A Robust and Reliable Tele-medical data Security and Authentication System using Spread Spectrum Steganography

Abstract

An emerging area with unique security challenges is the area of automated diagnosis (autodiagnosis) in teleradiology. In teleradiology, patients’ scans and associated electronic medical records(EMR) are transmitted to a remote location (rural-urban or urban-urban) for image analysis, classification, and diagnosis. The major challenge with this approach is that these scans and EMR are often fragmented and sent out to different users, such as requesting hospitals, independent specialists, patients, external artificial intelligence(AI) systems, and image archives. This occurrence makes it difficult to control the security and privacy of these health information. Therefore, new methods for tamper detection on the image and secrecy preservation of patient’s health records are now necessary in this new setting.

Steganography and digital watermarking, collectively known as information hiding (IH) techniques, are among the methods of providing robust security for multimedia (image, video, audio, and text) data. In particular, Spread Spectrum(SS) Steganography and watermarking are hiding techniques that provide secret and robust information hiding, respectively, by using secret keys that are known only to the authorized parties. However, due to the non-standardisation of IH techniques, coupled with the issues of diagnostic quality after data hiding in medical images, the adoption of IH methods in medical practice is currently low. Hence, we are also faced with the challenges of validation and adoption of IH-based algorithms for practical use.

Therefore, we are faced with two major challenges in this thesis: (i)how to improve tamper detection and data hiding capacity of spread spectrum steganography while retaining its robustness and secrecy and(ii)how to increase the adoption of data hiding security techniques in teleradiology for autodiagnosis. The goal of solving these challenges is to improve global healthcare with maximum security but at a low cost. The quest to achieve this objective led to the following contributions in this thesis:

1. Firstly, we design a new algorithm known as the Spread Spectrum-based Constant Correlation Compression Coding Scheme (C4S) for cover data Integrity and zero Bit Error Rate (BER) covert message detection. The goal is to allow both accurate and robust detection of secret message in the form of EMR, and content integrity verification by a third-party remote application.

2. Secondly, by leveraging the method developed above and the amplitude modulation techniques, we improved SS Steganographic data hiding capacity. We increased the number of bits that can be embedded in each 8x8 image sub-block from the classical 1 bit to 12 bits for 16-bit DICOM and 9 bits for 8-bit natural images. This steganographic capacity was achieved by both increasing the number of unique sequences and the number of frequency channels used for transmission.

3. The predictors and features (known as image biomarkers in medicine) used for remote autodiagnosis, are not usually considered while evaluating medical image IH algorithms. Thus, in this contribution, the effect of IH in computer-aided diagnosis is evaluated based on statistical significance testing of the feature changes, and Machine Learning classification (Support Vector Machine) of Chest X-ray scans of Normal and Pneumonia patients. The results imply that attention should be paid to the specific biomarkers that are sensitive to embedded information but are also relevant in autodiagnosis.

4. Finally, to bring together several algorithms, evaluation mechanisms, and medical image watermarking into practical use, a unified software framework was designed. This unified framework intends to standardise the validation and adoption all IH algorithms for medical image security applications.

In conclusion, this thesis has developed and evaluated new spread spectrum steganography security algorithms for both EMR extraction in the face of attacks and semi-fragile medical image tamper detection, thereby achieving both accuracy and integrity checks, unlike in the basic SS steganography. It also allows higher capacity, especially in the region of non-interest (RONI) of medical images. To enable the adoption of medical image IH techniques in autodiagnosis, a new software framework for unifying algorithms' testing and validation is designed. These contributions are believed to have advanced knowledge in the area of IH and informed practice in the area of medical data security.