3D Reconstruction for Super-Resolution CT Images in the Internet of Health Things Using Deep Learning

Jing Zhang, Ling Rui Gong, Keping Yu, Xin Qi, Zheng Wen, Qiaozhi Hua, San Hlaing Myint

研究成果: Article

抜粋

The Internet of Health Things (IoHT) enables health devices to connect to the Internet and communicate with each other, which provides the high-accuracy and high-security diagnosis result in the medical area. As essential parts of the IoHT, computed tomography (CT) images help doctors diagnose disease. In the traditional disease diagnosing process, low-resolution medical CT images produce low-accuracy diagnosis results for microlesions. Moreover, CT images can only provide 2D information about organs, and doctors should estimate the 3D shape of a lesion based on experience. To solve these problems, we propose a 3D reconstruction method for secure super-resolution computed tomography (SRCT) images in the IoHT using deep learning. First, we use deep learning to obtain secure SRCT images from low-resolution images in the IoHT. To this end, we adopt a conditional generative adversarial network (CGAN) based on the edge detection loss function (EDLF) in the deep learning process, namely EDLF-CGAN algorithm. In this algorithm, the CGAN is employed to generate SRCT images with luminance and contrast as the input auxiliary conditions, which can improve the accuracy of super-resolution (SR) images. An EDLF is proposed to consider the edge features in the generated SRCT images, which reduces the deformation of generated image. Second, we apply the secure SR images generated from the deep learning method to perform 3D reconstruction. An advanced ray casting 3D reconstruction algorithm that can reduce the number of rays by selecting the appropriate bounding box is proposed. Compared with the traditional algorithm, the proposed ray casting 3D reconstruction algorithm can reduce the time and memory cost. The experimental results show that our EDLF-CGAN has a better SR reconstruction effect than other algorithms via the indicators of the peak signal-to-noise ratio (PSNR) and structural similarity (SSIM). In addition, our advanced ray casting 3D reconstruction algorithm greatly improves the efficiency compared with the traditional ray casting algorithm.

元の言語English
記事番号9133099
ページ(範囲)121513-121525
ページ数13
ジャーナルIEEE Access
8
DOI
出版物ステータスPublished - 2020

ASJC Scopus subject areas

  • Computer Science(all)
  • Materials Science(all)
  • Engineering(all)

フィンガープリント 3D Reconstruction for Super-Resolution CT Images in the Internet of Health Things Using Deep Learning' の研究トピックを掘り下げます。これらはともに一意のフィンガープリントを構成します。

  • これを引用