由于隐私,透明度,问责制和缺少程序保障的担忧,印度的面部加工系统的增加越来越多。与此同时,我们也很少了解这些技术如何在印度13.4亿种群的不同特征,特征和肤色上表现出来。在本文中,我们在印度脸部的数据集中测试四个商用面部加工工具的面部检测和面部分析功能。该工具在面部检测和性别和年龄分类功能中显示不同的错误率。与男性相比,印度女性面的性别分类错误率始终如一,最高的女性错误率为14.68%。在某些情况下,这种错误率远高于其他国籍的女性之前的研究表明。年龄分类错误也很高。尽管从一个人的实际年龄从一个人的实际年龄到10年来考虑到可接受的误差率,但年龄预测失败的速度为14.3%至42.2%。这些发现指向面部加工工具的准确性有限,特别是某些人口组,在采用此类系统之前需要更关键的思维。
translated by 谷歌翻译
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
生成模型生成的合成数据可以增强医学成像中渴望数据深度学习模型的性能和能力。但是,(1)(合成)数据集的可用性有限,并且(2)生成模型训练很复杂,这阻碍了它们在研究和临床应用中的采用。为了减少此入口障碍,我们提出了Medigan,Medigan是一站式商店,用于验证的生成型号,该型号是开源框架 - 不合骨python图书馆。 Medigan允许研究人员和开发人员仅在几行代码中创建,增加和域名。在基于收集的最终用户需求的设计决策的指导下,我们基于生成模型的模块化组件(i)执行,(ii)可视化,(iii)搜索和排名以及(iv)贡献。图书馆的可伸缩性和设计是通过其越来越多的综合且易于使用的验证生成模型来证明的,该模型由21种模型组成,利用9种不同的生成对抗网络体系结构在4个域中在11个数据集中训练,即乳腺摄影,内窥镜检查,X射线和X射线和X射线镜头,X射线和X型。 MRI。此外,在这项工作中分析了Medigan的3个应用,其中包括(a)启用社区范围内的限制数据共享,(b)研究生成模型评估指标以及(c)改进临床下游任务。在(b)中,扩展了公共医学图像综合评估和报告标准,我们根据图像归一化和特定于放射学特征提取了Fr \'Echet Inception距离变异性。
translated by 谷歌翻译
域适应(DA)最近在医学影像社区提出了强烈的兴趣。虽然已经提出了大量DA技术进行了用于图像分割,但大多数这些技术已经在私有数据集或小公共可用数据集上验证。此外,这些数据集主要解决了单级问题。为了解决这些限制,与第24届医学图像计算和计算机辅助干预(Miccai 2021)结合第24届国际会议组织交叉模态域适应(Crossmoda)挑战。 Crossmoda是无监督跨型号DA的第一个大型和多级基准。挑战的目标是分割参与前庭施瓦新瘤(VS)的后续和治疗规划的两个关键脑结构:VS和Cochleas。目前,使用对比度增强的T1(CET1)MRI进行VS患者的诊断和监测。然而,使用诸如高分辨率T2(HRT2)MRI的非对比度序列越来越感兴趣。因此,我们创建了一个无人监督的跨模型分段基准。训练集提供注释CET1(n = 105)和未配对的非注释的HRT2(n = 105)。目的是在测试集中提供的HRT2上自动对HRT2进行单侧VS和双侧耳蜗分割(n = 137)。共有16支球队提交了评估阶段的算法。顶级履行团队达成的表现水平非常高(最佳中位数骰子 - vs:88.4%; Cochleas:85.7%)并接近完全监督(中位数骰子 - vs:92.5%;耳蜗:87.7%)。所有顶级执行方法都使用图像到图像转换方法将源域图像转换为伪目标域图像。然后使用这些生成的图像和为源图像提供的手动注释进行培训分割网络。
translated by 谷歌翻译