The number of international benchmarking competitions is steadily increasing in various fields of machine learning (ML) research and practice. So far, however, little is known about the common practice as well as bottlenecks faced by the community in tackling the research questions posed. To shed light on the status quo of algorithm development in the specific field of biomedical imaging analysis, we designed an international survey that was issued to all participants of challenges conducted in conjunction with the IEEE ISBI 2021 and MICCAI 2021 conferences (80 competitions in total). The survey covered participants' expertise and working environments, their chosen strategies, as well as algorithm characteristics. A median of 72% challenge participants took part in the survey. According to our results, knowledge exchange was the primary incentive (70%) for participation, while the reception of prize money played only a minor role (16%). While a median of 80 working hours was spent on method development, a large portion of participants stated that they did not have enough time for method development (32%). 25% perceived the infrastructure to be a bottleneck. Overall, 94% of all solutions were deep learning-based. Of these, 84% were based on standard architectures. 43% of the respondents reported that the data samples (e.g., images) were too large to be processed at once. This was most commonly addressed by patch-based training (69%), downsampling (37%), and solving 3D analysis tasks as a series of 2D tasks. K-fold cross-validation on the training set was performed by only 37% of the participants and only 50% of the participants performed ensembling based on multiple identical models (61%) or heterogeneous models (39%). 48% of the respondents applied postprocessing steps.
translated by 谷歌翻译
绘制因果推断的基本挑战是,任何单位都没有完全观察到反事实。此外,在观察性研究中,治疗分配可能会混淆。在不满足的条件下,已经出现了许多统计方法,这些方法在给定预处理的协变量下,包括基于倾向得分的方法,基于预后分数的方法和双重稳健方法。不幸的是,对于应用研究人员而言,没有“一定大小的”因果方法可以在普遍上表现出色。实际上,因果方法主要根据手工制作的模拟数据进行定量评估。这样的数据产生程序可能具有有限的价值,因为它们通常是现实的风格化模型。它们被简化为障碍性,缺乏现实世界数据的复杂性。对于应用研究人员,了解方法对手头数据的表现效果很好至关重要。我们的工作介绍了基于生成模型的深层框架,以验证因果推理方法。该框架的新颖性源于其产生锚定在观察到的样品的经验分布上的合成数据的能力,因此与后者几乎没有区别。该方法使用户可以为因果效应的形式和幅度指定地面真理,并将偏见作为协变量的功能。因此,模拟数据集用于评估与观察到的样本相似的数据时,各种因果估计方法的潜在性能。我们证明了Credence在广泛的仿真研究中准确评估因果估计技术的相对性能以及来自Lalonde和Project Star研究的两个现实世界数据应用的能力。
translated by 谷歌翻译
We present a Machine Learning (ML) study case to illustrate the challenges of clinical translation for a real-time AI-empowered echocardiography system with data of ICU patients in LMICs. Such ML case study includes data preparation, curation and labelling from 2D Ultrasound videos of 31 ICU patients in LMICs and model selection, validation and deployment of three thinner neural networks to classify apical four-chamber view. Results of the ML heuristics showed the promising implementation, validation and application of thinner networks to classify 4CV with limited datasets. We conclude this work mentioning the need for (a) datasets to improve diversity of demographics, diseases, and (b) the need of further investigations of thinner models to be run and implemented in low-cost hardware to be clinically translated in the ICU in LMICs. The code and other resources to reproduce this work are available at https://github.com/vital-ultrasound/ai-assisted-echocardiography-for-low-resource-countries.
translated by 谷歌翻译
Like fingerprints, cortical folding patterns are unique to each brain even though they follow a general species-specific organization. Some folding patterns have been linked with neurodevelopmental disorders. However, due to the high inter-individual variability, the identification of rare folding patterns that could become biomarkers remains a very complex task. This paper proposes a novel unsupervised deep learning approach to identify rare folding patterns and assess the degree of deviations that can be detected. To this end, we preprocess the brain MR images to focus the learning on the folding morphology and train a beta-VAE to model the inter-individual variability of the folding. We compare the detection power of the latent space and of the reconstruction errors, using synthetic benchmarks and one actual rare configuration related to the central sulcus. Finally, we assess the generalization of our method on a developmental anomaly located in another region. Our results suggest that this method enables encoding relevant folding characteristics that can be enlightened and better interpreted based on the generative power of the beta-VAE. The latent space and the reconstruction errors bring complementary information and enable the identification of rare patterns of different nature. This method generalizes well to a different region on another dataset. Code is available at https://github.com/neurospin-projects/2022_lguillon_rare_folding_detection.
