Privacy-Preserving Multiclass Lung Disorder Classification via CNN with Cosine Similarity in Big Data Framework
Informatica · 10.11.2025 · 49 (10)
DOI: 10.31449/inf.v49i10.9531 ↗Kurz gefasst
Fachartikel in der Zeitschrift Informatica, online erschienen am 10.11.2025. Verfasst von Jaya Sharma und 2 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref).
Abstract (Originalsprache)
Annotating large-scale medical data manually takes a lot of time and human resources, and it requires specific medical knowledge and experience. Big data and Deep learning are two advancing technologies being widely used in the medical field for improved analysis. Because of the recent advancements in imaging technology, computer vision researchers still have unsolved problems related to automatically identifying medical images. Images, however, could include sensitive information about specific body parts and specifics of diseases. In actuality, sharing medical images that contain extremely sensitive information for each user may expose sensitive information to adversaries. One of the main issues between a user and a databank is privacy, we present in this study a Multi-layered convolutional neural network (MLCNN) integrated with PPCS (Privacy preserved cosine similarity) for feature extraction from large-scale medical image data. The framework that uses fully homomorphic encryption (FHE), CSSK(Cheon-Kim-Kim-Song) scheme to search for safe and to enable the categorization CNN is used for large-scale encrypted images. This study aims to diagnose various lung disorders such as COVID-19, lung cancer, pulmonary tuberculosis, pneumonia, and differentiate them from normal conditions by analyzing computed tomography (CT) images. The model's results included 98.54% F1 score, 97.11% Matthew's correlation coefficient (MCC), 98.89% accuracy (AC), 98.38% recall, and 98.81% precision (PC). We compare and contrast our privacy-preserving method with a CNN-based multiclass classification model that offers quick and effective classification.
Zitieren
APA
Sharma, J., Vinod, D. F., & Chugh, U. (2025). Privacy-Preserving Multiclass Lung Disorder Classification via CNN with Cosine Similarity in Big Data Framework. Informatica, 49(10). https://doi.org/10.31449/inf.v49i10.9531
Vancouver
Sharma J, Vinod DF, Chugh U. Privacy-Preserving Multiclass Lung Disorder Classification via CNN with Cosine Similarity in Big Data Framework. Informatica. 2025;49(10). doi:10.31449/inf.v49i10.9531
BibTeX
@article{Sharma2025,
author = {Sharma, Jaya and Vinod, D Franklin and Chugh, Urvashi},
title = {Privacy-Preserving Multiclass Lung Disorder Classification via CNN with Cosine Similarity in Big Data Framework},
journal = {Informatica},
year = {2025},
volume = {49},
number = {10},
doi = {10.31449/inf.v49i10.9531}
}
EUVIMED