RESUMO
OBJECTIVES: We proposed a new approach to train deep learning model for aneurysm rupture prediction which only uses a limited amount of labeled data. METHOD: Using segmented aneurysm mask as input, a backbone model was pretrained using a self-supervised method to learn deep embeddings of aneurysm morphology from 947 unlabeled cases of angiographic images. Subsequently, the backbone model was finetuned using 120 labeled cases with known rupture status. Clinical information was integrated with deep embeddings to further improve prediction performance. The proposed model was compared with radiomics and conventional morphology models in prediction performance. An assistive diagnosis system was also developed based on the model and was tested with five neurosurgeons. RESULT: Our method achieved an area under the receiver operating characteristic curve (AUC) of 0.823, outperforming deep learning model trained from scratch (0.787). By integrating with clinical information, the proposed model's performance was further improved to AUC = 0.853, making the results significantly better than model based on radiomics (AUC = 0.805, p = 0.007) or model based on conventional morphology parameters (AUC = 0.766, p = 0.001). Our model also achieved the highest sensitivity, PPV, NPV, and accuracy among the others. Neurosurgeons' prediction performance was improved from AUC=0.877 to 0.945 (p = 0.037) with the assistive diagnosis system. CONCLUSION: Our proposed method could develop competitive deep learning model for rupture prediction using only a limited amount of data. The assistive diagnosis system could be useful for neurosurgeons to predict rupture. KEY POINTS: ⢠A self-supervised learning method was proposed to mitigate the data-hungry issue of deep learning, enabling training deep neural network with a limited amount of data. ⢠Using the proposed method, deep embeddings were extracted to represent intracranial aneurysm morphology. Prediction model based on deep embeddings was significantly better than conventional morphology model and radiomics model. ⢠An assistive diagnosis system was developed using deep embeddings for case-based reasoning, which was shown to significantly improve neurosurgeons' performance to predict rupture.
Assuntos
Aneurisma Roto , Aneurisma Intracraniano , Aneurisma Roto/diagnóstico por imagem , Humanos , Aneurisma Intracraniano/diagnóstico por imagem , Redes Neurais de Computação , Curva ROCRESUMO
OBJECTIVES: To investigate the development and clinical characteristics of nail changes in hand, foot, and mouth disease (HFMD). METHODS: A telephone survey was conducted with the parents of patients diagnosed with HFMD in the Fourth General Hospital of Nanhai from June to August 2013 to document nail changes within 3 months of diagnosis of HFMD. RESULTS: Valid survey results were obtained from 273 cases. Definitive nail changes were identified in 56 patients (20.5%). More boys (25.8%) than girls (10.6%) (p < 0.01) showed changes. The age distribution ranged from 1 to 5 years, and nail changes were rare in children younger than 1 year of age (p < 0.01). Nail changes were usually seen 1 to 2 months after the onset of HFMD and lasted for 1 to 8 weeks, most for approximately 4 weeks. Toenails or fingernails could be affected and the changes were more likely to occur synchronously. Fingernails were more commonly involved than toenails. When both fingernails and toenails were involved, this typically occurred synchronously. Although there were cases with all toenails and fingernails involved (16.1%), we did not encounter any instances involving 13 to 19 nails. The nail changes mainly presented as onychomadesis. Spontaneous recovery without special treatment was the course for all patients. No relapse or new nail involvement was identified. CONCLUSIONS: Nail change associated with HFMD usually occurs within 1 to 2 months after onset, mainly presents as onychomadesis, and is a self-limited process. Possible mechanisms are discussed.
