More from less: Overcoming Data Scarcity for Deep Learning in Medical Image Computing

少而多：克服医学图像计算中深度学习的数据稀缺性

• 批准号: 455548460
• 负责人: Professorin Dr.-Ing. Dorit Merhof
• 金额: --
• 依托单位: Professur für Bildverarbeitung
• 依托单位国家: 德国
• 项目类别: Research Grants
• 资助国家: 德国
• 项目状态: 未结题
• 来源: https://gepris.dfg.de/gepris/projekt/455548460?language=en
• 关键词: More; less; Overcoming; Data; Scarcity

This project aims at closing the gap between the performance of AI models in classic computer vision and natural language processing and the application of machine learning methods to radiological images by leveraging existing data more effectively. Specifically, we formulate the following goals:1. Simulate tomographic medical images using Generative Adversarial Networks (GANs) more effectively by leveraging all spatial context in 3D. We will then answer the question to what degree the synthesized data is beneficial as additional training data for classification problems. This will reveal how much real data is needed in order to train a GAN on medical images in a stable manner. Furthermore, this will provide evidence for the question to what the degree the performance of a classifier may be improved by artificial images.2. Develop models for inductive transfer learning which may be used to train algorithms for other related problems with much less data. The models and weights will be released as open source software. This will show under which conditions transfer learning is superior to training from scratch.3. Translate the success of self-supervised learning from natural language processing (NLP) into medical image computing (MIC) problems by developing problem-specific pretext tasks and loss functions. This will utilize existing data much more efficiently than in tranditional supervised learning.4. Develop probabilistic segmentation algorithms that model the distribution of possible tumor segmentations in 3D. This will provide even more precise probabilistic segmentations and provides a basis for many downstream tasks such as radiomics.

该项目旨在通过更有效地利用现有数据，缩小人工智能模型在经典计算机视觉和自然语言处理中的性能与机器学习方法在放射图像中的应用之间的差距。具体而言，我们制定了以下目标：1.通过利用3D中的所有空间背景，使用生成对抗网络（GAN）更有效地模拟断层医学图像。然后，我们将回答这个问题，在多大程度上合成的数据是有益的，作为额外的训练数据的分类问题。这将揭示为了以稳定的方式在医学图像上训练GAN需要多少真实的数据。此外，这将为人工图像可以在多大程度上提高分类器性能的问题提供证据.开发归纳迁移学习的模型，这些模型可用于训练其他相关问题的算法，而数据要少得多。模型和重量将作为开源软件发布。这将显示在哪些条件下迁移学习上级从头开始的训练。通过开发特定于问题的借口任务和损失函数，将自然语言处理（NLP）的自监督学习的成功转化为医学图像计算（MIC）问题。这将比瞬态监督学习更有效地利用现有数据。开发概率分割算法，对3D中可能的肿瘤分割分布进行建模。这将提供更精确的概率分割，并为许多下游任务（如放射组学）提供基础。