Nota, Inc.

University-Industry Foundation (Uif)

Shin Kook Choi

Jong Duk Baek

Gi Hun Kim

Jun Kyeong Choi

Min Ah Han

Provided are a method and apparatus for performing a convolution operation for optimizing the arithmetic intensity of device. The method includes obtaining input data, and generating output data through a convolution model for a device, by using the input data, wherein the convolution model includes a plurality of convolutional layers, the plurality of convolutional layers include an improved first convolutional layer that satisfies preset conditions related to latency characteristics of the device, the improved first convolutional layer is a layer obtained by adjusting a first convolutional layer so as to perform a first convolution operation on a first feature map, which is obtained by reshaping an input feature map of the first convolutional layer based on a predetermined final division value, and the final division value is determined considering the latency characteristics such that an overall arithmetic intensity of the improved first convolutional layer is increased compared to the first convolutional layer.

Method and apparatus for performing convolution operation for optimizing arithmetic intensity of device

Provided are a positron emission tomography (PET)-radiofrequency ablation (RFA) complex medical device and a treatment method using the same. According to an aspect of the present invention, there is provided a positron emission tomography (PET)-radiofrequency ablation (RFA) complex medical device comprising: a PET module which obtains, in real time, a location of a target to be treated by scanning a patient; and an RFA module which remotely treats the target using heat by focusing the heat on the location of the target.

Growing community of inventors

Seoul, South Korea

Shin Kook Choi