translated by 谷歌翻译
本文描述了(r)ules(o)f(t)he(r)oad(a)dvisor,该代理提供了推荐的和可能从一组人级规则生成的动作。我们以形式和示例描述了Rotra的架构和设计。具体来说,我们使用Rotra正式化和实施英国“道路规则”,并描述如何将其纳入自动驾驶汽车中,从而可以内部推荐遵守道路规则。此外,根据《英国公路法典》(《道路规则》),规定规则是否必须采取行动,或者仅建议采取行动,以指示生成的可能的措施。利用该系统的好处包括能够适应不同司法管辖区的不同法规;允许从规则到行为的清晰可追溯性,并提供外部自动责任机制,可以检查在某些给定情况下是否遵守规则。通过具体的示例,对自动驾驶汽车的模拟显示如何通过将自动驾驶汽车放置在许多情况下,这些场景测试了汽车遵守道路规则的能力。合并该系统的自动驾驶汽车能够确保他们遵守道路和外部(法律或监管机构的规则透明工作,从而使汽车公司,司法管辖区和公众之间的信任更大。
translated by 谷歌翻译
本文比较了软件定义网络中的网络安全性的两种深入强化学习方法。对深Q网络的神经情节控制已实施,并将其与双重深Q网络进行了比较。这两种算法以类似于零和游戏的格式实现。对两个游戏结果进行了两尾t检验分析,其中包含为防守者赢得的冠军的数量。另一个比较是在各自游戏中代理商的游戏得分上进行的。进行分析是为了确定哪种算法是游戏表演者最好的算法,以及它们之间是否存在显着差异,证明一个算法是否会更偏爱另一个。发现两种方法之间没有显着统计差异。
translated by 谷歌翻译
从机器学习的角度来看,当前的语音识别体系结构的表现非常出色,因此用户互动。这表明他们很好地模拟了人类生物系统。我们调查是否可以颠倒推论以提供对该生物系统的见解。特别是听力机制。使用SINCNET,我们确认端到端系统确实学习了众所周知的滤纸结构。但是,我们还表明,在学习结构中,更宽的带宽过滤器很重要。虽然可以通过初始化狭窄和宽带过滤器来获得一些好处,但生理上的限制表明,这种过滤器是在中脑而不是耳蜗中出现的。我们表明,必须修改标准的机器学习体系结构,以允许神经模拟此过程。
translated by 谷歌翻译
多模式学习通过在预测过程中同样组合多个输入数据模式来重点关注培训模型。但是,这种相等的组合可能不利于预测准确性,因为不同的方式通常伴随着不同水平的不确定性。通过几种方法研究了使用这种不确定性来组合模式,但是成功有限,因为这些方法旨在处理特定的分类或细分问题,并且不能轻易地转化为其他任务,或者遭受数值的不稳定性。在本文中,我们提出了一种新的不确定性多模式学习者,该学习者通过通过跨模式随机网络预测(CRNP)测量特征密度来估计不确定性。 CRNP旨在几乎不需要适应来在不同的预测任务之间转换,同时进行稳定的培训过程。从技术角度来看,CRNP是探索随机网络预测以估算不确定性并结合多模式数据的第一种方法。对两个3D多模式医学图像分割任务和三个2D多模式计算机视觉分类任务的实验显示了CRNP的有效性,适应性和鲁棒性。此外,我们提供了有关不同融合功能和可视化的广泛讨论,以验证提出的模型。
translated by 谷歌翻译
残疾人在医疗保健,就业和政府政策等各个领域的各种复杂的决策过程中受到各种复杂的决策。这些环境通常已经不透明他们影响的人并缺乏充分的残疾观点代表,它迅速采用人工智能(AI)技术来用于数据分析以告知决策,从而增加因不当或不公平的算法而造成的伤害风险增加。本文介绍了一个通过残疾镜头进行严格检查AI数据分析技术的框架,并研究了AI技术设计师选择的残疾定义如何影响其对残疾分析对象的影响。我们考虑了三种残疾的概念模型:医学模型,社会模型和关系模型;并展示在每个模型下设计的AI技术如何差异很大,以至于与彼此不相容和矛盾。通过讨论有关医疗保健和政府残疾福利中AI分析的常见用例,我们说明了技术设计过程中的特定考虑因素和决策点,这些因素和决策点影响了这些环境中的电力动态和包容性,并有助于确定其对边缘化或支持的方向。我们提出的框架可以作为对AI技术的深入批判性检查的基础,并开发用于残疾相关的AI分析的设计实践。
translated by 谷歌翻译
简介:人工智能(AI)有可能促进CMR分析以进行生物标志物提取的自动化。但是,大多数AI算法都经过特定输入域(例如单扫描仪供应商或医院量化成像协议)的培训,并且当从其他输入域中应用于CMR数据时,缺乏最佳性能的鲁棒性。方法:我们提出的框架包括一种基于AI的算法,用于对短轴图像的双脑室分割,然后进行分析后质量控制,以检测错误的结果。分割算法在来自两家NHS医院(n = 2793)的大型临床CMR扫描数据集上进行了培训,并在此数据集(n = 441)和五个外部数据集(n = 6808)上进行了验证。验证数据包括使用所有主要供应商的CMR扫描仪在12个不同中心获得的一系列疾病的患者的CMR扫描。结果:我们的方法产生的中位骰子得分超过87%,转化为观察者间变异范围内心脏生物标志物中的中值绝对错误:<8.4ml(左心室),<9.2ml(右心室),<13.3G(左心室),<13.3G(左心室所有数据集的心室质量),<5.9%(射血分数)。根据心脏疾病和扫描仪供应商的表型的病例分层显示出良好的一致性。结论:我们表明,我们提出的工具结合了在大规模多域CMR数据集中训练的最先进的AI算法和分析后质量控制,使我们能够从多个中心,供应商和心脏病。这是AI算法临床翻译的基本步骤。此外,我们的方法以无需额外的计算成本而产生一系列心脏功能(填充和弹出率,区域壁运动和应变)的附加生物标志物。
translated by 谷歌翻译