Title: Mobile lung cancer early warning based on Windows Azure cloud computing

Authors: Jun Lv; Pan Wang; Zijuan Zhao

Addresses: College of Information and Computer, Taiyuan University of Technology, Taiyuan, Shanxi, China ' Department of Computer Science and Technology, Lvliang University, Shanxi, China ' Department of Computer Science and Technology, Lvliang University, Shanxi, China

Abstract: In view of the repeated investment in the current medical lung cancer early warning system, 'information island' and the low rate of lung cancer early warning, this paper proposes a mobile lung cancer early warning system based on Windows Azure cloud computing with the application requirements of medical information system. The system is applied to the smart phones of Windows system, and the Windows Azure Microsoft cloud platform is accessed through wireless network, using SQL Azure to store medical data (such as lung CT image, ECG curve and high-resolution colour ultrasound image), embed the medical lung cancer early warning model based on deep learning in the cloud computing platform to process and analyse the patient's medical data, and realise the real-time synchronous update of doctors, patients and cloud platform data. The accuracy of lung cancer early-warning system on LIDC-IDRI is high, and the detection results are uploaded to doctors and patients' smart phones in real time. The results show that the mobile lung cancer early warning system based on Windows Azure cloud computing not only effectively integrates medical resources, but also provides patients with medical services and consultation at home, which integrates the advantages of all aspects and adapts to the development of the times.

Keywords: pulmonary nodule detection; cloud computing; mobile medicine; CT image of lung.

DOI: 10.1504/IJWMC.2021.113219

International Journal of Wireless and Mobile Computing, 2021 Vol.20 No.1, pp.9 - 19

Received: 29 Apr 2020
Accepted: 14 Sep 2020

Published online: 15 Feb 2021 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article