Objective: Convolutional neural networks (CNNs) have demonstrated promise in automated cardiac magnetic resonance image segmentation. However, when using CNNs in a large real-world dataset, it is important to quantify segmentation uncertainty and identify segmentations which could be problematic. In this work, we performed a systematic study of Bayesian and non-Bayesian methods for estimating uncertainty in segmentation neural networks. Methods: We evaluated Bayes by Backprop, Monte Carlo Dropout, Deep Ensembles, and Stochastic Segmentation Networks in terms of segmentation accuracy, probability calibration, uncertainty on out-of-distribution images, and segmentation quality control. Results: We observed that Deep Ensembles outperformed the other methods except for images with heavy noise and blurring distortions. We showed that Bayes by Backprop is more robust to noise distortions while Stochastic Segmentation Networks are more resistant to blurring distortions. For segmentation quality control, we showed that segmentation uncertainty is correlated with segmentation accuracy for all the methods. With the incorporation of uncertainty estimates, we were able to reduce the percentage of poor segmentation to 5% by flagging 31--48% of the most uncertain segmentations for manual review, substantially lower than random review without using neural network uncertainty (reviewing 75--78% of all images). Conclusion: This work provides a comprehensive evaluation of uncertainty estimation methods and showed that Deep Ensembles outperformed other methods in most cases. Significance: Neural network uncertainty measures can help identify potentially inaccurate segmentations and alert users for manual review.
translated by 谷歌翻译
包括MRI,CT和超声在内的医学成像在临床决策中起着至关重要的作用。准确的分割对于测量图像感兴趣的结构至关重要。但是,手动分割是高度依赖性的,这导致了定量测量的高度和内部变异性。在本文中,我们探讨了通过深神经网络参数参数的贝叶斯预测分布可以捕获临床医生的内部变异性的可行性。通过探索和分析最近出现的近似推理方案,我们可以评估近似贝叶斯的深度学习是否具有分割后的后验可以学习分割和临床测量中的内在评估者变异性。实验以两种不同的成像方式进行:MRI和超声。我们从经验上证明,通过深神经网络参数化参数的贝叶斯预测分布可以近似临床医生的内部变异性。我们通过提供临床测量不确定性来定量分析医学图像,展示了一个新的观点。
translated by 谷歌翻译
深度学习技术在检测医学图像中的对象方面取得了成功,但仍然遭受虚假阳性预测,可能会阻碍准确的诊断。神经网络输出的估计不确定性已用于标记不正确的预测。我们研究了来自神经网络不确定性估计的功能和基于形状的特征,这些特征是根据二进制预测计算出的,从二进制预测中,通过开发基于分类的后处理步骤来减少肝病病变检测中的假阳性,以用于不同的不确定性估计方法。我们证明了两个数据集上所有不确定性估计方法的神经网络的病变检测性能(相对于F1分数)的改善,分别包括腹部MR和CT图像。我们表明,根据神经网络不确定性估计计算的功能往往不会有助于降低假阳性。我们的结果表明,诸如阶级不平衡(真实假阳性比率)和从不确定性图提取的基于形状的特征之类的因素在区分假阳性和真实阳性预测方面起着重要作用
translated by 谷歌翻译
现代深层神经网络在医学图像分割任务中取得了显着进展。然而,最近观察到他们倾向于产生过于自信的估计,即使在高度不确定性的情况下,导致校准差和不可靠的模型。在这项工作中,我们介绍了错误的预测(MEEP)的最大熵,分割网络的培训策略,这些网络选择性地惩罚过度自信预测,仅关注错误分类的像素。特别是,我们设计了一个正规化术语,鼓励出于错误的预测,增加了复杂场景中的网络不确定性。我们的方法对于神经结构不可知,不会提高模型复杂性,并且可以与多分割损耗功能耦合。我们在两个具有挑战性的医学图像分割任务中将拟议的策略基准:脑磁共振图像(MRI)中的白质超强度病变,心脏MRI中的心房分段。实验结果表明,具有标准分割损耗的耦合MEEP不仅可以改善模型校准,而且还导致分割质量。
translated by 谷歌翻译
