A.I DOCTOR
Convergence Research Consortium: University-Enterprise-Hospital Joint Study to Obtain Medical Clinical Experiments and Data for Machine Learning of Virtual Company Platforms, and Proceed with Commercialization Research. Development of medical diagnosis platform using artificial intelligence technology.
 Cirrhosis of liver |  Confusion chart |
|---|
CIRRHOSIS OF THE LIVER
Many types of liver diseases and conditions injure healthy liver cells, causing cell death and inflammation. Cirrhosis is a late-stage result of liver disease and its complications. Cirrhosis keeps the liver from working properly and late-stage cirrhosis is life-threatening.
We propose a fully automated liver steatosis prediction model using deep learning neural networks. Our model can predict fatty liver disease with the sensitivity of 99.78%, specificity of 100%, PPV of 100%, NPV of 99.83%, and diagnostic accuracy of 99.91%, which is comparable to the common results annotated by medical experts.
DEEP LEARNING APPLICATIONS
GAN(Generative Adversarial Network)
A generative adversarial network, or GAN, is a deep neural network framework which is able to learn from a set of training data and generate new data with the same characteristics as the training data. Generative adversarial networks consist of two neural networks, the generator and the discriminator, which compete against each other.
Semantic segmenation
Semantic image segmentation is the task of classifying each pixel in an image from a predefined set of classes. In the following example, different entities are classified. In order to perform semantic segmentation, a higher level understanding of the image is required. The algorithm should figure out the objects present and also the pixels which correspond to the object. Semantic segmentation is one of the essential tasks for complete scene understanding.
LAB-ON-A-DISK
Amongst numerous microfluidic technologies available, this study proposes the design of a centrifugal microfluidic chip, also known as Lab-on-a-Disc (LOD), which is regarded as one of the most outstanding platforms in microfluidics. Typical centrifugal micro-devices perform a set of microfluidic operations, such as liquid transport, metering, aliquoting, mixing, and valving through rotational-speed control. Accordingly, such devices have the advantage of being able to control the fluid through use of a single motor to generate the force required for fluid propulsion thereby eliminating the need for an external pump and multiple laboratory instruments. Since fluid control is exclusively regulated by the centrifugal force, the overall process becomes simpler and faster. Implementation of the analytical protocol is based on the use of both capillary and vinyl valves. Through use of the proposed design, the authors expect to prevent leakage and exercise control over liquid flow with regard to centrifugal microfluidics.