RESUMO
Deformable image registration is one of the essential processes in analyzing medical images. In particular, when diagnosing abdominal diseases such as hepatic cancer and lymphoma, multi-domain images scanned from different modalities or different imaging protocols are often used. However, they are not aligned due to scanning times, patient breathing, movement, etc. Although recent learning-based approaches can provide deformations in real-time with high performance, multi-domain abdominal image registration using deep learning is still challenging since the images in different domains have different characteristics such as image contrast and intensity ranges. To address this, this paper proposes a novel unsupervised multi-domain image registration framework using neural optimal transport, dubbed OTMorph. When moving and fixed volumes are given as input, a transport module of our proposed model learns the optimal transport plan to map data distributions from the moving to the fixed volumes and estimates a domain-transported volume. Subsequently, a registration module taking the transported volume can effectively estimate the deformation field, leading to deformation performance improvement. Experimental results on multi-domain image registration using multi-modality and multi-parametric abdominal medical images demonstrate that the proposed method provides superior deformable registration via the domain-transported image that alleviates the domain gap between the input images. Also, we attain the improvement even on out-of-distribution data, which indicates the superior generalizability of our model for the registration of various medical images. Our source code is available at https://github.com/boahK/OTMorph.
RESUMO
Multi-parametric magnetic resonance imaging (mpMRI) exams have various series types acquired with different imaging protocols. The DICOM headers of these series often have incorrect information due to the sheer diversity of protocols and occasional technologist errors. To address this, we present a deep learning-based classification model to classify 8 different body mpMRI series types so that radiologists read the exams efficiently. Using mpMRI data from various institutions, multiple deep learning-based classifiers of ResNet, EfficientNet, and DenseNet are trained to classify 8 different MRI series, and their performance is compared. Then, the best-performing classifier is identified, and its classification capability under the setting of different training data quantities is studied. Also, the model is evaluated on the out-of-training-distribution datasets. Moreover, the model is trained using mpMRI exams obtained from different scanners in two training strategies, and its performance is tested. Experimental results show that the DenseNet-121 model achieves the highest F1-score and accuracy of 0.966 and 0.972 over the other classification models with p-value 0.05. The model shows greater than 0.95 accuracy when trained with over 729 studies of the training data, whose performance improves as the training data quantities grew larger. On the external data with the DLDS and CPTAC-UCEC datasets, the model yields 0.872 and 0.810 accuracy for each. These results indicate that in both the internal and external datasets, the DenseNet-121 model attains high accuracy for the task of classifying 8 body MRI series types.
RESUMO
Multi-parametric MRI (mpMRI) studies are widely available in clinical practice for the diagnosis of various diseases. As the volume of mpMRI exams increases yearly, there are concomitant inaccuracies that exist within the DICOM header fields of these exams. This precludes the use of the header information for the arrangement of the different series as part of the radiologist's hanging protocol, and clinician oversight is needed for correction. In this pilot work, we propose an automated framework to classify the type of 8 different series in mpMRI studies. We used 1,363 studies acquired by three Siemens scanners to train a DenseNet-121 model with 5-fold cross-validation. Then, we evaluated the performance of the DenseNet-121 ensemble on a held-out test set of 313 mpMRI studies. Our method achieved an average precision of 96.6%, sensitivity of 96.6%, specificity of 99.6%, and F 1 score of 96.6% for the MRI series classification task. To the best of our knowledge, we are the first to develop a method to classify the series type in mpMRI studies acquired at the level of the chest, abdomen, and pelvis. Our method has the capability for robust automation of hanging protocols in modern radiology practice.
