Medical images can be constructed in two-dimensional (2D) or three-dimensional (3D) view imaging to be applied in disease detection and diagnosis inside the body, such as cancer/tumor, heart, or lung-related diseases. These images may contain patients’ privacy information and clinical diagnosis records. Hence, these images need to ensure authorization demands among hospitals, medical service organizations, or physicians in a picture archiving and communication system. This study presents an intelligent symmetric cryptography with a chaotic map and quantum-based key generator (KG) for medical image encryption and decryption. Overall scheme processes include (1) random cipher code generation, (2) training gray relational analysis (GRA)-based encryptor and decryptor, and (3) decrypted image evaluation. The hybrid chaotic map and quantum-based KG are used to increase the chaotic complexity and unpredictable levels to produce cipher codes for changing pixel values (substitution method) in a 2D image by 256 key-space cipher codes. The first and second GRA models are used to train the cipher codes to achieve an encryptor and a decryptor, respectively. Through the methodology validation using a chest X-ray database, the structural similarity index measurement is employed to evaluate the decryption quality between the plain image and decrypted image. The encrypted images show a visual uncorrelation with the plain images, and experimental results indicate higher confidences against the passive eavesdropper.

The internet of medical thing system (IoMTS) comprises the fifth-generation (5G) networking technology that collects and shares digital data from signal- or image-capturing devices through computer and wireless communication networks. This framework enables healthcare professionals to gain immediate visibility into a patient’s condition and facilitates communication with patients and family members. Recently, artificial intelligence (AI)- based methods are being increasingly applied to preprocess digital data and extract features. The key physiological parameters and feature patterns can then be incorporated into AI- based tools to help monitor, detect, and diagnose applications. However, these digital data contain patients’ privacy and may be restricted to authorized users. In a public channel, IoMTS must ensure information security for protection against hacker attacks. Hence, in this study, a symmetric encryption and decryption protocol was designed to ensure infosecurity of biosignals and medical images and assist in specific purposes in disease diagnosis. For a symmetric cryptography scheme, this study proposed a key generator combining a chaotic map and Bell inequality and generating unordered numbers and unrepeated 256 secret keys in the key space. Then, a machine learning - based model was employed to train the encryptor and decryptor for both biosignals and image infosecurity. After secure - data transmission, a case study is conducted for classifying medical images. Here, a classifier based on a convolutional neural network (CNN) is used for AI- assisted breast tumor diagnosis. In addition, for biosignal infosecurity, raw data were collected from a radar millimeter-wave (mm-Wave) sensing firmware for detecting vital signs. The experimental results are validated for heartbeat signals, respiratory signals, and mammography images, demonstrating the effectiveness and feasibility of the proposed encryption, decryption, and AI-assisted diagnosis methods.

Digital physiological signals in telecare medicine information systems have been widely applied in remote medical applications, such as telecare, tele-examination, and telediagnosis, via computer networking transmission or wireless communication. However, these medical records need to ensure authorization demands in the channel model for human body communication and remote medical servers and enhance the confidentiality, recoverability, and availability of transmission data. Hence, this study proposes a symmetric cryptography scheme with a chaotic map and a multilayer machine learning network (MMLN) to achieve physiological signal infosecurity. A chaotic pseudorandom number generator within specific control parameters can dynamically produce unordered sequence numbers to set the secret keys for a regular secret key update, thereby improving the security of private cipher codes. The chaotic map is quickly iterated to produce a pseudorandom key stream for real-time applications, and the private cipher codes are selected using the initial and specific control parameters at the data emitter and receiver ends. A general regression neural network is used to map the high-dimensional input-output pair of cipher codes for substitution and permutation processes. Its adaptive MMLN with an optimization algorithm can rapidly train the random cipher code protocol to achieve an encryptor and a decryptor for a regular encrypted communication. Using the Massachusetts Institute of Technology-Beth Israel Hospital (MIT-BIH) Arrhythmia Database, 100 electrocardiogram fragments are used to verify the proposed model, and the peak signal-to-noise ratio (PSNR) as a quantitative quality metric is used to evaluate the visual quality after encryption and decryption processes for further diagnosis applications. Experimental results show that the proposed scheme has a higher mean PSNR (35.26 ± 3.77 dB) and shorter mean executing time (0.16 ± 0.01 s) compared with traditional cryptography protocol schemes.

