딥러닝을 이용한 CT 영상의 간과 종양 분할과 홀로그램 시각화 기법 연구 = A Study on the Liver and Tumor Segmentation and Hologram Visualization of CT Images Using Deep Learning

다국어 초록 (Multilingual Abstract)

In this paper, we proposed a system that visualizes a hologram device in 3D by utilizing the CT image segmentation function based on artificial intelligence deep learning. The input axial CT medical image is converted into Sagittal and Coronal, and the input image and the converted image are divided into 3D volumes using ResUNet, a deep learning model. In addition, the volume is created by segmenting the tumor region in the segmented liver image. Each result is integrated into one 3D volume, displayed in a medical image viewer, and converted into a video. When the converted video is transmitted to the hologram device and output from the device, a 3D image with a sense of space can be checked. As for the performance of the deep learning model, in Axial, the basic input image, DSC showed 95.0% performance in liver region segmentation and 67.5% in liver tumor region segmentation. If the system is applied to a real-world care environment, additional physical contact is not required, making it safer for patients to explain changes before and after surgery more easily. In addition, it will provide medical staff with information on liver and liver tumors necessary for treatment or surgery in a three-dimensional manner, and help patients manage them after surgery by comparing and observing the liver before and after liver resection.

참고문헌 (Reference)

1 임상헌 ; 김영재 ; 김광기, "딥 러닝 기반의 영상분할 알고리즘을 이용한 의료영상 3차원 시각화에 관한 연구" 한국멀티미디어학회 23 (23): 468-475, 2020

2 "VTK"

3 O. Ronneberger, "U-Net : Convolutional Networks for Biomedical Image Segmentation" 9351 : 234-241, 2015

4 Z. Zhang, "Road Extraction by Deep Residual U-Net" 15 (15): 749-753, 2018

5 G. Chlebus, "Reducing Inter-Observer Variability and In-Teraction Time of MR Liver Volumetry by Comnining Automatic CNN-Based Liver Segmentation and Manual Correctionsm" 14 (14): e0217228-, 2019

6 "OpenCV"

7 S. H. Lim, "Multi-class Whole Heart Segmentation Using Residual Multi-dilated Convolution U-Net" 508-510, 2019

8 Y. Saito, "Intraoperative 3D Hologram Support With Mixed Reality Techniques in Liver Surgery" 271 : 4-7, 2020

9 "ITK"

10 "HoloLens"

11 "Gatebox"

12 H. Meine, "Comparison of U-netbased Convolutional Neural Networks for Liver Segmentation in CT"

13 Statistics Korea, "Causes of Death Statistics in 2020"

14 X. -F. Xi, "Cascade U-ResNets for Simultaneous Liver and Lesion Segmentation" 8 : 68944-68952, 2020

15 A. Fatima, "Bata-Unet : Deep Learning Model for Liver Segmentation" 11 (11): 75-87, 2020

16 L. Huang, "Automatic Liver Segmentation from CT Images Using Single-Block Linear Detection" 2016 : 9420148-, 2016

17 Z. Oussema, "Automatic Liver Segmentation Method in CT Images" 2 (2): 92-85, 2011

18 F. Lu, "Automatic 3D Liver Location and Segmentation via Convolutional Neural Network and Graph Cut" 12 : 171-182, 2016