首页>
外国专利>
DISEASE DIAGNOSIS SYSTEM AND METHOD USING MULTIPLE COLOR MODELS AND NEURAL NETWORK
DISEASE DIAGNOSIS SYSTEM AND METHOD USING MULTIPLE COLOR MODELS AND NEURAL NETWORK
展开▼
机译:多色模型和神经网络疾病诊断系统和方法
展开▼
页面导航
摘要
著录项
相似文献
摘要
Disclosed are: a system performing learning through a neural network so as to use a learned neural network such that an image of biological tissue is inputted in a form of various color models different from each other, and thus a predetermined disease (for example, prostate cancer) can be diagnosed; and a method therefor. According to one aspect of the present invention, provided is a disease diagnosis system which is implemented in a system comprising a processor and a storage device storing a neural network, and which uses the neural network and a slide, which is a biological image, the system comprising: a pre-processing module for generating first image information to Kth image information (wherein, K is an integer of 2 or greater) corresponding to each of patches obtained by dividing the slide into a predetermined size - wherein, ith image information (i is an arbitrary integer satisfying 1<=i<=K) includes at least one channel value corresponding to an ith color model, and a first color model to a Kth color model are different from each other -; and a patch neural network, which receives, in an input layer, the first image information to the Kth image information corresponding to each of the divided patches, so as to output a patch-level diagnosis result indicating whether a disease exists in each patch.
展开▼