EUVIMEDEUVIMED entdecken
Open Access

A Faster Privacy-Preserving Medical Image Diagnosis Scheme with Machine Learning

Jiuhong Ran, Dong Li

Journal of Imaging Informatics in Medicine · 2025

DOI: 10.1007/s10278-024-01384-4 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Imaging Informatics in Medicine, 2025. Verfasst von Jiuhong Ran und 1 weiteren Autor:innen. Beteiligte Einrichtung: Hospital of Chongqing University, Chongqing University, No. 174, Shazheng Street, Shapingba, 400044, Chongqing, China. Hauptthemen laut MEDLINE: Machine Learning, Neural Networks, Computer, Confidentiality, Computer Security. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 45 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: National Natural Science Foundation of China, China Scholarship Council.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Convolutional neural networks (CNNs) have become indispensable to medical image diagnosis research, enabling the automated differentiation of diseased images from extensive medical image datasets. Due to their efficacy, these methods raise significant privacy concerns regarding patient images and diagnostic models. To address these issues, some researchers have explored privacy-preserving medical image diagnosis schemes using fully homomorphic encryption (FHE). However, these schemes often support and are suitable for only a limited number of non-linear layers, resulting in less effective diagnoses and potentially inaccurate results. To improve upon these limitations, we propose and design a robust privacy-preserving medical diagnosis scheme that maintains both diagnostic accuracy and effectiveness at the same time. First, we utilize FHE to encrypt both the image and the model to safeguard the confidentiality of medical data and the model itself. Then, we introduce batch normalization to facilitate the use of multiple non-linear layers in deep convolutional neural networks within a ciphertext context. Furthermore, we employ a 2-degree polynomial function to approximate the ReLU activation function effectively. Finally, we introduce two innovative network depth optimization techniques to solve the issue of CNN depth insufficiency. Both theoretical and empirical analyses confirm that our scheme not only protects the confidentiality of medical images and diagnostic models but also ensures practicality and efficiency.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningNeural Networks, ComputerConfidentialityComputer SecurityPrivacyHumansAlgorithms

Stichwörter der Autor:innen

Batch normalizationCNNFHEImage diagnosis

Autor:innen und Institutionen

  • Hospital of Chongqing University, Chongqing University, No. 174, Shazheng Street, Shapingba, 400044, Chongqing, China.
  • College of Computer, Chongqing University, No. 55 Daxuecheng South Rd, Shapingba, 401331, Chongqing, China. lilvmy@163.com.

Förderung

  • National Natural Science Foundation of China
  • China Scholarship Council

Zitieren

APA

Ran, J., & Li, D. (2025). A Faster Privacy-Preserving Medical Image Diagnosis Scheme with Machine Learning. Journal of Imaging Informatics in Medicine. https://doi.org/10.1007/s10278-024-01384-4

Vancouver

Ran J, Li D. A Faster Privacy-Preserving Medical Image Diagnosis Scheme with Machine Learning. Journal of Imaging Informatics in Medicine. 2025. doi:10.1007/s10278-024-01384-4

BibTeX
@article{Ran2025,
  author = {Ran, Jiuhong and Li, Dong},
  title = {A Faster Privacy-Preserving Medical Image Diagnosis Scheme with Machine Learning},
  journal = {Journal of Imaging Informatics in Medicine},
  year = {2025},
  doi = {10.1007/s10278-024-01384-4}
}
Kostenlos starten →