RESUMO
BACKGROUND: Segmentation of organs and structures in abdominal MRI is useful for many clinical applications, such as disease diagnosis and radiotherapy. Current approaches have focused on delineating a limited set of abdominal structures (13 types). To date, there is no publicly available abdominal MRI dataset with voxel-level annotations of multiple organs and structures. Consequently, a segmentation tool for multi-structure segmentation is also unavailable. METHODS: We curated a T1-weighted abdominal MRI dataset consisting of 195 patients who underwent imaging at National Institutes of Health (NIH) Clinical Center. The dataset comprises of axial pre-contrast T1, arterial, venous, and delayed phases for each patient, thereby amounting to a total of 780 series (69,248 2D slices). Each series contains voxel-level annotations of 62 abdominal organs and structures. A 3D nnUNet model, dubbed as MRISegmentator-Abdomen (MRISegmentator in short), was trained on this dataset, and evaluation was conducted on an internal test set and two large external datasets: AMOS22 and Duke Liver. The predicted segmentations were compared against the ground-truth using the Dice Similarity Coefficient (DSC) and Normalized Surface Distance (NSD). FINDINGS: MRISegmentator achieved an average DSC of 0.861$\pm$0.170 and a NSD of 0.924$\pm$0.163 in the internal test set. On the AMOS22 dataset, MRISegmentator attained an average DSC of 0.829$\pm$0.133 and a NSD of 0.908$\pm$0.067. For the Duke Liver dataset, an average DSC of 0.933$\pm$0.015 and a NSD of 0.929$\pm$0.021 was obtained. INTERPRETATION: The proposed MRISegmentator provides automatic, accurate, and robust segmentations of 62 organs and structures in T1-weighted abdominal MRI sequences. The tool has the potential to accelerate research on various clinical topics, such as abnormality detection, radiotherapy, disease classification among others.
RESUMO
BACKGRUOUND: Osteoporosis is the most common metabolic bone disease and can cause fragility fractures. Despite this, screening utilization rates for osteoporosis remain low among populations at risk. Automated bone mineral density (BMD) estimation using computed tomography (CT) can help bridge this gap and serve as an alternative screening method to dual-energy X-ray absorptiometry (DXA). METHODS: The feasibility of an opportunistic and population agnostic screening method for osteoporosis using abdominal CT scans without bone densitometry phantom-based calibration was investigated in this retrospective study. A total of 268 abdominal CT-DXA pairs and 99 abdominal CT studies without DXA scores were obtained from an oncology specialty clinic in the Republic of Korea. The center axial CT slices from the L1, L2, L3, and L4 lumbar vertebrae were annotated with the CT slice level and spine segmentation labels for each subject. Deep learning models were trained to localize the center axial slice from the CT scan of the torso, segment the vertebral bone, and estimate BMD for the top four lumbar vertebrae. RESULTS: Automated vertebra-level DXA measurements showed a mean absolute error (MAE) of 0.079, Pearson's r of 0.852 (P<0.001), and R2 of 0.714. Subject-level predictions on the held-out test set had a MAE of 0.066, Pearson's r of 0.907 (P<0.001), and R2 of 0.781. CONCLUSION: CT scans collected during routine examinations without bone densitometry calibration can be used to generate DXA BMD predictions.
Assuntos
Absorciometria de Fóton , Densidade Óssea , Vértebras Lombares , Osteoporose , Tomografia Computadorizada por Raios X , Humanos , Osteoporose/diagnóstico por imagem , Osteoporose/diagnóstico , Tomografia Computadorizada por Raios X/métodos , Feminino , Absorciometria de Fóton/métodos , Estudos Retrospectivos , Pessoa de Meia-Idade , Masculino , Idoso , Vértebras Lombares/diagnóstico por imagem , Programas de Rastreamento/métodos , República da Coreia , Aprendizado ProfundoRESUMO
Multi-parametric MRI of the body is routinely acquired for the identification of abnormalities and diagnosis of diseases. However, a standard naming convention for the MRI protocols and associated sequences does not exist due to wide variations in imaging practice at institutions and myriad MRI scanners from various manufacturers being used for imaging. The intensity distributions of MRI sequences differ widely as a result, and there also exists information conflicts related to the sequence type in the DICOM headers. At present, clinician oversight is necessary to ensure that the correct sequence is being read and used for diagnosis. This poses a challenge when specific series need to be considered for building a cohort for a large clinical study or for developing AI algorithms. In order to reduce clinician oversight and ensure the validity of the DICOM headers, we propose an automated method to classify the 3D MRI sequence acquired at the levels of the chest, abdomen, and pelvis. In our pilot work, our 3D DenseNet-121 model achieved an F1 score of 99.5% at differentiating 5 common MRI sequences obtained by three Siemens scanners (Aera, Verio, Biograph mMR). To the best of our knowledge, we are the first to develop an automated method for the 3D classification of MRI sequences in the chest, abdomen, and pelvis, and our work has outperformed the previous state-of-the-art MRI series classifiers.
