Alzheimer's disease and Frontotemporal dementia are common types of neurodegenerative disorders that present overlapping clinical symptoms, making their differential diagnosis very challenging. Numerous efforts have been done for the diagnosis of each disease but the problem of multi-class differential diagnosis has not been actively explored. In recent years, transformer-based models have demonstrated remarkable success in various computer vision tasks. However, their use in disease diagnostic is uncommon due to the limited amount of 3D medical data given the large size of such models. In this paper, we present a novel 3D transformer-based architecture using a deformable patch location module to improve the differential diagnosis of Alzheimer's disease and Frontotemporal dementia. Moreover, to overcome the problem of data scarcity, we propose an efficient combination of various data augmentation techniques, adapted for training transformer-based models on 3D structural magnetic resonance imaging data. Finally, we propose to combine our transformer-based model with a traditional machine learning model using brain structure volumes to better exploit the available data. Our experiments demonstrate the effectiveness of the proposed approach, showing competitive results compared to state-of-the-art methods. Moreover, the deformable patch locations can be visualized, revealing the most relevant brain regions used to establish the diagnosis of each disease.
相關內容
ACM/IEEE第23屆模型驅動工程語言和系統國際會議，是模型驅動軟件和系統工程的首要會議系列，由ACM-SIGSOFT和IEEE-TCSE支持組織。自1998年以來，模型涵蓋了建模的各個方面，從語言和方法到工具和應用程序。模特的參加者來自不同的背景，包括研究人員、學者、工程師和工業專業人士。MODELS 2019是一個論壇，參與者可以圍繞建模和模型驅動的軟件和系統交流前沿研究成果和創新實踐經驗。今年的版本將為建模社區提供進一步推進建模基礎的機會，并在網絡物理系統、嵌入式系統、社會技術系統、云計算、大數據、機器學習、安全、開源等新興領域提出建模的創新應用以及可持續性。
官網鏈接： ·
Networking
·
最大匯聚
·
Extensibility
·
損失
·
Automatic segmentation of breast tumors from the ultrasound images is essential for the subsequent clinical diagnosis and treatment plan. Although the existing deep learning-based methods have achieved significant progress in automatic segmentation of breast tumor, their performance on tumors with similar intensity to the normal tissues is still not pleasant, especially for the tumor boundaries. To address this issue, we propose a PBNet composed by a multilevel global perception module (MGPM) and a boundary guided module (BGM) to segment breast tumors from ultrasound images. Specifically, in MGPM, the long-range spatial dependence between the voxels in a single level feature maps are modeled, and then the multilevel semantic information is fused to promote the recognition ability of the model for non-enhanced tumors. In BGM, the tumor boundaries are extracted from the high-level semantic maps using the dilation and erosion effects of max pooling, such boundaries are then used to guide the fusion of low and high-level features. Moreover, to improve the segmentation performance for tumor boundaries, a multi-level boundary-enhanced segmentation (BS) loss is proposed. The extensive comparison experiments on both publicly available dataset and in-house dataset demonstrate that the proposed PBNet outperforms the state-of-the-art methods in terms of both qualitative visualization results and quantitative evaluation metrics, with the Dice score, Jaccard coefficient, Specificity and HD95 improved by 0.70%, 1.1%, 0.1% and 2.5% respectively. In addition, the ablation experiments validate that the proposed MGPM is indeed beneficial for distinguishing the non-enhanced tumors and the BGM as well as the BS loss are also helpful for refining the segmentation contours of the tumor.
Cancer is a significant health issue globally and it is well known that cancer risk varies geographically. However in many countries there are no small area level data on cancer risk factors with high resolution and complete reach, which hinders the development of targeted prevention strategies. Using Australia as a case study, the 2017-2018 National Health Survey was used to generate prevalence estimates for 2221 small areas across Australia for eight cancer risk factor measures covering smoking, alcohol, physical activity, diet and weight. Utilising a recently developed Bayesian two-stage small area estimation methodology, the model incorporated survey-only covariates, spatial smoothing and hierarchical modelling techniques, along with a vast array of small area level auxiliary data, including census, remoteness, and socioeconomic data. The models borrowed strength from previously published cancer risk estimates provided by the Social Health Atlases of Australia. Estimates were internally and externally validated. We illustrated that in 2017-18 health behaviours across Australia exhibited more spatial disparities than previously realised by improving the reach and resolution of formerly published cancer risk factors. The derived estimates reveal higher prevalence of unhealthy behaviours in more remote areas, and areas of lower socioeconomic status; a trend that aligns well with previous work. Our study addresses the gaps in small area level cancer risk factor estimates in Australia. The new estimates provide improved spatial resolution and reach and will enable more targeted cancer prevention strategies at the small area level, supporting policy makers, researchers, and the general public in understanding the spatial distribution of cancer risk factors in Australia. To help disseminate the results of this work, they will be made available in the Australian Cancer Atlas 2.0.
