Stacked Autoencoders for Unsupervised Feature Learning and Multiple Organ Detection in a Pilot Study Using 4D Patient Data
Stacked Autoencoders for Unsupervised Feature Learning and Multiple Organ Detection in a Pilot Study Using 4D Patient Data
复制标题
DOI：
10.1109/tpami.2012.277
复制
发表时间：
2013-08-01
影响因子：
23.6
通讯作者：
Leach, Martin O.
中科院分区：
文献类型：
--
作者：
Shin, Hoo-Chang;Orton, Matthew R.;Leach, Martin O.
医学图像分析仍然是人工智能的一个具有挑战性的应用领域。在应用机器学习时，获得监督学习的地面实况标签比许多更常见的机器学习应用更困难。对于具有异常的数据集尤其如此，因为这些数据集中的组织类型和器官形状差异很大。然而，在这样的异常数据集中的器官检测可能具有许多有前途的潜在的现实世界的应用，如自动诊断，自动放射治疗计划，和医学图像检索，其中新的多模态医学图像提供更多的信息，用于诊断的成像组织。在这里，我们测试了深度学习方法在磁共振医学图像中器官识别的应用，学习了视觉和时间层次特征，从未标记的多模态DCE-MRI数据集中对对象类进行分类，因此分类器只需要弱监督训练。采用基于概率块的方法进行多器官检测，并从深度学习模型中学习特征。这显示了深度学习模型应用于医学图像的潜力，尽管难以获得正确标记的训练数据集的库，尽管患者数据集中存在固有的异常。
Medical image analysis remains a challenging application area for artificial intelligence. When applying machine learning, obtaining ground-truth labels for supervised learning is more difficult than in many more common applications of machine learning. This is especially so for datasets with abnormalities, as tissue types and the shapes of the organs in these datasets differ widely. However, organ detection in such an abnormal dataset may have many promising potential real-world applications, such as automatic diagnosis, automated radiotherapy planning, and medical image retrieval, where new multimodal medical images provide more information about the imaged tissues for diagnosis. Here, we test the application of deep learning methods to organ identification in magnetic resonance medical images, with visual and temporal hierarchical features learned to categorize object classes from an unlabeled multimodal DCE-MRI dataset so that only a weakly supervised training is required for a classifier. A probabilistic patch-based method was employed for multiple organ detection, with the features learned from the deep learning model. This shows the potential of the deep learning model for application to medical images, despite the difficulty of obtaining libraries of correctly labeled training datasets and despite the intrinsic abnormalities present in patient datasets.