-
Automatic construction of Chinese herbal prescription from tongue image via convolution networks and auxiliary latent therapy topics
The tongue image is an important physical information of human, it is of...
read it
-
Generating Chinese Poetry from Images via Concrete and Abstract Information
In recent years, the automatic generation of classical Chinese poetry ha...
read it
-
Neural Network-based Automatic Factor Construction
Instead of conducting manual factor construction based on traditional an...
read it
-
Tongue image constitution recognition based on Complexity Perception method
Background and Object: In China, body constitution is highly related to ...
read it
-
Convolutional herbal prescription building method from multi-scale facial features
In Traditional Chinese Medicine (TCM), facial features are important bas...
read it
-
Which Ads to Show? Advertisement Image Assessment with Auxiliary Information via Multi-step Modality Fusion
Assessing aesthetic preference is a fundamental task related to human co...
read it
Automatic construction of Chinese herbal prescription from tongue image via CNNs and auxiliary latent therapy topics
The tongue image is an important physical information of human, it is of great importance to the diagnosis and treatment in clinical medicine. Herbal prescriptions are simple, noninvasive and low side effects, and are widely applied in China. Researches on automatic construction technology of herbal prescription based on tongue image have great significance for deep learning to explore the relevance from tongue image to herbal prescription, and can be applied to healthcare services in mobile medical system. In order to adapt to the tongue image in a variety of photographing environments and construct the herbal prescriptions, a neural network framework for prescriptions construction is designed, which includes single / double convolution channels and fully connected layers, and propose the mechanism of auxiliary therapy topic loss to model the therapy of Chinese doctors then alleviate the interference of sparse output labels to the diversity of results. The experimental data include the patient tongue images and their corresponding prescriptions from real world outpatient clinic, and the experiment results can generate the prescriptions that are close to the real samples, which verifies the feasibility of the proposed method for automatic construction of herbal prescription from tongue image. Also, provides a reference for automatic herbal prescription construction from more physical information (or integrated body information).
READ FULL TEXT
Comments
There are no comments yet.