Randomization inference is a powerful tool in early phase vaccine trials to estimate the causal effect of a regimen against a placebo or another regimen. Traditionally, randomization-based inference often focuses on testing either Fisher's sharp null hypothesis of no treatment effect for any unit or Neyman's weak null hypothesis of no sample average treatment effect. Many recent efforts have explored conducting exact randomization-based inference for other summaries of the treatment effect profile, for instance, quantiles of the treatment effect distribution function. In this article, we systematically review methods that conduct exact, randomization-based inference for quantiles of individual treatment effects (ITEs) and extend some results by incorporating auxiliary information often available in a vaccine trial. These methods are suitable for four scenarios: (i) a randomized controlled trial (RCT) where the potential outcomes under one regimen are constant; (ii) an RCT with no restriction on any potential outcomes; (iii) an RCT with some user-specified bounds on potential outcomes; and (iv) a matched study comparing two non-randomized, possibly confounded treatment arms. We then conduct two extensive simulation studies, one comparing the performance of each method in many practical clinical settings and the other evaluating the usefulness of the methods in ranking and advancing experimental therapies. We apply these methods to an early-phase clinical trail, HIV Vaccine Trials Network Study 086 (HVTN 086), to showcase the usefulness of the methods.
Increasing individuals' awareness of their own body signals can lead to improved interoception, enabling the brain to estimate current body states more accurately and in a timely manner. However, certain body signals, such as eye movements, often go unnoticed by individuals themselves. This study aimed to test the hypothesis that providing eye-movement-correlated tactile feedback on the body enhances individuals' awareness of their attentive states, subsequently improving attention. Our results demonstrate the effectiveness of such feedback in redirecting and enhancing attention, particularly in the presence of distractions during long-duration tasks. Additionally, we observed that people's gaze behaviors changed in response to the tactile feedback, suggesting an increased self-awareness of current eye movements and attentive states. Ultimately, these changes in gaze behaviors contribute to the modulation of attentive states. Our findings highlight the potential of eye-movement-correlated bodily tactile feedback to increase individuals' self-awareness of their eye movements and attentive states. By providing real-time feedback through tactile stimuli, we can actively engage individuals in regulating their attention and enhancing their overall performance.
One of the most catastrophic neurological disorders worldwide is Parkinson's Disease. Along with it, the treatment is complicated and abundantly expensive. The only effective action to control the progression is diagnosing it in the early stage. However, this is challenging because early detection necessitates a large and complex clinical study. This experimental work used Machine Learning techniques to automate the early detection of Parkinson's Disease from clinical characteristics, voice features and motor examination. In this study, we develop ML models utilizing a public dataset of 130 individuals, 30 of whom are untreated Parkinson's Disease patients, 50 of whom are Rapid Eye Movement Sleep Behaviour Disorder patients who are at a greater risk of contracting Parkinson's Disease, and 50 of whom are Healthy Controls. We use MinMax Scaler to rescale the data points, Local Outlier Factor to remove outliers, and SMOTE to balance existing class frequency. Afterwards, apply a number of Machine Learning techniques. We implement the approaches in such a way that data leaking and overfitting are not possible. Finally, obtained 100% accuracy in classifying PD and RBD patients, as well as 92% accuracy in classifying PD and HC individuals.
Agent-based models are widely used to predict infectious disease spread. For these predictions, one needs to understand how each input parameter affects the result. Here, some parameters may affect the sensitivities of others, requiring the analysis of higher order coefficients through e.g. Sobol sensitivity analysis. The geographical structures of real-world regions are distinct in that they are difficult to reduce to single parameter values, making a unified sensitivity analysis intractable. Yet analyzing the importance of geographical structure on the sensitivity of other input parameters is important because a strong effect would justify the use of models with real-world geographical representations, as opposed to stylized ones. Here we perform a grouped Sobol's sensitivity analysis on COVID-19 spread simulations across a set of three diverse real-world geographical representations. We study the differences in both results and the sensitivity of non-geographical parameters across these geographies. By comparing Sobol indices of parameters across geographies, we find evidence that infection rate could have more sensitivity in regions where the population is segregated, while parameters like recovery period of mild cases are more sensitive in regions with mixed populations. We also show how geographical structure affects parameter sensitivity changes over time.
