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
The availability of large public datasets and the increased amount of computing power have shifted the interest of the medical community to high-performance algorithms. However, little attention is paid to the quality of the data and their annotations. High performance on benchmark datasets may be reported without considering possible shortcuts or artifacts in the data, besides, models are not tested on subpopulation groups. With this work, we aim to raise awareness about shortcuts problems. We validate previous findings, and present a case study on chest X-rays using two publicly available datasets. We share annotations for a subset of pneumothorax images with drains. We conclude with general recommendations for medical image classification.
translated by 谷歌翻译
Furigana是日语写作中使用的发音笔记。能够检测到这些可以帮助提高光学特征识别(OCR)性能,或通过正确显示Furigana来制作日本书面媒体的更准确的数字副本。该项目的重点是在日本书籍和漫画中检测Furigana。尽管已经研究了日本文本的检测,但目前尚无提议检测Furigana的方法。我们构建了一个包含日本书面媒体和Furigana注释的新数据集。我们建议对此类数据的评估度量,该度量与对象检测中使用的评估协议类似,除非它允许对象组通过一个注释标记。我们提出了一种基于数学形态和连接组件分析的Furigana检测方法。我们评估数据集的检测,并比较文本提取的不同方法。我们还分别评估了不同类型的图像,例如书籍和漫画,并讨论每种图像的挑战。所提出的方法在数据集上达到76 \%的F1得分。该方法在常规书籍上表现良好,但在漫画和不规则格式的书籍上的表现较少。最后,我们证明所提出的方法可以在漫画109数据集上提高OCR的性能5 \%。源代码可通过\ texttt {\ url {https://github.com/nikolajkb/furiganadetection}}}
translated by 谷歌翻译
自动生物医学图像分析的领域至关重要地取决于算法验证的可靠和有意义的性能指标。但是,当前的度量使用通常是不明智的,并且不能反映基本的域名。在这里,我们提出了一个全面的框架,该框架指导研究人员以问题意识的方式选择绩效指标。具体而言,我们专注于生物医学图像分析问题,这些问题可以解释为图像,对象或像素级别的分类任务。该框架首先编译域兴趣 - 目标结构 - ,数据集和算法与输出问题相关的属性的属性与问题指纹相关,同时还将其映射到适当的问题类别,即图像级分类,语义分段,实例,实例细分或对象检测。然后,它指导用户选择和应用一组适当的验证指标的过程,同时使他们意识到与个人选择相关的潜在陷阱。在本文中,我们描述了指标重新加载推荐框架的当前状态,目的是从图像分析社区获得建设性的反馈。当前版本是在由60多个图像分析专家的国际联盟中开发的,将在社区驱动的优化之后公开作为用户友好的工具包提供。
translated by 谷歌翻译
如今,深度卷积神经网络(CNNS)对医学图像分割的最先进的性能,在各种成像方式和任务上。尽管已经提早成功,分割网络可能仍然产生解剖学上异常的分割,并且在物体边界附近具有孔或不准确的孔。为了实施解剖学合理性,最近的研究研究专注于将现有知识(例如对象形状或边界)掺入,作为损耗功能的约束。之前的集成可以是低级,参考从地面真理分割中提取的重新表达,或者高级代表外部医疗信息,例如器官的形状或大小。在过去的几年里,基于事先的损失在研究领域的兴趣表现出了兴趣,因为它们允许一体化专家知识,同时仍然是架构 - 不可知论者。然而,鉴于对不同医学成像挑战和任务的先前损失的多样性,它变得难以确定最适合数据集的损失工作。在本文中,我们建立了近期基于医学图像分割损失的基准。主要目的是提供直觉,以便给定特定任务或数据集的损失。为此,选择了四个低级和高级的基于先前的损耗。考虑的损失在8个不同的数据集中验证了来自各种医学图像分割挑战,包括迪卡侬,群岛和WMH挑战。结果表明,虽然低级别的先前损耗可以保证骰子损耗基线的性能提高,但无论数据集特性如何,高级别的先前损耗都可以根据数据特征提高解剖合理性。
translated by 谷歌翻译
我们提升了一个具有多个注释的开放数据集,可以补充现有的ISIC和PH2皮肤病变分类数据集。此数据集包含非专家注释来源的Visual ABC(不对称,边框,颜色)功能:本科生,来自亚马逊MTURK的人群工人和经典图像处理算法。在本文中,我们首先分析了病变的注释与诊断标签之间的相关性,以及研究不同的注释来源之间的协议。总的来说,我们发现非专家注释与诊断标签的相关性较弱,不同的注释源之间的低协议。然后,我们将多任务学习(MTL)与额外标签一起研究,并表明非专家注释可以通过MTL改进(集成)最先进的卷积神经网络。我们希望我们的数据集可以用于进一步研究多个注释和/或MTL。 GitHub上提供所有数据和模型:https://github.com/raumannsr/enhance。
translated by 谷歌翻译
尽管自动图像分析的重要性不断增加,但最近的元研究揭示了有关算法验证的主要缺陷。性能指标对于使用的自动算法的有意义,客观和透明的性能评估和验证尤其是关键,但是在使用特定的指标进行给定的图像分析任务时,对实际陷阱的关注相对较少。这些通常与(1)无视固有的度量属性,例如在存在类不平衡或小目标结构的情况下的行为,(2)无视固有的数据集属性,例如测试的非独立性案例和(3)无视指标应反映的实际生物医学领域的兴趣。该动态文档的目的是说明图像分析领域通常应用的性能指标的重要局限性。在这种情况下,它重点介绍了可以用作图像级分类,语义分割,实例分割或对象检测任务的生物医学图像分析问题。当前版本是基于由全球60多家机构的国际图像分析专家进行的关于指标的Delphi流程。
translated by 谷歌翻译
Large language models (LLMs) have been shown to be able to perform new tasks based on a few demonstrations or natural language instructions. While these capabilities have led to widespread adoption, most LLMs are developed by resource-rich organizations and are frequently kept from the public. As a step towards democratizing this powerful technology, we present BLOOM, a 176B-parameter open-access language model designed and built thanks to a collaboration of hundreds of researchers. BLOOM is a decoder-only Transformer language model that was trained on the ROOTS corpus, a dataset comprising hundreds of sources in 46 natural and 13 programming languages (59 in total). We find that BLOOM achieves competitive performance on a wide variety of benchmarks, with stronger results after undergoing multitask prompted finetuning. To facilitate future research and applications using LLMs, we publicly release our models and code under the Responsible AI License.
translated by 谷歌翻译
在没有明确或易于处理的可能性的情况下,贝叶斯人经常诉诸于贝叶斯计算(ABC)进行推理。我们的工作基于生成的对抗网络(GAN)和对抗性变分贝叶斯(GAN),为ABC桥接了ABC。 ABC和GAN都比较了观察到的数据和假数据的各个方面,分别从后代和似然模拟。我们开发了一个贝叶斯gan(B-GAN)采样器,该采样器通过解决对抗性优化问题直接靶向后部。 B-GAN是由有条件gan在ABC参考上学习的确定性映射驱动的。一旦训练了映射,就可以通过以可忽略的额外费用过滤噪声来获得IID后样品。我们建议使用(1)数据驱动的提案和(2)变化贝叶斯提出两项后处理的本地改进。我们通过常见的bayesian结果支持我们的发现,表明对于某些神经网络发生器和歧视器,真实和近似后骨之间的典型总变化距离收敛到零。我们对模拟数据的发现相对于一些最新的无可能后验模拟器显示出竞争激烈的性能。
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