting relevant features. The multiscale downsampling module analyzes myocardial motion deformation across different receptive fields. Experimental results on a 2D transthoracic echocardiography dataset show that the proposed STGA-MS model achieves better performance compared to state-of-the-art models. It holds promise in improving the accuracy and reproducibility of RWMA diagnosis, assisting clinicians in diagnosing ischemic heart disease more reliably.
RESUMO
Medical image analysis techniques have been employed in diagnosing and screening clinical diseases. However, both poor medical image quality and illumination style inconsistency increase uncertainty in clinical decision-making, potentially resulting in clinician misdiagnosis. The majority of current image enhancement methods primarily concentrate on enhancing medical image quality by leveraging high-quality reference images, which are challenging to collect in clinical applications. In this study, we address image quality enhancement within a fully self-supervised learning setting, wherein neither high-quality images nor paired images are required. To achieve this goal, we investigate the potential of self-supervised learning combined with domain adaptation to enhance the quality of medical images without the guidance of high-quality medical images. We design a Domain Adaptation Self-supervised Quality Enhancement framework, called DASQE. More specifically, we establish multiple domains at the patch level through a designed rule-based quality assessment scheme and style clustering. To achieve image quality enhancement and maintain style consistency, we formulate the image quality enhancement as a collaborative self-supervised domain adaptation task for disentangling the low-quality factors, medical image content, and illumination style characteristics by exploring intrinsic supervision in the low-quality medical images. Finally, we perform extensive experiments on six benchmark datasets of medical images, and the experimental results demonstrate that DASQE attains state-of-the-art performance. Furthermore, we explore the impact of the proposed method on various clinical tasks, such as retinal fundus vessel/lesion segmentation, nerve fiber segmentation, polyp segmentation, skin lesion segmentation, and disease classification. The results demonstrate that DASQE is advantageous for diverse downstream image analysis tasks.
RESUMO
In the medical field, datasets are mostly integrated across sites due to difficult data acquisition and insufficient data at a single site. The domain shift problem caused by the heterogeneous distribution among multi-site data makes autism spectrum disorder (ASD) hard to identify. Recently, domain adaptation has received considerable attention as a promising solution. However, domain adaptation on graph data like brain networks has not been fully studied. It faces two major challenges: (1) complex graph structure; and (2) multiple source domains. To overcome the issues, we propose an end-to-end structure-aware domain adaptation framework for brain network analysis (BrainDAS) using resting-state functional magnetic resonance imaging (rs-fMRI). The proposed approach contains two stages: supervision-guided multi-site graph domain adaptation with dynamic kernel generation and graph classification with attention-based graph pooling. We evaluate our BrainDAS on a public dataset provided by Autism Brain Imaging Data Exchange (ABIDE) which includes 871 subjects from 17 different sites, surpassing state-of-the-art algorithms in several different evaluation settings. Furthermore, our promising results demonstrate the interpretability and generalization of the proposed method. Our code is available at https://github.com/songruoxian/BrainDAS.
Assuntos
Algoritmos , Transtorno do Espectro Autista , Imageamento por Ressonância Magnética , Humanos , Imageamento por Ressonância Magnética/métodos , Transtorno do Espectro Autista/diagnóstico por imagem , Encéfalo/diagnóstico por imagem , Rede Nervosa/diagnóstico por imagem , Processamento de Imagem Assistida por Computador/métodosRESUMO
Colorectal cancer is a prevalent and life-threatening disease, where colorectal cancer liver metastasis (CRLM) exhibits the highest mortality rate. Currently, surgery stands as the most effective curative option for eligible patients. However, due to the insufficient performance of traditional methods and the lack of multi-modality MRI feature complementarity in existing deep learning methods, the prognosis of CRLM surgical resection has not been fully explored. This paper proposes a new method, multi-modal guided complementary network (MGCNet), which employs multi-sequence MRI to predict 1-year recurrence and recurrence-free survival in patients after CRLM resection. In light of the complexity and redundancy of features in the liver region, we designed the multi-modal guided local feature fusion module to utilize the tumor features to guide the dynamic fusion of prognostically relevant local features within the liver. On the other hand, to solve the loss of spatial information during multi-sequence MRI fusion, the cross-modal complementary external attention module designed an external mask branch to establish inter-layer correlation. The results show that the model has accuracy (ACC) of 0.79, the area under the curve (AUC) of 0.84, C-Index of 0.73, and hazard ratio (HR) of 4.0, which is a significant improvement over state-of-the-art methods. Additionally, MGCNet exhibits good interpretability.
Assuntos
Neoplasias Colorretais , Neoplasias Hepáticas , Humanos , Prognóstico , Neoplasias Hepáticas/diagnóstico por imagem , Neoplasias Hepáticas/cirurgia , Imageamento por Ressonância Magnética , Neoplasias Colorretais/diagnóstico por imagem , Neoplasias Colorretais/cirurgiaRESUMO
A benchmark histopathological Hematoxylin and Eosin (H&E) image dataset for Cervical Adenocarcinoma in Situ (CAISHI), containing 2240 histopathological images of Cervical Adenocarcinoma in Situ (AIS), is established to fill the current data gap, of which 1010 are images of normal cervical glands and another 1230 are images of cervical AIS. The sampling method is endoscope biopsy. Pathological sections are obtained by H&E staining from Shengjing Hospital, China Medical University. These images have a magnification of 100 and are captured by the Axio Scope. A1 microscope. The size of the image is 3840 × 2160 pixels, and the format is ".png". The collection of CAISHI is subject to an ethical review by China Medical University with approval number 2022PS841K. These images are analyzed at multiple levels, including classification tasks and image retrieval tasks. A variety of computer vision and machine learning methods are used to evaluate the performance of the data. For classification tasks, a variety of classical machine learning classifiers such as k-means, support vector machines (SVM), and random forests (RF), as well as convolutional neural network classifiers such as Residual Network 50 (ResNet50), Vision Transformer (ViT), Inception version 3 (Inception-V3), and Visual Geometry Group Network 16 (VGG-16), are used. In addition, the Siamese network is used to evaluate few-shot learning tasks. In terms of image retrieval functions, color features, texture features, and deep learning features are extracted, and their performances are tested. CAISHI can help with the early diagnosis and screening of cervical cancer. Researchers can use this dataset to develop new computer-aided diagnostic tools that could improve the accuracy and efficiency of cervical cancer screening and advance the development of automated diagnostic algorithms.