Your browser doesn't support javascript.
loading
DP-SSLoRA: A privacy-preserving medical classification model combining differential privacy with self-supervised low-rank adaptation.
Yan, Chaokun; Yan, Haicao; Liang, Wenjuan; Yin, Menghan; Luo, Huimin; Luo, Junwei.
Affiliation
  • Yan C; School of Computer and Information Engineering, Henan University, Kaifeng, 475004, Henan, China; Academy for Advanced Interdisciplinary Studies, Henan University, Kaifeng, 475004, Henan, China; Henan Engineering Research Center of Intelligent Technology and Application, Henan University, Kaifeng, 47
  • Yan H; School of Computer and Information Engineering, Henan University, Kaifeng, 475004, Henan, China.
  • Liang W; School of Computer and Information Engineering, Henan University, Kaifeng, 475004, Henan, China; Academy for Advanced Interdisciplinary Studies, Henan University, Kaifeng, 475004, Henan, China; Henan Engineering Research Center of Intelligent Technology and Application, Henan University, Kaifeng, 47
  • Yin M; School of Computer and Information Engineering, Henan University, Kaifeng, 475004, Henan, China.
  • Luo H; School of Computer and Information Engineering, Henan University, Kaifeng, 475004, Henan, China; Academy for Advanced Interdisciplinary Studies, Henan University, Kaifeng, 475004, Henan, China; Henan Engineering Research Center of Intelligent Technology and Application, Henan University, Kaifeng, 47
  • Luo J; School of Software, Henan Polytecgnic University, Jiaozuo, 454000, Henan, China.
Comput Biol Med ; 179: 108792, 2024 Sep.
Article in En | MEDLINE | ID: mdl-38964242
ABSTRACT
BACKGROUND AND

OBJECTIVE:

Concerns about patient privacy issues have limited the application of medical deep learning models in certain real-world scenarios. Differential privacy (DP) can alleviate this problem by injecting random noise into the model. However, naively applying DP to medical models will not achieve a satisfactory balance between privacy and utility due to the high dimensionality of medical models and the limited labeled samples.

METHODS:

This work proposed the DP-SSLoRA model, a privacy-preserving classification model for medical images combining differential privacy with self-supervised low-rank adaptation. In this work, a self-supervised pre-training method is used to obtain enhanced representations from unlabeled publicly available medical data. Then, a low-rank decomposition method is employed to mitigate the impact of differentially private noise and combined with pre-trained features to conduct the classification task on private datasets.

RESULTS:

In the classification experiments using three real chest-X ray datasets, DP-SSLoRA achieves good performance with strong privacy guarantees. Under the premise of ɛ=2, with the AUC of 0.942 in RSNA, the AUC of 0.9658 in Covid-QU-mini, and the AUC of 0.9886 in Chest X-ray 15k.

CONCLUSION:

Extensive experiments on real chest X-ray datasets show that DP-SSLoRA can achieve satisfactory performance with stronger privacy guarantees. This study provides guidance for studying privacy-preserving in the medical field. Source code is publicly available online. https//github.com/oneheartforone/DP-SSLoRA.
Subject(s)
Key words

Full text: 1 Collection: 01-internacional Database: MEDLINE Main subject: Privacy Limits: Humans Language: En Journal: Comput Biol Med Year: 2024 Document type: Article Country of publication: Estados Unidos

Full text: 1 Collection: 01-internacional Database: MEDLINE Main subject: Privacy Limits: Humans Language: En Journal: Comput Biol Med Year: 2024 Document type: Article Country of publication: Estados Unidos