Projectrons - Artificial Neural Networks for Learning Medical Images

学习检索相似的图像有许多应用。在医学成像中，定位相似的图像可以帮助诊断和治疗计划。任何检索系统的第一步都是描述存档图像。为此，使用图像描述符，或者是手工制作的，比如LBP（局部二进制模式），或者是基于学习的，比如深度特征。深度特征是训练深度神经网络（如CNN和自动编码器）的结果。尽管文献中报道了很高的准确性，但深度架构面临着几个挑战，特别是对于医学图像分析：1)它们需要一个大的、平衡的和标记的数据集来正确学习，这在医学领域是无法保证的。医学影像档案非常庞大，但医学影像的性质和复杂的人体解剖结构造成了不平衡类别（例如，乳腺癌的图像很多，甲状腺癌的图像相对较少），无法通过增强手术（即，通过旋转人为地增加图像数量）来平衡。此外，在医学成像的许多子领域中，临床工作流程不包括标记（标记）感兴趣的区域，这是对无法轻易绕过的监督深度网络训练的要求，2)深度架构容易受到对抗性攻击，并且可能容易表现出过拟合行为（记忆数据而不是实际学习数据），3)深度特征不可解释。不可能理解为什么要采取某种行动。在医疗领域，必须详细解释和描述决定（即在病理报告中）。我将探索一种称为“投影”的新型神经网络的设计、训练和验证，这种神经网络对于表示医学图像特别有用。这种表示可以用于大型医学图像档案中的图像搜索和识别。Projectron是一个具有相对少量神经元的连接图，可以学习图像表示（以无监督的方式）并创建紧凑（二进制）输出，特别是用于标记图像以促进高效存储和快速搜索大型档案。投影仪可能不需要标记数据，如果需要，也不应该需要数百万。同时，投影仪将不受过拟合的影响，也不会被愚弄而伪造陈述。对于医生来说，图像和投影到图表中的方式之间的关系应该是可验证的。由于反向传播算法不能在连通图上工作，因此将探索新的学习方法，其中包括进化元启发式，以及由基于对立（反命题）配对指导的子图随机抽样的混合方法。所有设计的图形将在组织病理学和放射学图像上进行测试。在这个项目中，我将培养2名博士生，1名硕士，10名本科生，1名博士后。

Learning to retrieve similar images has many applications. In medical imaging, locating similar images can assist the diagnosis and treatment planning. The first step in any retrieval system is describing archived images. For that, image descriptors are used, either handcrafted ones like LBP (Local Binary Patterns) or learning--based ones like deep features. Deep features are the result of training deep neural networks such as CNN and autoencoders. In spite of high accuracies reported in the literature, deep architectures face several challenges, particularly for medical image analysis: 1) they require a large, balanced, and labeled dataset to learn properly, which cannot be guaranteed in the medical field. Medical imaging archives are very large, but the nature of medical imaging and the complex human anatomy creates imbalance classes (e.g., many images for breast cancer, and comparably few images for thyroid cancer) that cannot be balanced via augmentation operations (i.e., artificially increase the number of images through rotations). Additionally, in many sub-fields of medical imaging, the clinical workflow does not include labeling (marking) regions of interest, a requirement for training of supervised deep nets that cannot be easily circumvented, 2) deep architectures are prone to adversarial attacks and may easily exhibit overfitting behaviour (memorize the data instead of actually learning it), 3) deep features are not interpretable. It is not possible to understand why a certain action was taken. In the medical filed, decisions have to be explained and described in details (i.e., in pathology reports). I will explore the design, training, and validation of a new type of neural networks called "Projectron" that are particularly useful for representing medical images. Such representations can be used for image search and identification in large archives of medical images. A Projectron is a connected graph with a relatively small number of neurons that can learn an image representation (in an unsupervised manner) and create a compact (binary) output especially learned for tagging images to facilitate efficient storage and fast search in large archives. A Projectron may not need labeled data and if does, it should not need millions. As well, the Projectron will be immune to overfitting and cannot be fooled into falsifying representations. The relationship between the image and the way it is projected into the graph should be verifiable for the physicians. As backpropgation algorithms would not work on connected graphs, new ways for learning will be explored, among others evolutionary metaheuristics, and a mixture of the random sampling of sub-graphs guided by opposition-based (anti-thetic) pairing. All designed graphs will be tested on histopathology and radiology images. In this project, I will train 2 PhD students, 1 MSc student, 10 undergraduate students, and a postdoctoral fellow.