RESUMO
Blood vessel segmentation in medical imaging is one of the essential steps for vascular disease diagnosis and interventional planning in a broad spectrum of clinical scenarios in image-based medicine and interventional medicine. Unfortunately, manual annotation of the vessel masks is challenging and resource-intensive due to subtle branches and complex structures. To overcome this issue, this paper presents a self-supervised vessel segmentation method, dubbed the contrastive diffusion adversarial representation learning (C-DARL) model. Our model is composed of a diffusion module and a generation module that learns the distribution of multi-domain blood vessel data by generating synthetic vessel images from diffusion latent. Moreover, we employ contrastive learning through a mask-based contrastive loss so that the model can learn more realistic vessel representations. To validate the efficacy, C-DARL is trained using various vessel datasets, including coronary angiograms, abdominal digital subtraction angiograms, and retinal imaging. Experimental results confirm that our model achieves performance improvement over baseline methods with noise robustness, suggesting the effectiveness of C-DARL for vessel segmentation.Our source code is available at https://github.com/boahK/MEDIA_CDARL.2.
Assuntos
Aprendizagem , Retina , Humanos , Angiografia Coronária , Difusão , Software , Processamento de Imagem Assistida por ComputadorRESUMO
INTRODUCTION: Multimorbidity is defined as the presence of two or more chronic diseases. Co-occurring diseases can have synergistic negative effects, and are associated with significant impacts on individual health outcomes and healthcare systems. However, the specific effects of diseases in combination will vary between different diseases. Identifying which diseases are most likely to co-occur in multimorbidity is an important step towards population health assessment and development of policies to prevent and manage multimorbidity more effectively and efficiently. The goal of this project is to conduct a systematic review and meta-analysis of studies of disease clustering in multimorbidity, in order to identify multimorbid disease clusters and test their stability. METHODS AND ANALYSIS: We will review data from studies of multimorbidity that have used data clustering methodologies to reveal patterns of disease co-occurrence. We propose a network-based meta-analytic approach to perform meta-clustering on a select list of chronic diseases that are identified as priorities for multimorbidity research. We will assess the stability of obtained disease clusters across the research literature to date, in order to evaluate the strength of evidence for specific disease patterns in multimorbidity. ETHICS AND DISSEMINATION: This study does not require ethics approval as the work is based on published research studies. The study findings will be published in a peer-reviewed journal and disseminated through conference presentations and meetings with knowledge users in health systems and public health spheres. PROSPERO REGISTRATION NUMBER: CRD42023411249.
Assuntos
Hotspot de Doença , Multimorbidade , Humanos , Atenção à Saúde , Doença Crônica , Revisão por Pares , Projetos de Pesquisa , Metanálise como Assunto , Revisões Sistemáticas como AssuntoRESUMO
OBJECTIVE: Informal caregivers are playing a vital role in improving the degree to which older adults access community and healthcare systems in a more seamless and timely manner, thereby fulfilling their complex needs. It is critical to understand their experiences and perspectives while navigating these systems. This review aimed to identify and organise the research findings on the roles and experiences of informal caregivers of older adults while navigating community and healthcare systems. DESIGN: This scoping review was undertaken according to the Joanna Briggs Institute's Reviewer manual. Four databases were used: AgeLine, PsycINFO, CINAHL and Medline to capture literature with a focus on informal caregivers whose care recipients are aged 55 years or older. Articles were included if they focused on examining the experience, perspective and/or role of informal caregivers in providing care for their older care recipients, while articles were excluded if they only focused on healthcare professionals or older adults. RESULTS: A total of 24 studies were identified that met the study inclusion criteria. This review elucidated the roles of caregivers as a primary system navigator and as an advocate for older adults. Numerous challenges/barriers in system navigation were uncovered, such as lack of consistency in fragmented systems, as well as facilitators, including interface/coordination roles. Finally, recommendations for better system navigation such as caregiver engagement and integration of continuity of care services were identified. CONCLUSION: The need to raise the visibility of the roles and experiences of informal caregivers in system navigation was highlighted. Further research needs to focus on implementing interventions for informal caregivers incorporating a care coordinator to fill the care gap within community and healthcare systems. This review has the potential to foster greater integration of community and healthcare systems.