Consensus criteria for tremor classification in Parkinson’s disease (PD) patients are clinically important for automatically evaluating the PD rating scale. Wearable sensing tools with direct contact measurements can obtain physiological signals to monitor tremor symptoms. Then, machine learning algorithms (MLAs) can train the frequency-based parameters and motion features to accurately measure PD-related tremors. Noncontact measurement with customized computer information devices can also digitalize the digitized handwritten patterns with the bespoke movements that a hand makes for identifying tremor classes. However, wearable sensors need a set of multiple electrodes to be placed on a patient’s body to acquire biosignals, and the setup does not allow continuous measurement and limits the patient’s motion range. The handwritten patterns of noncontact-based methods need frequency-domain and linearization transformations. In addition, feature extraction methods and MLAs are limited in complex computations and adaptive applications. Hence, in this work, a noncontact measurement with an array X-band microwave (10 GHz) Doppler-based linear quantizer is designed to continuously measure upper limb movements for tremor class scaling. To overcome the complex computations, time-domain parametric features, including zero crossing (ZC), Willison amplitude (WAMP), and waveform length (WL) indexes, are used to extract the physical changes in the oscillation frequencies, amplitudes, and directions of tremor signals for scaling upper limb tremor (ULT) levels. In the experiments involving 10 subjects, the proposed noncontact bioradar sensor could quantify asymmetrical and irregular oscillations with a positive correlation (mean R ² > 0.85) between the three indexes (ZC, WAMP, WL) and various oscillation frequencies. The linear relationship quantizer could predict the ULT levels from 0 Hz to 8 Hz for PD patients (typical tremor frequency: 4–6 Hz). It could also map the three indexes into colored visual representation for computerized visual analysis.

Chest X-ray images are usually used to identify the causes of patients symptoms, including the classes of lung or heart disorders. In visualization examination, CXR imaging in anterior posterior views is a preliminary screening method used by clinicians or radiologists to diagnose possible lung abnormalities. However, the identification of the causes of multiple abnormalities associated with coexisting conditions presents a challenge. In ruling out a suspected lung disease, the signs and symptoms of physical conditions need to be identified to arrive at a definitive diagnosis. Hence, this study aims to propose an iterated function system (IFS) and a multilayer fractional-order machine learning classifier to rapidly screen the possible classes of lung diseases within regions of interest on CXR images and to improve screening accuracy. For digital image processes, a two-dimensional (2D) fractional-order convolution is used to enhance symptomatic features. The IFS with nonlinear interpolation functions is then used to reconstruct the 2D feature patterns. These reconstructed patterns are self-affine in the same class and thus help distinguish normal subjects from those with lung diseases. The accuracy rate is thus improved. The proposed classifier is evaluated in terms of recall (99.6%), precision (87.78%), accuracy (88.88%), and F1 score (0.9334).

Imaging examinations, such as chest X-ray (CXR) images, can be used for early detection of diseases inside the human body, such as lung cancer, and cardio-pulmonary-related diseases; however, they may contain patients’ private information, which raises concerns about the security levels of medical images in Internet of Medical Things (IoMT) systems. The promising authorization protocol algorithm in 5th-generation networking technology can protect medical image confidentiality, recoverability, and availability. Hence, we propose a symmetric cryptography protocol based on the Riemann–Lebesgue (R–L)-based key generator and a machine learning (ML)-based cryptography scheme for CXR image infosecurity. The R–L-based key generator uses the composite function, ${g}$ ( ${x}$ ) • sin((1/2 $+\,\,{N}$ ) • ${x}$ ), to dynamically produce the oscillation function by controlling the terms of the nonlinear function ${g}$ ( ${x}$ ), and frequency ${N}$ , which are used to produce the random- number seed and to select nonordered numbers and nonrepeated 256 secret keys in the key space. The ML-based scheme uses these random secret keys to train an image encryptor and decryptor, respectively. Based on the diffusion method, the ML-based cryptography scheme is used to change image pixel values. For evaluation experiments, CXR images are collected from the National Institutes of Health CXR database and used to evaluate image quality after encryption and decryption processes. For different cardiopulmonary-related disease images, the number of pixel change rates (NPCRs) and unified averaged changed intensity (UACI) are used to evaluate the security level and decryption quality. The experimental results show an average NPCR of 99.6% and average UACI of 32.61% between plain and cipher images for evaluating the security level, enabling further online diagnosis applications in IoMT systems.