深度学习(DL)模型为各种医学成像基准挑战提供了最先进的性能,包括脑肿瘤细分(BRATS)挑战。然而,局灶性病理多隔室分割(例如,肿瘤和病变子区)的任务特别具有挑战性,并且潜在的错误阻碍DL模型转化为临床工作流程。量化不确定形式的DL模型预测的可靠性,可以实现最不确定的地区的临床审查,从而建立信任并铺平临床翻译。最近,已经引入了许多不确定性估计方法,用于DL医学图像分割任务。开发指标评估和比较不确定性措施的表现将有助于最终用户制定更明智的决策。在本研究中,我们探索并评估在Brats 2019-2020任务期间开发的公制,以对不确定量化量化(Qu-Brats),并旨在评估和排列脑肿瘤多隔室分割的不确定性估计。该公制(1)奖励不确定性估计,对正确断言产生高置信度,以及在不正确的断言处分配低置信水平的估计数,(2)惩罚导致更高百分比的无关正确断言百分比的不确定性措施。我们进一步基准测试由14个独立参与的Qu-Brats 2020的分割不确定性,所有这些都参与了主要的Brats细分任务。总体而言,我们的研究结果证实了不确定性估计提供了分割算法的重要性和互补价值,因此突出了医学图像分析中不确定性量化的需求。我们的评估代码在HTTPS://github.com/ragmeh11/qu-brats公开提供。
translated by 谷歌翻译
机器学习算法支撑现代诊断辅助软件,这在临床实践中证明了有价值的,特别是放射学。然而,不准确的是,主要是由于临床样本的可用性有限,用于培训这些算法,妨碍他们在临床医生中更广泛的适用性,接受和识别。我们对最先进的自动质量控制(QC)方法进行了分析,可以在这些算法中实现,以估计其输出的确定性。我们验证了识别磁共振成像数据中的白质超收缩性(WMH)的大脑图像分割任务上最有前途的方法。 WMH是在上层前期成年中常见的小血管疾病的关联,并且由于其变化的尺寸和分布模式而尤其具有挑战性。我们的研究结果表明,不确定度和骰子预测的聚集在此任务的故障检测中最有效。两种方法在0.82至0.84的情况下独立改善平均骰子。我们的工作揭示了QC方法如何有助于检测失败的分割案例,从而使自动分割更可靠,适合临床实践。
translated by 谷歌翻译
在这项工作中,我们使用变分推论来量化无线电星系分类的深度学习模型预测的不确定性程度。我们表明,当标记无线电星系时,个体测试样本的模型后差水平与人类不确定性相关。我们探讨了各种不同重量前沿的模型性能和不确定性校准,并表明稀疏事先产生更良好的校准不确定性估计。使用单个重量的后部分布,我们表明我们可以通过从最低信噪比(SNR)中除去权重来修剪30%的完全连接的层权重,而无需显着损失性能。我们证明,可以使用基于Fisher信息的排名来实现更大程度的修剪,但我们注意到两种修剪方法都会影响Failaroff-Riley I型和II型无线电星系的不确定性校准。最后,我们表明,与此领域的其他工作相比,我们经历了冷的后效,因此后部必须缩小后加权以实现良好的预测性能。我们检查是否调整成本函数以适应模型拼盘可以弥补此效果,但发现它不会产生显着差异。我们还研究了原则数据增强的效果,并发现这改善了基线,而且还没有弥补观察到的效果。我们将其解释为寒冷的后效,因为我们的培训样本过于有效的策划导致可能性拼盘,并将其提高到未来无线电银行分类的潜在问题。
translated by 谷歌翻译
量化监督学习模型的不确定性在制定更可靠的预测方面发挥着重要作用。认知不确定性,通常是由于对模型的知识不足,可以通过收集更多数据或精炼学习模型来减少。在过去的几年里,学者提出了许多认识的不确定性处理技术,这些技术可以大致分为两类,即贝叶斯和集合。本文对过去五年来提供了对监督学习的认识性不确定性学习技术的全面综述。因此,我们首先,将认知不确定性分解为偏见和方差术语。然后,介绍了认知不确定性学习技术以及其代表模型的分层分类。此外,提出了几种应用,例如计算机视觉(CV)和自然语言处理(NLP),然后讨论研究差距和可能的未来研究方向。
translated by 谷歌翻译
Deep neural networks (NNs) are powerful black box predictors that have recently achieved impressive performance on a wide spectrum of tasks. Quantifying predictive uncertainty in NNs is a challenging and yet unsolved problem. Bayesian NNs, which learn a distribution over weights, are currently the state-of-the-art for estimating predictive uncertainty; however these require significant modifications to the training procedure and are computationally expensive compared to standard (non-Bayesian) NNs. We propose an alternative to Bayesian NNs that is simple to implement, readily parallelizable, requires very little hyperparameter tuning, and yields high quality predictive uncertainty estimates. Through a series of experiments on classification and regression benchmarks, we demonstrate that our method produces well-calibrated uncertainty estimates which are as good or better than approximate Bayesian NNs. To assess robustness to dataset shift, we evaluate the predictive uncertainty on test examples from known and unknown distributions, and show that our method is able to express higher uncertainty on out-of-distribution examples. We demonstrate the scalability of our method by evaluating predictive uncertainty estimates on ImageNet.