Assuntos
Cuidadores , Atenção à Saúde , Idoso , Humanos , Família , Pessoal de Saúde , Pessoa de Meia-IdadeRESUMO
Blood vessel segmentation in medical imaging is one of the essential steps for vascular disease diagnosis and interventional planning in a broad spectrum of clinical scenarios in image-based medicine and interventional medicine. Unfortunately, manual annotation of the vessel masks is challenging and resource-intensive due to subtle branches and complex structures. To overcome this issue, this paper presents a self-supervised vessel segmentation method, dubbed the contrastive diffusion adversarial representation learning (C-DARL) model. Our model is composed of a diffusion module and a generation module that learns the distribution of multi-domain blood vessel data by generating synthetic vessel images from diffusion latent. Moreover, we employ contrastive learning through a mask-based contrastive loss so that the model can learn more realistic vessel representations. To validate the efficacy, C-DARL is trained using various vessel datasets, including coronary angiograms, abdominal digital subtraction angiograms, and retinal imaging. Experimental results confirm that our model achieves performance improvement over baseline methods with noise robustness, suggesting the effectiveness of C-DARL for vessel segmentation.
RESUMO
OBJECTIVES: This paper examines the longitudinal effects of the COVID-19 pandemic on older adults (65+) with multimorbidity on levels of depression, anxiety, and perceived global impact on their lives. METHODS: Baseline (2011-2015) and Follow-up 1 (2015-2018) data from the Canadian Longitudinal Study on Aging (CLSA), and the Baseline and Exit waves of the CLSA COVID-19 study (April-December, 2020) (n = 18,099). Multimorbidity was measured using: a) an additive scale of chronic conditions; and b) six chronic disease clusters. Linear Mixed Models were employed to test hypotheses. RESULTS: Number of chronic conditions pre-pandemic was associated with pandemic levels of depression (estimate = 0.40, 95% CI: [0.37,0.44]); anxiety (estimate = 0.20, 95% CI: [0.18, 0.23]); and perceived negative impact of the pandemic (OR = 1.04, 95% CI: [1.02, 1.06]). The associations between multimorbidity and anxiety decreased during the period of the COVID-19 surveys (estimate = -0.02, 95% CI: [-0.05, -0.01]); whereas the multimorbidity association with perceived impact increased (OR = 1.03, 95% CI: [1.01, 1.05]). CONCLUSIONS: This study demonstrates that pre-pandemic multimorbidity conditions are associated with worsening mental health. CLINICAL IMPLICATIONS: Clinicians treating mental health of older adults need to consider the joint effects of multimorbidity conditions and pandemic experiences to tailor counseling and other treatment protocols.
RESUMO
Recently, distributed learning approaches have been studied for using data from multiple sources without sharing them, but they are not usually suitable in applications where each client carries out different tasks. Meanwhile, Transformer has been widely explored in computer vision area due to its capability to learn the common representation through global attention. By leveraging the advantages of Transformer, here we present a new distributed learning framework for multiple image processing tasks, allowing clients to learn distinct tasks with their local data. This arises from a disentangled representation of local and non-local features using a task-specific head/tail and a task-agnostic Vision Transformer. Each client learns a translation from its own task to a common representation using the task-specific networks, while the Transformer body on the server learns global attention between the features embedded in the representation. To enable decomposition between the task-specific and common representations, we propose an alternating training strategy between clients and server. Experimental results on distributed learning for various tasks show that our method synergistically improves the performance of each client with its own data.
RESUMO
Image registration is a fundamental task in medical image analysis. Recently, many deep learning based image registration methods have been extensively investigated due to their comparable performance with the state-of-the-art classical approaches despite the ultra-fast computational time. However, the existing deep learning methods still have limitations in the preservation of original topology during the deformation with registration vector fields. To address this issues, here we present a cycle-consistent deformable image registration, dubbed CycleMorph. The cycle consistency enhances image registration performance by providing an implicit regularization to preserve topology during the deformation. The proposed method is so flexible that it can be applied for both 2D and 3D registration problems for various applications, and can be easily extended to multi-scale implementation to deal with the memory issues in large volume registration. Experimental results on various datasets from medical and non-medical applications demonstrate that the proposed method provides effective and accurate registration on diverse image pairs within a few seconds. Qualitative and quantitative evaluations on deformation fields also verify the effectiveness of the cycle consistency of the proposed method.