Assuntos
Doença de Mão, Pé e Boca/complicações , Doenças da Unha/etiologia , Distribuição por Idade , Criança , Pré-Escolar , China/epidemiologia , Feminino , Inquéritos Epidemiológicos , Humanos , Lactente , Masculino , Unhas , Distribuição por SexoRESUMO
Rupture prediction is crucial for precise treatment and follow-up management of patients with intracranial aneurysms (IAs). Considerable machine learning (ML) methods have been proposed to improve rupture prediction by leveraging electronic medical records (EMRs), however, data scarcity and category imbalance strongly influence performance. Thus, we propose a novel data synthesis method i.e., Transformer-based conditional GAN (TransCGAN), to synthesize highly authentic and category-aware EMRs to address above challenges. Specifically, we first align feature-wise context relationship and distribution between synthetic and original data to enhance synthetic data quality. To achieve this, we first integrate the Transformer structure into GAN to match the contextual relationship by processing the long-range dependencies among clinical factors and introduce a statistical loss to maintain distributional consistency by constraining the mean and variance of the synthesis features. Additionally, a conditional module is designed to assign the category of the synthesis data, thereby addressing the challenge of category imbalance. Subsequently, the synthetic data are merged with the original data to form a large-scale and category-balanced training dataset for IAs rupture prediction. Experimental results show that using TransCGAN's synthetic data enhances classifier performance, achieving AUC of 0.89 and outperforming state-of-the-art resampling methods by 5 %-33 % in F1 score.
RESUMO
PURPOSE: Microvascular decompression (MVD) is a widely used neurosurgical intervention for the treatment of cranial nerves compression. Segmentation of MVD-related structures, including the brainstem, nerves, arteries, and veins, is critical for preoperative planning and intraoperative decision-making. Automatically segmenting structures related to MVD is still challenging for current methods due to the limited information from a single modality and the complex topology of vessels and nerves. METHODS: Considering that it is hard to distinguish MVD-related structures, especially for nerve and vessels with similar topology, we design a multimodal segmentation network with a shared encoder-dual decoder structure and propose a clinical knowledge-driven distillation scheme, allowing reliable knowledge transferred from each decoder to the other. Besides, we introduce a class-wise contrastive module to learn the discriminative representations by maximizing the distance among classes across modalities. Then, a projected topological loss based on persistent homology is proposed to constrain topological continuity. RESULTS: We evaluate the performance of our method on in-house dataset consisting of 100 paired HR-T2WI and 3D TOF-MRA volumes. Experiments indicate that our model outperforms the SOTA in DSC by 1.9% for artery, 3.3% for vein and 0.5% for nerve. Visualization results show our method attains improved continuity and less breakage, which is also consistent with intraoperative images. CONCLUSION: Our method can comprehensively extract the distinct features from multimodal data to segment the MVD-related key structures and preserve the topological continuity, allowing surgeons precisely perceiving the patient-specific target anatomy and substantially reducing the workload of surgeons in the preoperative planning stage. Our resources will be publicly available at https://github.com/JaronTu/Multimodal_MVD_Seg .
Assuntos
Imageamento por Ressonância Magnética , Cirurgia de Descompressão Microvascular , Imagem Multimodal , Humanos , Cirurgia de Descompressão Microvascular/métodos , Imagem Multimodal/métodos , Imageamento por Ressonância Magnética/métodos , Imageamento Tridimensional/métodos , Síndromes de Compressão Nervosa/cirurgiaRESUMO
The need for sustainable and environment-friendly materials has led to growing interest in the development of biodegradable polymers based on natural compounds. However, metal-based catalysts used in the polymerization process may cause concerns about the toxicity of the resultant polymers. Therefore, polymers derived from natural compounds and synthesized through the use of green catalysts are highly desirable. Lipase-catalyzed ring-opening polymerization (ROP) of biocompound-based cyclic monomers has emerged as a promising and green strategy for the design and synthesis of such polymers. In this review, we summarize reports on the use of ROP catalyzed by lipase for cyclic monomers derived from natural compounds, including bile acid- and porphyrin-based macrocycles, carbonate-based macrocycles, lactones, and cyclic anhydrides, with an emphasis on ring-closure reactions for the synthesis of cyclic monomers, the types of lipases for the ROP and the choice of reaction conditions (temperature, solvent, reaction time, etc.). Moreover, the current challenges and perspectives for the choice and reusability of lipases, ring-closure versus ring-opening reactions, monomer design, and potential applications are discussed.