translated by 谷歌翻译
深度学习(DL)在数字病理应用中表现出很大的潜力。诊断DL的解决方案的鲁棒性对于安全的临床部署至关重要。在这项工作中,我们通过增加数字病理学中的DL预测的不确定性估计,可以通过提高一般预测性能或通过检测错误预测性来导致临床应用的价值增加。我们将模型 - 集成方法(MC辍学和深度集成)的有效性与模型 - 不可知方法(测试时间增强,TTA)进行比较。此外,比较了四个不确定性度量。我们的实验专注于两个域改变情景:转移到不同的医疗中心和癌症的不足亚型。我们的结果表明,不确定性估计可以增加一些可靠性并降低对分类阈值选择的敏感性。虽然高级指标和深度集合在我们的比较中表现最佳,但更简单的度量和TTA的附加值很小。重要的是,所有评估的不确定度估计方法的益处通过域移位减少。
translated by 谷歌翻译
胎儿超声(US)中胎盘的自动分割由于(i)(i)胎盘外观的高度多样性而具有挑战性我们禁止在妊娠晚期进行整个胎盘评估的观点。在这项工作中,我们通过多任务学习方法解决了这三个挑战,该方法结合了单个卷积神经网络中胎盘位置(例如,前,后部)和语义胎盘分段的分类。通过分类任务,模型可以从更大,更多样化的数据集中学习,同时在有限的训练集条件下提高分割任务的准确性。通过这种方法,我们研究了多个评估者的注释的变异性,并表明我们的自动分割(前胎盘的骰子为0.86,后胎盘的骰子为0.83),与观察者内和观察者间的变异性相比,我们的自动段性能达到了人级的性能。最后,我们的方法可以使用由三个阶段组成的多视图US采集管道提供整个胎盘分割:多探针图像采集,图像融合和图像分段。这会导致对较大结构(例如胎盘中的胎盘)的高质量分割,其图像伪像降低,这超出了单个探针的视野。
translated by 谷歌翻译
人工智能(AI)辅助方法在风险领域(例如疾病诊断)受到了很多关注。与疾病类型的分类不同,将医学图像归类为良性或恶性肿瘤是一项精细的任务。但是,大多数研究仅着重于提高诊断准确性,而忽略了模型可靠性的评估,从而限制了其临床应用。对于临床实践,校准对过度参数化的模型和固有的噪声极为明显地提出了低数据表格的主要挑战。特别是,我们发现建模与数据相关的不确定性更有利于置信度校准。与测试时间增强(TTA)相比,我们通过混合数据增强策略提出了一个修改后的自举损失(BS损耗)功能,可以更好地校准预测性不确定性并捕获数据分布转换而无需额外推断时间。我们的实验表明,与标准数据增强,深度集合和MC辍学相比,混合(BSM)模型的BS损失(BSM)模型可以将预期校准误差(ECE)减半。在BSM模型下,不确定性与相似性之间的相关性高达-0.4428。此外,BSM模型能够感知室外数据的语义距离,这表明在现实世界中的临床实践中潜力很高。
translated by 谷歌翻译
Medical image segmentation (MIS) is essential for supporting disease diagnosis and treatment effect assessment. Despite considerable advances in artificial intelligence (AI) for MIS, clinicians remain skeptical of its utility, maintaining low confidence in such black box systems, with this problem being exacerbated by low generalization for out-of-distribution (OOD) data. To move towards effective clinical utilization, we propose a foundation model named EvidenceCap, which makes the box transparent in a quantifiable way by uncertainty estimation. EvidenceCap not only makes AI visible in regions of uncertainty and OOD data, but also enhances the reliability, robustness, and computational efficiency of MIS. Uncertainty is modeled explicitly through subjective logic theory to gather strong evidence from features. We show the effectiveness of EvidenceCap in three segmentation datasets and apply it to the clinic. Our work sheds light on clinical safe applications and explainable AI, and can contribute towards trustworthiness in the medical domain.
