Deep neural networks (DNNs) have rapidly become a \textit{de facto} choice for medical image understanding tasks. However, DNNs are notoriously fragile to the class imbalance in image classification. We further point out that such imbalance fragility can be amplified when it comes to more sophisticated tasks such as pathology localization, as imbalances in such problems can have highly complex and often implicit forms of presence. For example, different pathology can have different sizes or colors (w.r.t.the background), different underlying demographic distributions, and in general different difficulty levels to recognize, even in a meticulously curated balanced distribution of training data. In this paper, we propose to use pruning to automatically and adaptively identify \textit{hard-to-learn} (HTL) training samples, and improve pathology localization by attending them explicitly, during training in \textit{supervised, semi-supervised, and weakly-supervised} settings. Our main inspiration is drawn from the recent finding that deep classification models have difficult-to-memorize samples and those may be effectively exposed through network pruning \cite{hooker2019compressed} - and we extend such observation beyond classification for the first time. We also present an interesting demographic analysis which illustrates HTLs ability to capture complex demographic imbalances. Our extensive experiments on the Skin Lesion Localization task in multiple training settings by paying additional attention to HTLs show significant improvement of localization performance by $\sim$2-3\%.
translated by 谷歌翻译
Scene text recognition (STR) enables computers to recognize and read the text in various real-world scenes. Recent STR models benefit from taking linguistic information in addition to visual cues into consideration. We propose a novel Masked Vision-Language Transformers (MVLT) to capture both the explicit and the implicit linguistic information. Our encoder is a Vision Transformer, and our decoder is a multi-modal Transformer. MVLT is trained in two stages: in the first stage, we design a STR-tailored pretraining method based on a masking strategy; in the second stage, we fine-tune our model and adopt an iterative correction method to improve the performance. MVLT attains superior results compared to state-of-the-art STR models on several benchmarks. Our code and model are available at https://github.com/onealwj/MVLT.
translated by 谷歌翻译
AI-powered Medical Imaging has recently achieved enormous attention due to its ability to provide fast-paced healthcare diagnoses. However, it usually suffers from a lack of high-quality datasets due to high annotation cost, inter-observer variability, human annotator error, and errors in computer-generated labels. Deep learning models trained on noisy labelled datasets are sensitive to the noise type and lead to less generalization on the unseen samples. To address this challenge, we propose a Robust Stochastic Knowledge Distillation (RoS-KD) framework which mimics the notion of learning a topic from multiple sources to ensure deterrence in learning noisy information. More specifically, RoS-KD learns a smooth, well-informed, and robust student manifold by distilling knowledge from multiple teachers trained on overlapping subsets of training data. Our extensive experiments on popular medical imaging classification tasks (cardiopulmonary disease and lesion classification) using real-world datasets, show the performance benefit of RoS-KD, its ability to distill knowledge from many popular large networks (ResNet-50, DenseNet-121, MobileNet-V2) in a comparatively small network, and its robustness to adversarial attacks (PGD, FSGM). More specifically, RoS-KD achieves >2% and >4% improvement on F1-score for lesion classification and cardiopulmonary disease classification tasks, respectively, when the underlying student is ResNet-18 against recent competitive knowledge distillation baseline. Additionally, on cardiopulmonary disease classification task, RoS-KD outperforms most of the SOTA baselines by ~1% gain in AUC score.