Assuntos
Algoritmos , Processamento de Imagem Assistida por Computador , HumanosRESUMO
Recent state-of-the-art image segmentation algorithms are mostly based on deep neural networks, thanks to their high performance and fast computation time. However, these methods are usually trained in a supervised manner, which requires large number of high quality ground-truth segmentation masks. On the other hand, classical image segmentation approaches such as level-set methods are formulated in a self-supervised manner by minimizing energy functions such as Mumford-Shah functional, so they are still useful to help generation of segmentation masks without labels. Unfortunately, these algorithms are usually computationally expensive and often have limitation in semantic segmentation. In this paper, we propose a novel loss function based on Mumford-Shah functional that can be used in deep-learning based image segmentation without or with small labeled data. This loss function is based on the observation that the softmax layer of deep neural networks has striking similarity to the characteristic function in the Mumford-Shah functional. We show that the new loss function enables semi-supervised and unsupervised segmentation. In addition, our loss function can be also used as a regularized function to enhance supervised semantic segmentation algorithms. Experimental results on multiple datasets demonstrate the effectiveness of the proposed method.
RESUMO
Increased dopamine availability may be associated with impaired structural maturation of brain white matter connectivity. This study aimed to derive a comprehensive, whole-brain characterization of large-scale axonal connectivity differences in attention-deficit/hyperactivity disorder (ADHD) associated with catechol-O-methyltransferase gene (COMT) Val158Met polymorphism. Using diffusion tensor imaging, whole-brain tractography, and an imaging connectomics approach, we characterized altered white matter connectivity in youth with ADHD who were COMT Val-homozygous (N = 29) compared with those who were Met-carriers (N = 29). Additionally, we examined whether dopamine transporter gene (DAT1) and dopamine D4 receptor gene (DRD4) polymorphisms were associated with white matter differences. Level of attention was assessed using the continuous performance test before and after an 8-week open-label trial of methylphenidate (MPH). A network of white matter connections linking 18 different brain regions was significantly weakened in youth with ADHD who were COMT Met-carriers compared to those who were Val-homozygous (P < 0.05, family-wise error-corrected). A measure of white matter integrity, fractional anisotropy, was correlated with impaired pretreatment performance in continuous performance test omission errors and response time variability, as well as with improvement in continuous performance test response time variability after MPH treatment. Altered white matter connectivity was exclusively based on COMT genotypes, and was not evident in DAT1 or DRD4. We demonstrated that white matter connectivity in youth with ADHD is associated with COMT Val158Met genotypes. The present findings suggest that different layers of dopamine-related genes and interindividual variability in the genetic polymorphisms should be taken into account when investigating the human connectome.
Assuntos
Transtorno do Deficit de Atenção com Hiperatividade/genética , Transtorno do Deficit de Atenção com Hiperatividade/patologia , Encéfalo/patologia , Catecol O-Metiltransferase/genética , Polimorfismo Genético , Substância Branca/patologia , Anisotropia , Transtorno do Deficit de Atenção com Hiperatividade/tratamento farmacológico , Encéfalo/efeitos dos fármacos , Mapeamento Encefálico , Estimulantes do Sistema Nervoso Central/farmacologia , Criança , Conectoma , Imagem de Tensor de Difusão , Feminino , Genótipo , Humanos , Masculino , Metilfenidato/uso terapêutico , Substância Branca/efeitos dos fármacosRESUMO
INTRODUCTION: Internet gaming disorder (IGD) and alcohol dependence (AD) have been reported to share clinical characteristics including craving and over-engagement despite negative consequences. However, there are also clinical factors that differ between individuals with IGD and those with AD in terms of chemical intoxication, prevalence age, and visual and auditory stimulation. METHODS: We assessed brain functional connectivity within the prefrontal, striatum, and temporal lobe in 15 patients with IGD and in 16 patients with AD. Symptoms of depression, anxiety, and the attention deficit hyperactivity disorder were assessed in patients with IGD and in patients with AD. RESULTS: Both AD and IGD subjects have positive functional connectivity between the dorsolateral prefrontal cortex (DLPFC), cingulate, and cerebellum. In addition, both groups have negative functional connectivity between the DLPFC and the orbitofrontal cortex. However, the AD subjects have positive functional connectivity between the DLPFC, temporal lobe and striatal areas while IGD subjects have negative functional connectivity between the DLPFC, temporal lobe and striatal areas. CONCLUSIONS: AD and IGD subjects may share deficits in executive function, including problems with self-control and adaptive responding. However, the negative connectivity between the DLPFC and the striatal areas in IGD subjects, different from the connectivity observed in AD subjects, may be due to the earlier prevalence age, different comorbid diseases as well as visual and auditory stimulation.