translated by 谷歌翻译
尽管脑肿瘤分割的准确性最近取得了进步,但结果仍然遭受低可靠性和鲁棒性的影响。不确定性估计是解决此问题的有效解决方案,因为它提供了对分割结果的信心。当前的不确定性估计方法基于分位数回归,贝叶斯神经网络,集合和蒙特卡洛辍学者受其高计算成本和不一致的限制。为了克服这些挑战,在最近的工作中开发了证据深度学习(EDL),但主要用于自然图像分类。在本文中,我们提出了一个基于区域的EDL分割框架,该框架可以生成可靠的不确定性图和可靠的分割结果。我们使用证据理论将神经网络的输出解释为从输入特征收集的证据价值。遵循主观逻辑,将证据作为差异分布进行了参数化,预测的概率被视为主观意见。为了评估我们在分割和不确定性估计的模型的性能,我们在Brats 2020数据集上进行了定量和定性实验。结果证明了所提出的方法在量化分割不确定性和稳健分割肿瘤方面的最高性能。此外,我们提出的新框架保持了低计算成本和易于实施的优势,并显示了临床应用的潜力。
translated by 谷歌翻译
准确的不确定性估计是医学成像社区的关键需求。已经提出了多种方法,所有直接扩展分类不确定性估计技术。独立像素的不确定性估计通常基于神经网络的概率解释,不考虑解剖学的先验知识,因此为许多细分任务提供了次优的结果。因此,我们提出了不确定性预测方法的酥脆图像分割。 Crisp以其核心实现了一种对比的方法来学习一个共同的潜在空间,该方法编码有效分割及其相应图像的分布。我们使用此联合潜在空间将预测与数千个潜在矢量进行比较,并提供解剖学上一致的不确定性图。在涉及不同方式和器官的四个医学图像数据库上进行的综合研究强调了我们方法的优势与最先进的方法相比。
translated by 谷歌翻译
Clinical diagnostic and treatment decisions rely upon the integration of patient-specific data with clinical reasoning. Cancer presents a unique context that influence treatment decisions, given its diverse forms of disease evolution. Biomedical imaging allows noninvasive assessment of disease based on visual evaluations leading to better clinical outcome prediction and therapeutic planning. Early methods of brain cancer characterization predominantly relied upon statistical modeling of neuroimaging data. Driven by the breakthroughs in computer vision, deep learning became the de facto standard in the domain of medical imaging. Integrated statistical and deep learning methods have recently emerged as a new direction in the automation of the medical practice unifying multi-disciplinary knowledge in medicine, statistics, and artificial intelligence. In this study, we critically review major statistical and deep learning models and their applications in brain imaging research with a focus on MRI-based brain tumor segmentation. The results do highlight that model-driven classical statistics and data-driven deep learning is a potent combination for developing automated systems in clinical oncology.