RESUMO
The coronavirus disease 2019 (COVID-19) has become a severe worldwide health emergency and is spreading at a rapid rate. Segmentation of COVID lesions from computed tomography (CT) scans is of great importance for supervising disease progression and further clinical treatment. As labeling COVID-19 CT scans is labor-intensive and time-consuming, it is essential to develop a segmentation method based on limited labeled data to conduct this task. In this paper, we propose a self-ensembled co-training framework, which is trained by limited labeled data and large-scale unlabeled data, to automatically extract COVID lesions from CT scans. Specifically, to enrich the diversity of unsupervised information, we build a co-training framework consisting of two collaborative models, in which the two models teach each other during training by using their respective predicted pseudo-labels of unlabeled data. Moreover, to alleviate the adverse impacts of noisy pseudo-labels for each model, we propose a self-ensembling strategy to perform consistency regularization for the up-to-date predictions of unlabeled data, in which the predictions of unlabeled data are gradually ensembled via moving average at the end of every training epoch. We evaluate our framework on a COVID-19 dataset containing 103 CT scans. Experimental results show that our proposed method achieves better performance in the case of only 4 labeled CT scans compared to the state-of-the-art semi-supervised segmentation networks.
Assuntos
COVID-19 , Aprendizado de Máquina Supervisionado , Humanos , SARS-CoV-2 , Tomografia Computadorizada por Raios XRESUMO
PURPOSE: Microelectrode recordings (MERs) are a significant clinical indicator for sweet spots identification of implanted electrodes during deep brain stimulation of the subthalamic nucleus (STN) surgery. As 1D MERs signals have the unboundedness, large-range, large-amount and time-dependent characteristics, the purpose of this study is to propose an automatic and precise identification method of sweet spots from MERs, reducing the time-consuming and labor-intensive human annotations. METHODS: We propose an automatic identification method of sweet spots from MERs for electrodes implantation in STN-DBS. To better imitate the surgeons' observation and obtain more intuitive contextual information, we first employ the 2D Gramian angular summation field (GASF) images generated from MERs data to perform the sweet spots determination for electrodes implantation. Then, we introduce the convolutional block attention module into convolutional neural network (CNN) to identify the 2D GASF images of sweet spots for electrodes implantation. RESULTS: Experimental results illustrate that the identification result of our method is consistent with the result of doctor's decision, while our method can achieve the accuracy and precision of 96.72% and 98.97%, respectively, which outperforms state-of-the-art for intraoperative sweet spots determination. CONCLUSIONS: The proposed method is the first time to automatically and accurately identify sweet spots from MERs for electrodes implantation by the combination an advanced time series-to-image encoding way with CBAM-enhanced networks model. Our method can assist neurosurgeons in automatically detecting the most likely locations of sweet spots for electrodes implantation, which can provide an important indicator for target selection while it reduces the localization error of the target during STN-DBS surgery.
Assuntos
Estimulação Encefálica Profunda/métodos , Eletrodos Implantados , Microeletrodos , Núcleo Subtalâmico/diagnóstico por imagem , Algoritmos , Análise de Fourier , Humanos , Masculino , Pessoa de Meia-Idade , Doença de Parkinson/cirurgia , Reconhecimento Automatizado de Padrão , Reprodutibilidade dos Testes , Análise de OndaletasRESUMO
To better understand early brain development in health and disorder, it is critical to accurately segment infant brain magnetic resonance (MR) images into white matter (WM), gray matter (GM), and cerebrospinal fluid (CSF). Deep learning-based methods have achieved state-of-the-art performance; h owever, one of the major limitations is that the learning-based methods may suffer from the multi-site issue, that is, the models trained on a dataset from one site may not be applicable to the datasets acquired from other sites with different imaging protocols/scanners. To promote methodological development in the community, the iSeg-2019 challenge (http://iseg2019.web.unc.edu) provides a set of 6-month infant subjects from multiple sites with different protocols/scanners for the participating methods. T raining/validation subjects are from UNC (MAP) and testing subjects are from UNC/UMN (BCP), Stanford University, and Emory University. By the time of writing, there are 30 automatic segmentation methods participated in the iSeg-2019. In this article, 8 top-ranked methods were reviewed by detailing their pipelines/implementations, presenting experimental results, and evaluating performance across different sites in terms of whole brain, regions of interest, and gyral landmark curves. We further pointed out their limitations and possible directions for addressing the multi-site issue. We find that multi-site consistency is still an open issue. We hope that the multi-site dataset in the iSeg-2019 and this review article will attract more researchers to address the challenging and critical multi-site issue in practice.
