互联网公司越来越多地使用机器学习模型来创建分配每个人的个性化政策,为每个人提供最佳预测的待遇。它们通常来自黑盒异质处理效果(HTE)模型,预测单个治疗效果。在本文中,我们专注于(1)HTE模型的学习解释;(2)学习规定待遇任务的可解释政策。我们还提出了指导树木,这一方法可以在没有解释性丧失的情况下集合多种可意识到的政策。这些基于规则的可解释策略很容易部署,避免需要在生产环境中维护HTE模型。
translated by 谷歌翻译
State estimation is important for a variety of tasks, from forecasting to substituting for unmeasured states in feedback controllers. Performing real-time state estimation for PDEs using provably and rapidly converging observers, such as those based on PDE backstepping, is computationally expensive and in many cases prohibitive. We propose a framework for accelerating PDE observer computations using learning-based approaches that are much faster while maintaining accuracy. In particular, we employ the recently-developed Fourier Neural Operator (FNO) to learn the functional mapping from the initial observer state and boundary measurements to the state estimate. By employing backstepping observer gains for previously-designed observers with particular convergence rate guarantees, we provide numerical experiments that evaluate the increased computational efficiency gained with FNO. We consider the state estimation for three benchmark PDE examples motivated by applications: first, for a reaction-diffusion (parabolic) PDE whose state is estimated with an exponential rate of convergence; second, for a parabolic PDE with exact prescribed-time estimation; and, third, for a pair of coupled first-order hyperbolic PDEs that modeling traffic flow density and velocity. The ML-accelerated observers trained on simulation data sets for these PDEs achieves up to three orders of magnitude improvement in computational speed compared to classical methods. This demonstrates the attractiveness of the ML-accelerated observers for real-time state estimation and control.
translated by 谷歌翻译
Chromosome analysis is essential for diagnosing genetic disorders. For hematologic malignancies, identification of somatic clonal aberrations by karyotype analysis remains the standard of care. However, karyotyping is costly and time-consuming because of the largely manual process and the expertise required in identifying and annotating aberrations. Efforts to automate karyotype analysis to date fell short in aberration detection. Using a training set of ~10k patient specimens and ~50k karyograms from over 5 years from the Fred Hutchinson Cancer Center, we created a labeled set of images representing individual chromosomes. These individual chromosomes were used to train and assess deep learning models for classifying the 24 human chromosomes and identifying chromosomal aberrations. The top-accuracy models utilized the recently introduced Topological Vision Transformers (TopViTs) with 2-level-block-Toeplitz masking, to incorporate structural inductive bias. TopViT outperformed CNN (Inception) models with >99.3% accuracy for chromosome identification, and exhibited accuracies >99% for aberration detection in most aberrations. Notably, we were able to show high-quality performance even in "few shot" learning scenarios. Incorporating the definition of clonality substantially improved both precision and recall (sensitivity). When applied to "zero shot" scenarios, the model captured aberrations without training, with perfect precision at >50% recall. Together these results show that modern deep learning models can approach expert-level performance for chromosome aberration detection. To our knowledge, this is the first study demonstrating the downstream effectiveness of TopViTs. These results open up exciting opportunities for not only expediting patient results but providing a scalable technology for early screening of low-abundance chromosomal lesions.
translated by 谷歌翻译
The many successes of deep neural networks (DNNs) over the past decade have largely been driven by computational scale rather than insights from biological intelligence. Here, we explore if these trends have also carried concomitant improvements in explaining the visual strategies humans rely on for object recognition. We do this by comparing two related but distinct properties of visual strategies in humans and DNNs: where they believe important visual features are in images and how they use those features to categorize objects. Across 84 different DNNs trained on ImageNet and three independent datasets measuring the where and the how of human visual strategies for object recognition on those images, we find a systematic trade-off between DNN categorization accuracy and alignment with human visual strategies for object recognition. State-of-the-art DNNs are progressively becoming less aligned with humans as their accuracy improves. We rectify this growing issue with our neural harmonizer: a general-purpose training routine that both aligns DNN and human visual strategies and improves categorization accuracy. Our work represents the first demonstration that the scaling laws that are guiding the design of DNNs today have also produced worse models of human vision. We release our code and data at https://serre-lab.github.io/Harmonization to help the field build more human-like DNNs.
