A Study on the Applications of the Biomedical Image Encryption Methods for Secured Computer Aided Diagnostics

Roy, Mousomi; Mali, Kalyani; Chatterjee, Sankhadeep; Chakraborty, Shouvik; Debnath, Reshmi; Sen, Soumya

doi:10.1109/aicai.2019.8701382

Cited by 34 publications

(8 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, among the fields mentioned above, the medical industry is one of the most vibrant research areas based on the application of CNNs, which has been developed, employed in computational biomedical domains, and significantly contributed [33]. Doctors can effectively analyze medical images for lesion detection and diagnosis decision-making using the CADe/CADx system.…”

Section: Related Workmentioning

confidence: 99%

Symmetry GAN Detection Network: An Automatic One-Stage High-Accuracy Detection Network for Various Types of Lesions on CT Images

Zhang

et al. 2022

Symmetry

View full text Add to dashboard Cite

Computed tomography (CT) is the first modern slice-imaging modality. Recent years have witnessed its widespread application and improvement in detecting and diagnosing related lesions. Nonetheless, there are several difficulties in detecting lesions in CT images: (1) image quality degrades as the radiation dose is reduced to decrease radiational injury to the human body; (2) image quality is frequently hampered by noise interference; (3) because of the complicated circumstances of diseased tissue, lesion pictures typically show complex shapes; (4) the difference between the orientated object and the background is not discernible. This paper proposes a symmetry GAN detection network based on a one-stage detection network to tackle the challenges mentioned above. This paper employs the DeepLesion dataset, containing 10,594 CT scans (studies) of 4427 unique patients. The symmetry GANs proposed in this research consist of two distinct GAN models that serve different functions. A generative model is introduced ahead of the backbone to increase the input CT image series to address the typical problem of small sample size in medical datasets. Afterward, GAN models are added to the attention extraction module to generate attention masks. Furthermore, experimental data indicate that this strategy has significantly improved the model’s robustness. Eventually, the proposed method reaches 0.9720, 0.9858, and 0.9833 on P, R, and mAP, on the validation set. The experimental outcome shows that the suggested model outperforms other comparison models. In addition to this innovation, we are inspired by the innovation of the ResNet model in terms of network depth. Thus, we propose parallel multi-activation functions, an optimization method in the network width. It is theoretically proven that by adding coefficients to each base activation function and performing a softmax function on all coefficients, parallel multi-activation functions can express a single activation function, which is a unique ability compared to others. Ultimately, our model outperforms all comparison models in terms of P, R, and mAP, achieving 0.9737, 0.9845, and 0.9841. In addition, we encapsulate the model and build a related iOS application to make the model more applicable. The suggested model also won the second prize in the 2021 Chinese Collegiate Computing Competition.

show abstract

Section: Related Workmentioning

confidence: 99%

Symmetry GAN Detection Network: An Automatic One-Stage High-Accuracy Detection Network for Various Types of Lesions on CT Images

Zhang

et al. 2022

Symmetry

View full text Add to dashboard Cite

show abstract

“…Watermarking scheme uses different domain such as spatial domain and frequency domain. Spatial domain is simple and straight forward to use but not robust and also faces difficulty in surviving attacks [6,15]. Transform domain or frequency domain is robust in nature, and information is embedded in transform co-efficient.…”

Section: Different Security Techniques Used For Medical Imagesmentioning

confidence: 99%

“…The proposed method shows the result in terms of higher PSNR and high EPR with weighted peak signal to noise ratio (WPSNR). Roy et al [6] give a brief review about different aspects of biomedical image security and different methods to provide medical image security. Jero et al [7] proposed a method using DWT and SVD.…”

Section: Introductionmentioning

confidence: 99%

Security of Medical Images Using DWT and SVD Watermarking Technique

Singh¹,

Singh²

2021

Lecture Notes in Electrical Engineering

View full text Add to dashboard Cite

“…Image encryption has received much attention in the last few years [18,23,24]. This is more needed for biomedical images, since they are part of human information [25,26]. A review on medical image encryption has been proposed in refs [27][28][29].…”

Section: Introductionmentioning

confidence: 99%

Biomedical Image Encryption with a Novel Memristive Chua Oscillator Embedded in a Microcontroller

et al. 2023

View full text Add to dashboard Cite

In this paper, a chaos-based encryption/decryption scheme using a novel memristive Chua oscillator to protect medical images is presented. The novel Chua oscillator is constructed by using the active voltage memristor in the nonlinear branch of the Chua oscillator. The chaotic dynamics behaviors are investigated using 1-D, 2-D bifurcation diagrams, time traces, basin of attractions, and largest Lyapunov exponent plot. The study reveals that the novel memristive Chua oscillator exhibits versatile transitions to chaos with interesting dynamics like multistability, spiking, and bursting oscillations just to name a few. These remarkable features are experimentally confirmed by a laboratory microcontroller-based setup. Thereafter, a chaos-based cryptography algorithm designed for biomedical images is built using pseudorandom number generated from the oscillator. The robustness and security tests undergone by the algorithm yielded high sensitivity on the encryption keys and resisted noise contamination as well as data loss. These results are encouraging and prove that the chaos-based cryptosystem built with the memristive Chua circuit-generated pseudorandom number is suitable for securing images in a healthcare system.

show abstract

A Study on the Applications of the Biomedical Image Encryption Methods for Secured Computer Aided Diagnostics

Cited by 34 publications

References 38 publications

Symmetry GAN Detection Network: An Automatic One-Stage High-Accuracy Detection Network for Various Types of Lesions on CT Images

Symmetry GAN Detection Network: An Automatic One-Stage High-Accuracy Detection Network for Various Types of Lesions on CT Images

Security of Medical Images Using DWT and SVD Watermarking Technique

Biomedical Image Encryption with a Novel Memristive Chua Oscillator Embedded in a Microcontroller

Contact Info

Product

Resources

About