translated by 谷歌翻译
无监督的域适应性(UDA)旨在使在标记的源域上训练的模型适应未标记的目标域。在本文中,我们提出了典型的对比度适应(PROCA),这是一种无监督域自适应语义分割的简单有效的对比度学习方法。以前的域适应方法仅考虑跨各个域的阶级内表示分布的对齐,而阶层间结构关系的探索不足,从而导致目标域上的对齐表示可能不像在源上歧视的那样容易歧视。域了。取而代之的是,ProCA将类间信息纳入班级原型,并采用以班级为中心的分布对齐进行适应。通过将同一类原型与阳性和其他类原型视为实现以集体为中心的分配对齐方式的负面原型,Proca在经典领域适应任务上实现了最先进的性能,{\ em i.e. text {and} synthia $ \ to $ cityScapes}。代码可在\ href {https://github.com/jiangzhengkai/proca} {proca}获得代码
translated by 谷歌翻译
在深度学习方法进行自动医学图像分析的最新成功之前,从业者使用手工制作的放射线特征来定量描述当地的医学图像斑块。但是,提取区分性放射素特征取决于准确的病理定位,这在现实世界中很难获得。尽管疾病分类和胸部X射线的定位方面取得了进步,但许多方法未能纳入临床知名的领域知识。由于这些原因,我们提出了一个放射素引导的变压器(RGT),该变压器(RGT)与\ textit {global}图像信息与\ textit {local}知识引导的放射线信息信息提供准确的心肺病理学定位和分类\ textit {无需任何界限盒{ }。 RGT由图像变压器分支,放射线变压器分支以及聚集图像和放射线信息的融合层组成。 RGT使用对图像分支的自我注意事项,提取了一个边界框来计算放射线特征,该特征由放射线分支进一步处理。然后通过交叉注意层融合学习的图像和放射线特征。因此,RGT利用了一种新型的端到端反馈回路,该回路只能使用图像水平疾病标签引导精确的病理定位。 NIH CHESTXRAR数据集的实验表明,RGT的表现优于弱监督疾病定位的先前作品(在各个相交联合阈值的平均余量为3.6 \%)和分类(在接收器操作方下平均1.1 \%\%\%\%曲线)。接受代码和训练有素的模型将在接受后发布。
translated by 谷歌翻译
视频实例细分(VIS)是一项在视频中同时需要分类,细分和实例关联的任务。最近的VIS方法依靠复杂的管道来实现此目标,包括与ROI相关的操作或3D卷积。相比之下,我们通过添加额外的跟踪头提出了基于实例分割方法Condinst的简单有效的单阶段VIS框架。为了提高实例关联精度,提出了一种新型的双向时空对比度学习策略,用于跟踪跨帧的嵌入。此外,利用实例的时间一致性方案来产生时间连贯的结果。在YouTube-VIS-2019,YouTube-Vis-2021和OVIS-2021数据集上进行的实验验证了所提出方法的有效性和效率。我们希望所提出的框架可以作为许多其他实例级视频关联任务的简单而强大的替代方案。
translated by 谷歌翻译
放射学报告生成旨在产生计算机辅助诊断,以缓解放射科医生的工作量,并最近引起了越来越长的关注。然而,之前的深度学习方法倾向于忽视医学发现之间的相互影响,这可以是限制所生成的报告质量的瓶颈。在这项工作中,我们建议在信息知识图表中提出和代表医学发现的协会,并将此事先知识纳入放射学报告,以帮助提高所生成的报告质量。实验结果证明了我们在IU X射线数据集上的提出方法的优越性,Rouge-L为0.384 $ \ PM $ 0.007和0.340 $ \ PM $ 0.011。与以前的作品相比,我们的模型平均实现了1.6%(苹果酒和Rouge-L的增加2.0%和1.5%)。实验表明,先验知识可以为准确的放射学报告生成表现收益。我们将在https://github.com/bionlplab/report_generation_amia2022中公开公开可用的代码。
translated by 谷歌翻译
背景:患者的分类是控制2019年冠状病毒疾病的大流行病(Covid-19),特别是在临床资源极为有限时在大流行的峰值期间。目的:开发一种用合成胸CT自动筛分和量化肺和肺炎病变的方法,并评估Covid-19患者的疾病严重程度。材料和方法:在本研究中,我们通过可用的数据集(来自“肺结核分析2016年”的285个数据集“来生成数据增强以产生合成胸CT图像。合成图像和掩模用于训练2D U-Net神经网络并在203个Covid-19数据集上测试,以产生肺和病变分段。疾病严重程度评分(DL:损伤负荷; DS:损伤得分)是基于分段计算的。使用Pearson方法评估DL / DS和临床实验室测试之间的相关性。 p值<0.05被认为是统计显着性。结果:将自动肺和病变分段与手动注释进行比较。对于肺部分割,骰子相似系数,Jaccard指数和平均表面距离的中值分别为98.56%,97.15%和0.49 mm。病变分割的相同度量分别为76.95%,62.54%和2.36毫米。在DL / DS和百分比淋巴细胞检测中发现显着(P << 0.05)相关性,R值分别为-0.561和-0.501。结论:基于胸部射线照相和数据增强的AI系统对Covid-19患者的肺癌和病变进行了分段。成像结果与临床实验室测试之间的相关性表明该系统的价值作为评估Covid-19疾病严重程度的潜在工具。
translated by 谷歌翻译
基于深度学习的组织病理学图像分类是帮助医生提高癌症诊断的准确性和迅速性的关键技术。然而,在复杂的手动注释过程中,嘈杂的标签通常是不可避免的,因此误导了分类模型的培训。在这项工作中,我们介绍了一种用于组织病理学图像分类的新型硬样本感知噪声稳健学习方法。为了区分来自有害嘈杂的内容漏洞,我们通过使用样本培训历史来构建一个简单/硬/噪声(EHN)检测模型。然后,我们将EHN集成到自动训练架构中,通过逐渐校正降低噪声速率。通过获得的几乎干净的数据集,我们进一步提出了一种噪声抑制和硬增强(NSHE)方案来训练噪声鲁棒模型。与以前的作品相比,我们的方法可以节省更多清洁样本,并且可以直接应用于实际嘈杂的数据集场景,而无需使用清洁子集。实验结果表明,该方案在合成和现实世界嘈杂的数据集中优于当前最先进的方法。源代码和数据可在https://github.com/bupt-ai-cz/hsa-nrl/处获得。
translated by 谷歌翻译
小型无人驾驶飞机的障碍避免对于未来城市空袭(UAM)和无人机系统(UAS)交通管理(UTM)的安全性至关重要。有许多技术用于实时强大的无人机指导,但其中许多在离散的空域和控制中解决,这将需要额外的路径平滑步骤来为UA提供灵活的命令。为提供无人驾驶飞机的操作安全有效的计算指导,我们探讨了基于近端政策优化(PPO)的深增强学习算法的使用,以指导自主UA到其目的地,同时通过连续控制避免障碍物。所提出的场景状态表示和奖励功能可以将连续状态空间映射到连续控制,以便进行标题角度和速度。为了验证所提出的学习框架的性能,我们用静态和移动障碍进行了数值实验。详细研究了与环境和安全操作界限的不确定性。结果表明,该拟议的模型可以提供准确且强大的指导,并解决了99%以上的成功率的冲突。
translated by 谷歌翻译