translated by 谷歌翻译
2型糖尿病(T2DM)的早期诊断对于及时的治疗干预措施和生活方式改变至关重要。随着医学成像数据在许多患者群体中变得更广泛可用,我们试图研究是否可以在表格学习分类器模型中利用图像衍生的表型数据来预测T2DM的发病率,而无需使用侵入性血液实验室测量。我们表明,使用图像衍生表型的神经网络和决策树模型都可以预测患者T2DM状态的召回评分高达87.6%。我们还提出了与“ Syntha1c编码器”相同的结构的新颖使用,这些结构能够输出模仿血液血红蛋白A1C经验实验室测量值的可解释值。最后,我们证明了T2DM风险预测模型对输入矢量成分中小扰动的敏感性可用于预测从以前看不见的患者人群中取样的协变量的性能。
translated by 谷歌翻译
在恶性原发性脑肿瘤中,癌细胞浸润到周围的脑结构中,导致不可避免的复发。对周围区域的浸润性异质性(活检或切除可能是危险的区域)的定量评估对于临床决策很重要。以前关于表征周围区域浸润性异质性的工作使用了各种成像方式,但是已经探索了细胞外无水运动限制的信息。在这里,我们通过使用基于扩散的张量成像(DTI)的自由水量分数图来表征一组独特的人工智能(AI)标记,从而捕获肿瘤浸润的异质性,从而捕获肿瘤的异质性。首先通过利用胶质母细胞瘤和脑转移的广泛不同的水扩散性能作为在周围肿瘤组织中有和没有浸润的区域的区域,首先提取了一种新型的基于体素的深度学习周围微环境指数(PMI)。均匀高PMI值的局部枢纽的描述性特征被提取为基于AI的标记,以捕获渗透性异质性的不同方面。提出的标记物应用于两个临床用例,对275个成人型弥漫性神经胶质瘤的独立人群(4级)分析,分析异氯酸盐 - 脱水酶1(IDH1) - wildtypes之间的生存持续时间以及带有IDH1-杀剂的差异。我们的发现提供了一系列标记物作为浸润的替代物,可捕获有关周围微观结构异质性生物学潜在生物学的独特见解,使其成为与生存和分子分层有关的预后生物标志物,并具有潜在的适用性在临床决策中。
translated by 谷歌翻译
捕获和归因于代码变更引起的生产中的性能回归很难;事先预测它们,甚至更努力。关于自动学习预测软件中性能回归的入门,本文介绍了我们在Meta研究和部署基于ML的回归预测管道时获得的经验。在本文中,我们报告了一项比较研究,其复杂性增加了四个ML模型,从(1)代码 - opaque,(2)单词袋,(3)基于转换的变压器到(4)基于定制变压器的模型,创造的超大通信器。我们的调查表明,性能预测问题的固有难度,其特征是良性对回归变化的不平衡。我们的结果还质疑了基于变压器的架构在性能预测中的一般适用性:基于基础的代码伯特方法的性能令人惊讶。我们高度定制的超大号架构最初实现了预测性能,这与简单的单词模型相当,并且仅在下游用例中优于它们。超级人员将其转移到应用程序的这种能力很少有学习示例提供了在Meta实践中部署它的机会:它可以作为预滤波器来解决不太可能引入回归的更改,从而缩小更改空间的变化空间搜索回归高达43%,比随机基线提高45倍。为了进一步洞悉超大号公园,我们通过一系列计算反事实解释进行了探索。这些突出显示了代码的哪些部分更改模型认为重要的,从而验证了学习的黑框模型。
translated by 谷歌翻译
我们提出\ textbf {jaws},这是一系列用于无分配的不确定性量化任务的包装方法,以协变量偏移为中心,以我们的核心方法\ textbf {jaw}为中心,\ textbf {ja} ckknife+ \ textbf {w}八 - 重量。下巴还包括使用高阶影响函数的JAW的计算有效\ TextBf {a} pproximations:\ textbf {jawa}。从理论上讲,我们表明JAW放宽了Jackknife+对数据交换性的假设,即使在协变量转移下,也可以实现相同的有限样本覆盖范围保证。 Jawa在轻度假设下进一步以样本量或影响函数顺序的限制接近JAW保证。此外,我们提出了一种通用方法,以重新利用任何无分配不确定性量化方法及其对风险评估的任务的保证:该任务产生了真正标签在用户指定间隔内的估计概率。然后,我们将\ textbf {Jaw-r}和\ textbf {Jawa-r}作为\ textbf {r} ISK评估的建议方法的重新定义版本。实际上,在各种有偏见的现实世界数据集中,下颌的最先进的预测推理基准都超出了间隔生成和风险评估审计任务的偏差。
translated by 谷歌翻译
从侵入性冠状动脉造影(ICA)中准确提取冠状动脉(ICA)在临床决策中对于冠状动脉疾病的诊断和风险分层(CAD)很重要。在这项研究中,我们开发了一种使用深度学习来自动提取冠状动脉腔的方法。方法。提出了一个深度学习模型U-NET 3+,其中包含了全面的跳过连接和深度监督,以自动从ICAS中自动提取冠状动脉。在这个新型的冠状动脉提取框架中采用了转移学习和混合损失功能。结果。使用了一个包含从210名患者获得的616个ICA的数据集。在技​​术评估中,U-NET 3+的骰子得分为0.8942,灵敏度为0.8735,高于U-NET ++(骰子得分:0.8814:0.8814,灵敏度为0.8331)和U-net(骰子分数) :0.8799,灵敏度为0.8305)。结论。我们的研究表明,U-NET 3+优于其他分割框架,用于自动从ICA中提取冠状动脉。该结果表明了临床使用的巨大希望。
translated by 谷歌翻译
监督的学习任务,例如GigaiPixel全幻灯片图像(WSIS)等癌症存活预测是计算病理学中的关键挑战,需要对肿瘤微环境的复杂特征进行建模。这些学习任务通常通过不明确捕获肿瘤内异质性的深层多企业学习(MIL)模型来解决。我们开发了一种新颖的差异池体系结构,使MIL模型能够将肿瘤内异质性纳入其预测中。说明了基于代表性补丁的两个可解释性工具,以探测这些模型捕获的生物学信号。一项针对癌症基因组图集的4,479吉普像素WSI的实证研究表明,在MIL框架上增加方差汇总可改善五种癌症类型的生存预测性能。
translated by 谷歌翻译