The possibility of recognizing diverse aspects of human behavior and environmental context from passively captured data motivates its use for mental health assessment. In this paper, we analyze the contribution of different passively collected sensor data types (WiFi, GPS, Social interaction, Phone Log, Physical Activity, Audio, and Academic features) to predict daily selfreport stress and PHQ-9 depression score. First, we compute 125 mid-level features from the original raw data. These 125 features include groups of features from the different sensor data types. Then, we evaluate the contribution of each feature type by comparing the performance of Neural Network models trained with all features against Neural Network models trained with specific feature groups. Our results show that WiFi features (which encode mobility patterns) and Phone Log features (which encode information correlated with sleep patterns), provide significative information for stress and depression prediction.
Alzheimer's disease is one of the most common types of neurodegenerative disease, characterized by the accumulation of amyloid-beta plaque and tau tangles. Recently, deep learning approaches have shown promise in Alzheimer's disease diagnosis. In this study, we propose a reproducible model that utilizes a 3D convolutional neural network with a dual attention module for Alzheimer's disease classification. We trained the model in the ADNI database and verified the generalizability of our method in two independent datasets (AIBL and OASIS1). Our method achieved state-of-the-art classification performance, with an accuracy of 91.94% for MCI progression classification and 96.30% for Alzheimer's disease classification on the ADNI dataset. Furthermore, the model demonstrated good generalizability, achieving an accuracy of 86.37% on the AIBL dataset and 83.42% on the OASIS1 dataset. These results indicate that our proposed approach has competitive performance and generalizability when compared to recent studies in the field.
The correlation among the gene genealogies at different loci is crucial in biology, yet challenging to understand because such correlation depends on many factors including genetic linkage, recombination, natural selection and population structure. Based on a diploid Wright-Fisher model with a single mating type and partial selfing for a constant large population with size $N$, we quantify the combined effect of genetic drift and two competing factors, recombination and selfing, on the correlation of coalescence times at two linked loci for samples of size two. Recombination decouples the genealogies at different loci and decreases the correlation while selfing increases the correlation. We obtain explicit asymptotic formulas for the correlation for four scaling scenarios that depend on whether the selfing probability and the recombination probability are of order $O(1/N)$ or $O(1)$ as $N$ tends to infinity. Our analytical results confirm that the asymptotic lower bound in [King, Wakeley, Carmi (Theor. Popul. Biol. 2018)] is sharp when the loci are unlinked and when there is no selfing, and provide a number of new formulas for other scaling scenarios that have not been considered before. We present asymptotic results for the variance of Tajima's estimator of the population mutation rate for infinitely many loci as $N$ tends to infinity. When the selfing probability is of order $O(1)$ and is equal to a positive constant $s$ for all $N$ and if the samples at both loci are in the same individual, then the variance of the Tajima's estimator tends to $s/2$ (hence remains positive) even when the recombination rate, the number of loci and the population size all tend to infinity.
Breast cancer remains a global challenge, causing over 1 million deaths globally in 2018. To achieve earlier breast cancer detection, screening x-ray mammography is recommended by health organizations worldwide and has been estimated to decrease breast cancer mortality by 20-40%. Nevertheless, significant false positive and false negative rates, as well as high interpretation costs, leave opportunities for improving quality and access. To address these limitations, there has been much recent interest in applying deep learning to mammography; however, obtaining large amounts of annotated data poses a challenge for training deep learning models for this purpose, as does ensuring generalization beyond the populations represented in the training dataset. Here, we present an annotation-efficient deep learning approach that 1) achieves state-of-the-art performance in mammogram classification, 2) successfully extends to digital breast tomosynthesis (DBT; "3D mammography"), 3) detects cancers in clinically-negative prior mammograms of cancer patients, 4) generalizes well to a population with low screening rates, and 5) outperforms five-out-of-five full-time breast imaging specialists by improving absolute sensitivity by an average of 14%. Our results demonstrate promise towards software that can improve the accuracy of and access to screening mammography worldwide.
小貼士
登錄享
相關主題
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191