Artificial Intelligence in Breast Cancer Early Detection and Diagnosis

By: Khalid Shaikh, Rohit Thanki, Sabitha K

This book provides an introduction to next generation smart screening technology for medical image analysis that combines artificial intelligence (AI) techniques with digital screening to develop innovative methods for detecting breast cancer. The authors begin with a discussion of breast cancer, its characteristics and symptoms, and the importance of early screening. It then provide insight on the role of artificial intelligence in global healthcare, screening methods for breast cancer using mammogram, ultrasound, and thermogram images, and the potential benefits of using AI-based systems for clinical screening to more accurately detect, diagnose, and treat breast cancer.

  • Discusses various existing screening methods for breast cancer;
  • Presents deep information on artificial intelligence-based screening methods;
  • Discusses cancer treatment based on geographical differences and cultural characteristics.

Hybrid and Advanced Compression Techniques for Medical Images

By: Rohit Thanki, Ashish Kothari

This book introduces advanced and hybrid compression techniques specifically used for medical images. The book discusses conventional compression and compressive sensing (CS) theory based approaches that are designed and implemented using various image transforms, such as: Discrete Fourier Transform (DFT), Discrete Cosine Transform (DCT), Discrete Wavelet Transform (DWT), and Singular Value Decomposition (SVD) and greedy based recovery algorithm. The authors show how these techniques provide simulation results of various compression techniques for different types of medical images, such as MRI, CT, US, and x-ray images. Future research directions are provided for medical imaging science. The book will be a welcomed reference for engineers, clinicians, and research students working with medical image compression in the biomedical imaging field.

  • Covers various algorithms for data compression and medical image compression;
  • Provides simulation results of compression algorithms for different types of medical images;
  • Provides study of compressive sensing theory for compression of medical images.

Dental Image Processing for Human Identification

By: Trivedi, D.N., Shah, N.D., Kothari, A.M., Thanki R.M.

This book presents an approach to postmortem human identification using dental image processing based on dental features and characteristics, and provides information on various identification systems based on dental features using image processing operations. The book also provides information on a novel human identification approach that uses Infinite Symmetric Exponential Filter (ISEF) based edge detection and contouring algorithms.

  • Provides complete details on dental imaging;
  • Discusses the important features of a human identification approach and presents a brief review on DICOM standard for dental imaging;
  • Presents human identification approach based on dental features.

Medical Imaging and its Security in Telemedicine Applications

By: Rohit Thanki, Surekha Borra

This book introduces medical imaging, its security requirements, and various security mechanisms using data hiding approaches. The book in particular provides medical data hiding techniques using various advanced image transforms and encryption methods. The book focuses on two types of data hiding techniques: steganography and watermarking for medical images. The authors show how these techniques are used for security and integrity verification of medical images and designed for various types of medical images such as grayscale image and color image. The implementation of techniques are done using discrete cosine transform (DCT), discrete wavelet transform (DWT), singular value decomposition (SVD), redundant DWT (RDWT), fast discrete curvelet transform (FDCuT), finite ridgelet transform (FRT) and non-subsampled contourlet transform (NSCT). The results of these techniques are also demonstrated after description of each technique. Finally, some future research directions are provided for security of medical images in telemedicine application.

A steganographic approach for secure communication of medical images based on the DCT-SVD and the compressed sensing (CS) theory

By: Rohit Thanki, Surekha Borra, Vedvyas Dwivedi, Komal Borisaga

In this paper, a hybrid approach based on cryptography and steganography is proposed for the security of medical image over an open communication channel. In this approach, medical image information is embedded using discrete cosine transform (DCT)-singular value decomposition (SVD)-based embedding process. The medical image is encrypted using CS encryption before embedding into the standard image. This encrypted medical image is inserted into the singular values of DCT coefficients of the standard image to get the stego image. The experimental results show that the encrypted medical image is successfully extracted from the stego image under various image processing attacks at recovering side. The result analysis also shows improved imperceptibility of the stego image with a peak signal-to-noise ratio value above 60 dB for all types of medical images under consideration. Furthermore, the computation time of proposed approach is less than that of existing approaches.

A FRT – SVD Based Blind Medical Watermarking Technique for Telemedicine Applications

By: Rohit Thanki, Surekha Borra—svd-based-blind-medical-watermarking-technique-for-telemedicine-applications/223939

In this article, a blind and robust medical image watermarking technique based on Finite Ridgelet Transform (FRT) and Singular Value Decomposition (SVD) is proposed. A host medical image is first transformed into 16 × 16 non-overlapping blocks and then ridgelet transform is applied on the individual blocks to obtain sets of ridgelet coefficients. SVD is then applied on these sets, to obtain the corresponding U, S and V matrix. The watermark information is embedded into the host medical image by modification of the value of the significant elements of U matrix. This proposed technique is tested on various types of medical images such as X-ray and CT scan. The simulation results revealed that this technique provides better imperceptibility, with an average PSNR being 42.95 dB for all test medical images. This technique also overcomes the limitation of the existing technique which is applicable on only the Region of Interest (ROI) of the medical image.

Secure transmission and integrity verification of color radiological images using fast discrete curvelet transform and compressive sensing

By: Surekha Borra, Rohit Thanki, Nilanjan Dey, Komal Borisagar

Rapid growth in digitization and globalization has influenced the medical field immensely. The radiological pictures are frequently shared comprehensively among specialists, medicinal experts, radiologists, analysts, and patients themselves by means of wired or remote media for purposes, for example, common accessibility and enhancing the diagnostic results. This paper proposes a hybrid and high capacity image hiding technique for secure transmission and integrity of color radiological images. The Compressive Sensing (CS) theory is used to encrypt the color secret image before embedding them into high frequency Fast Discrete Curvelet Transform (FDCuT) coefficients of color radiological images. The simulations gave a PSNR of 63.96 dB, which demonstrates better performance in terms of imperceptibility of stego color radiological image. Further, expansive payload limit is permitted when contrasted with many existing strategies.

