Ctrl-GenAug: 可控生成增强用于医学序列分类
Ctrl-GenAug: Controllable Generative Augmentation for Medical Sequence Classification
AI总结：
Ctrl-GenAug通过可控生成增强方法提升医学序列分类性能，解决语义和序列可控性不足及噪声样本问题。
摘要：
在医疗领域，大规模数据集的有限可用性和人工密集的标注过程阻碍了深度模型的性能。基于扩散的生成增强方法提供了一种有希望的解决方案，已被证明在推进下游医疗识别任务中是有效的。然而，现有工作缺乏足够的语义和序列可操控性，以处理具有挑战性的视频/3D序列生成，并且忽视了对噪声合成样本的质量控制，导致不可靠的合成数据库，严重限制了下游任务的性能。在本工作中，我们提出了Ctrl-GenAug，一种新颖且通用的生成增强框架，能够实现高度语义和序列定制的序列合成，并抑制错误合成的样本，以辅助医学序列分类。具体而言，我们首先设计了一个多模态条件引导的序列生成器，以可控地合成诊断促进的样本。一个序列增强模块被集成进来，以增强生成样本的时间/立体一致性。然后，我们提出了一种噪声合成数据过滤器，以在语义和序列层面抑制不可靠的案例。在三个医疗数据集上进行了广泛的实验，使用11种网络在三种范式上训练，全面分析了Ctrl-GenAug的有效性和通用性，特别是在代表性不足的高风险人群和域外条件中。
英文摘要：
In the medical field, the limited availability of large-scale datasets and labor-intensive annotation processes hinder the performance of deep models. Diffusion-based generative augmentation approaches present a promising solution to this issue, having been proven effective in advancing downstream medical recognition tasks. Nevertheless, existing works lack sufficient semantic and sequential steerability for challenging video/3D sequence generation, and neglect quality control of noisy synthesized samples, resulting in unreliable synthetic databases and severely limiting the performance of downstream tasks. In this work, we present Ctrl-GenAug, a novel and general generative augmentation framework that enables highly semantic- and sequential-customized sequence synthesis and suppresses incorrectly synthesized samples, to aid medical sequence classification. Specifically, we first design a multimodal conditions-guided sequence generator for controllably synthesizing diagnosis-promotive samples. A sequential augmentation module is integrated to enhance the temporal/stereoscopic coherence of generated samples. Then, we propose a noisy synthetic data filter to suppress unreliable cases at semantic and sequential levels. Extensive experiments on 3 medical datasets, using 11 networks trained on 3 paradigms, comprehensively analyze the effectiveness and generality of Ctrl-GenAug, particularly in underrepresented high-risk populations and out-domain conditions.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