translated by 谷歌翻译
简介白质超强度(WMHS)的自动分割是磁共振成像(MRI)神经影像分析的重要步骤。流体减弱的反转恢复(FLAIR加权)是MRI对比度,对于可视化和量化WMHS,这是脑小血管疾病和阿尔茨海默氏病(AD)特别有用的。临床MRI方案迁移到三维(3D)FLAIR加权的采集,以在所有三个体素维度中实现高空间分辨率。当前的研究详细介绍了深度学习工具的部署,以使自动化的WMH分割和表征从获得的3D Flair加权图像作为国家广告成像计划的一部分获得。 DDI研究中的642名参与者(283名男性,平均年龄:(65.18 +/- 9.33)年)中的材料和方法,在五个国家收集地点进行了培训和验证两个内部网络。在642名参与者的内部数据和一个外部数据集中,对三个模型进行了测试,其中包含来自国际合作者的29个情况。这些测试集进行了独立评估。使用了五个已建立的WMH性能指标与地面真理人体分割进行比较。测试的三个网络的结果,3D NNU-NET具有最佳性能,平均骰子相似性系数得分为0.78 +/- 0.10,其性能优于内部开发的2.5D模型和SOTA DEEP DEEP BAYESIAN网络。结论MRI协议中3D Flair加权图像的使用越来越多,我们的结果表明,WMH分割模型可以在3D数据上进行训练,并产生与无需更高的或更好的无需先进的WMH分割性能用于包括T1加权图像系列。
translated by 谷歌翻译
在过去的十年中,卷积神经网络(Convnets)主导了医学图像分析领域。然而,发现脉搏的性能仍然可以受到它们无法模拟图像中体素之间的远程空间关系的限制。最近提出了众多视力变压器来解决哀悼缺点,在许多医学成像应用中展示最先进的表演。变压器可以是用于图像配准的强烈候选者,因为它们的自我注意机制能够更精确地理解移动和固定图像之间的空间对应。在本文中,我们呈现透射帧,一个用于体积医学图像配准的混合变压器-Cromnet模型。我们还介绍了三种变速器的变形,具有两个散晶变体,确保了拓扑保存的变形和产生良好校准的登记不确定性估计的贝叶斯变体。使用来自两个应用的体积医学图像的各种现有的登记方法和变压器架构进行广泛验证所提出的模型:患者间脑MRI注册和幻影到CT注册。定性和定量结果表明,传输和其变体导致基线方法的实质性改进,展示了用于医学图像配准的变压器的有效性。
translated by 谷歌翻译
In medical image analysis, automated segmentation of multi-component anatomical structures, which often have a spectrum of potential anomalies and pathologies, is a challenging task. In this work, we develop a multi-step approach using U-Net-based neural networks to initially detect anomalies (bone marrow lesions, bone cysts) in the distal femur, proximal tibia and patella from 3D magnetic resonance (MR) images of the knee in individuals with varying grades of osteoarthritis. Subsequently, the extracted data are used for downstream tasks involving semantic segmentation of individual bone and cartilage volumes as well as bone anomalies. For anomaly detection, the U-Net-based models were developed to reconstruct the bone profiles of the femur and tibia in images via inpainting so anomalous bone regions could be replaced with close to normal appearances. The reconstruction error was used to detect bone anomalies. A second anomaly-aware network, which was compared to anomaly-na\"ive segmentation networks, was used to provide a final automated segmentation of the femoral, tibial and patellar bones and cartilages from the knee MR images containing a spectrum of bone anomalies. The anomaly-aware segmentation approach provided up to 58% reduction in Hausdorff distances for bone segmentations compared to the results from the anomaly-na\"ive segmentation networks. In addition, the anomaly-aware networks were able to detect bone lesions in the MR images with greater sensitivity and specificity (area under the receiver operating characteristic curve [AUC] up to 0.896) compared to the anomaly-na\"ive segmentation networks (AUC up to 0.874).
translated by 谷歌翻译
Modern machine learning methods including deep learning have achieved great success in predictive accuracy for supervised learning tasks, but may still fall short in giving useful estimates of their predictive uncertainty. Quantifying uncertainty is especially critical in real-world settings, which often involve input distributions that are shifted from the training distribution due to a variety of factors including sample bias and non-stationarity. In such settings, well calibrated uncertainty estimates convey information about when a model's output should (or should not) be trusted. Many probabilistic deep learning methods, including Bayesian-and non-Bayesian methods, have been proposed in the literature for quantifying predictive uncertainty, but to our knowledge there has not previously been a rigorous largescale empirical comparison of these methods under dataset shift. We present a largescale benchmark of existing state-of-the-art methods on classification problems and investigate the effect of dataset shift on accuracy and calibration. We find that traditional post-hoc calibration does indeed fall short, as do several other previous methods. However, some methods that marginalize over models give surprisingly strong results across a broad spectrum of tasks.
translated by 谷歌翻译