Crypto-watermarking scheme for tamper detection of medical images

By: Surekha Borra, Rohit Thanki

Medical images of patients are often exchanged among specialist physicians, radiologists, hospital authorities and patients for remote monitoring and assessment as part of telemedicine. With the revolutions in the technology, the threat models and attackers are evolving on a daily basis and hence there is a constant need for the development of novel schemes that can protect personal information. In this paper, a non-blind fragile watermarking is developed to invisibly hide and integrate patient’s unique information such as biometrics in their radiological images for secure authentication, integrity verification and tamper detection purposes. The concept of compressive sensing theory is employed with discrete cosine transform to improve confidentiality. The performance of the proposed scheme is tested and evaluated on three types of medical images: X-ray, computed tomography and magnetic resonance imaging. The proposed scheme presents a means of verifying data integrity when medical images are subjected to attacks. The experimental results showed that the scheme invisibly hides high payloads of patient’s unique identities, apart from providing better tamper detection. The simulation results show that the proposed scheme provides high imperceptibility up to 92 dB and high payload capacity of up to 1 bpp.

A RONI Based Visible Watermarking Approach for Medical Image Authentication

By: Rohit Thanki, Surekha Borra, Vedvyas Dwivedi, Komal Borisagar

Nowadays medical data in terms of image files are often exchanged between different hospitals for use in telemedicine and diagnosis. Visible watermarking being extensively used for Intellectual Property identification of such medical images, leads to serious issues if failed to identify proper regions for watermark insertion. In this paper, the Region of Non-Interest (RONI) based visible watermarking for medical image authentication is proposed. In this technique, to RONI of the cover medical image is first identified using Human Visual System (HVS) model. Later, watermark logo is visibly inserted into RONI of the cover medical image to get watermarked medical image. Finally, the watermarked medical image is compared with the original medical image for measurement of imperceptibility and authenticity of proposed scheme. The experimental results showed that this proposed scheme reduces the computational complexity and improves the PSNR when compared to many existing schemes.

Intelligent approach for retinal disease identification

By: Vipul Rajyaguru, Chandresh Vithalani, Rohit Thanki

In recent time, various types of biomedical images are available at every health stations for diagnostic of different diseases. These images can easily be detected and can identify the issues of the disease by analyzing it. Nowadays, retinal based images are widely used for the identification of diabetes-related health issues. Glaucoma is a retinal disease that plays an important role in detecting of an earlier stage of diabetes. This disease affects the optic nerve system and astrocytes of the retina. This chapter presents basic steps for the detection of glaucoma in the retinal image. In this approach, various retinal features such as nerve lines, optic cup, optic disk, cup-to-disk ratio, and so on are used for the detection of glaucoma disease using the retinal image. In this chapter, a study of various approaches for glaucoma detection based on different image-processing methodologies and machine-learning algorithms are given. This chapter also provides an analysis of glaucoma detection in color fundus retinal image using various image-processing methods, fuzzy C-mean clustering, and thresholding. This approach can be used for the classification of the color retinal image. Experimental results also show that the presented approach works better than the existing approaches in the literature.

Application of Machine Learning Algorithms for Classification and Security of Diagnostic Images

By: Rohit Thanki, Surekha Borra

As of late, different sorts of diagnostic images have been produced everywhere in clinics, diagnostic centers, and well-being stations. Accordingly, diagnostic images are effortlessly put away, transmitted and appropriated between different stations and hence arises the issue of legitimate administration of patient information at every point of the framework. Additionally, these pictures are exchanged from one hospital to other for better treatments and diagnosis, which are effectively controlled or replicated by assailant. Hence, the security of medical images is the need of the hour. This chapter is focused on classification and security of diagnostic images using machine learning. These methods are likewise enhanced to provide security of medical images in telemedicine applications.

A Hybrid Watermarking Technique for Copyright Protection of Medical Signals in Teleradiology

By: Rohit Thanki, Surekha Borra, Komal Borisagar

Today, an individual’s health is being monitored for diagnosis and treatment of diseases upon analyzing various medical data such as images and signals. Modifications of this medical data when it is transferred over an open communication channel or network leads to deviations in diagnosis and creates a serious health issue for any individual. Digital watermarking techniques are one of the solutions for providing protection to multimedia contents. This chapter gives requirements and various techniques for the security of medical data using watermarking. This chapter also demonstrates a novel hybrid watermarking technique based on fast discrete curvelet transform (FDCuT), redundant discrete wavelet transform (RDWT), and discrete cosine transform (DCT). This watermarking technique can be used for securing medical various types of medical images and ECG signals over an open communication channel.

Medical Imaging and Its Objective Quality Assessment: An Introduction

By: Rohit Thanki, Surekha Borra, Nilanjan Dey, Amira Ashour

With the rise in research on applications of medical image processing, the evaluation of parameters and techniques required for measurement of medical image quality is the need of the hour. The effective, yet automatic methods for measurement of quality of a medical image are of particular interest. This chapter is an overview of different medical imaging technologies, and the related image quality assessment (IQA) algorithms. The main focus is on objective assessment (OA), rather than subjective assessment (SA). Three types of OA-based IQA algorithms are presented in detail: full reference-based IQA (FR-IQA) algorithms; no reference-based IQA (NR-IQA) algorithms and reduced reference-based IQA (RR-IQA) algorithms.