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

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

doi:10.1109/access.2020.3007024

Abstract

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.

Highlights

The Internet of Health Things (IoHT) represents a concept that connects physical devices, networking devices, The associate editor coordinating the review of this manuscript and approving it for publication was Muhammad Tariq .intelligent devices and patient software applications [1], [2], which enable these devices to collect and transfer medical data
This paper proposes an advanced ray casting 3D reconstruction algorithm, which can reduce the number of rays by selecting an appropriate bounding box
An advanced ray casting 3D reconstruction algorithm is proposed, which can reduce the number of rays by selecting an appropriate bounding box

Summary

Introduction

Intelligent devices and patient software applications [1], [2], which enable these devices to collect and transfer medical data. A patient can be remotely sensed via existing network facilities, such as tracking patients’ wearable health equipment and diagnosing disease using machine learning and AI, which will send the doctors’ suggestions to patients. J. Zhang et al.: 3D Reconstruction for SRCT Images in the IoHT Using Deep Learning. Zhang et al.: 3D Reconstruction for SRCT Images in the IoHT Using Deep Learning This approach is a new way to remotely diagnose patients at home by IoHT. When patients have medical problems or the states of a disease changes, the IoHT can reduce the time required by patients to travel to the hospital and obtain an immediate response. The IoHT would redefine healthcare systems and advance the medical communication between doctors and patients [3], [4]

Methods

Results

Conclusion