Assuntos
Algoritmos , Imageamento por Ressonância Magnética , Encéfalo/diagnóstico por imagem , Mapeamento Encefálico , Substância Cinzenta , Humanos , LactenteRESUMO
Segmentation of medical images, particularly late gadolinium-enhanced magnetic resonance imaging (LGE-MRI) used for visualizing diseased atrial structures, is a crucial first step for ablation treatment of atrial fibrillation. However, direct segmentation of LGE-MRIs is challenging due to the varying intensities caused by contrast agents. Since most clinical studies have relied on manual, labor-intensive approaches, automatic methods are of high interest, particularly optimized machine learning approaches. To address this, we organized the 2018 Left Atrium Segmentation Challenge using 154 3D LGE-MRIs, currently the world's largest atrial LGE-MRI dataset, and associated labels of the left atrium segmented by three medical experts, ultimately attracting the participation of 27 international teams. In this paper, extensive analysis of the submitted algorithms using technical and biological metrics was performed by undergoing subgroup analysis and conducting hyper-parameter analysis, offering an overall picture of the major design choices of convolutional neural networks (CNNs) and practical considerations for achieving state-of-the-art left atrium segmentation. Results show that the top method achieved a Dice score of 93.2% and a mean surface to surface distance of 0.7â¯mm, significantly outperforming prior state-of-the-art. Particularly, our analysis demonstrated that double sequentially used CNNs, in which a first CNN is used for automatic region-of-interest localization and a subsequent CNN is used for refined regional segmentation, achieved superior results than traditional methods and machine learning approaches containing single CNNs. This large-scale benchmarking study makes a significant step towards much-improved segmentation methods for atrial LGE-MRIs, and will serve as an important benchmark for evaluating and comparing the future works in the field. Furthermore, the findings from this study can potentially be extended to other imaging datasets and modalities, having an impact on the wider medical imaging community.
Assuntos
Benchmarking , Gadolínio , Algoritmos , Átrios do Coração/diagnóstico por imagem , Humanos , Imageamento por Ressonância MagnéticaRESUMO
BACKGROUND: Segmentation of anatomical structures of the heart from cardiac magnetic resonance images (MRI) has a significant impact on the quantitative analysis of the cardiac contractile function. Although deep convolutional neural networks (ConvNets) have achieved considerable success in medical imaging segmentation, it is still a challenging task for existing deep ConvNets to precisely and automatically segment multiple heart structures from cardiac MRI. This paper presents a novel recurrent interleaved attention network (RIANet) to comprehensively tackle this issue. METHOD: The proposed RIANet can efficiently reuse parameters to encode richer representative features via introducing a recurrent feedback structure, Clique Block, which incorporates both forward and backward connections between different layers with the same resolution. Further, we integrate a plug-and-play interleaved attention (IA) block to modulate the information passed to the decoding stage of RIANet by effectively fusing multi-level contextual information. In addition, we improve the discrimination capability of our RIANet through a deep supervision mechanism with weighted losses. RESULTS: The performance of RIANet has been extensively validated in the segmentation contest of the ACDC 2017 challenge held in conjunction with MICCAI 2017, with mean Dice scores of 0.942 (left ventricular), 0.923 (right ventricular) and 0.910 (myocardium) for cardiac MRI segmentation. Besides, we visualize intermediate features of our RIANet using guided backpropagation, which can intuitively depict the effects of our proposed components in feature representation. CONCLUSION: Experimental results demonstrate that our RIANet have achieved competitive segmentation results with fewer parameters compared with the state-of-the-art approaches, corroborating the effectiveness and robustness of our proposed RIANet.