Medical Image Analysis

A novel automatic 3D+time left ventricle (LV) segmentation framework is proposed for cardiac magnetic resonance (CMR) datasets. The proposed framework consists of three conceptual blocks to delineate both endo and epicardial contours throughout the cardiac cycle: 1) an automatic 2D midventricular initialization and segmentation; 2) an automatic stack initialization followed by a 3D segmentation at the end-diastolic phase; and 3) a tracking procedure. Hereto, we propose to adapt the recent B-spline Explicit Active Surfaces (BEAS) framework to the properties of CMR images by integrating dedicated energy terms. Moreover, we extend the coupled BEAS formalism towards its application in 3D MR data by adapting it to a cylindrical space suited to deal with the topology of the image data. Furthermore, a fast stack initialization method is presented for efficient initialization and to enforce consistent cylindrical topology. Finally, we make use of an anatomically constrained optical flow method for temporal tracking of the LV surface.

The purpose of this paper is to present a survey of recent (published in 1993 or later) publications concerning medical image registration techniques. These publications will be classified according to a model based on nine salient criteria, the main dichotomy of which is extrinsic versus intrinsic methods. The statistics of the classification show definite trends in the evolving registration techniques, which will be discussed. At this moment, the bulk of interesting intrinsic methods is based on either segmented points or surfaces, or on techniques endeavouring to use the full information content of the images involved. .nl) a Also formerly and popularly CAT, computed axial tomography. b Also referred to as NMR, nuclear magnetic resonance, spin imaging and various other names. c Also echo(graphy).

Breast cancer is the most frequent cancer type among women. We present a method of classification of nodules (malignant or benign) found in mammograms using shape-based attributes and texture-based ones. Firstly, we built a test database, then we segmented and extracted a Gray Level Cooccurrence Matrix (GLCM) from each mammographic finding and analyzed texture-based and shape-based attributes. Finally, classification was performed through machine learning algorithms. Tests reached a maximum Correct Classification Rate (CCR) of 93.75%, when performed with the Radial Basis Function Network algorithm. The largest area under the ROC curve (AUC), 0.964, was achieved with the Multilayer Perceptron algorithm.

In this paper, we contribute to the development of context-aware operating rooms by introducing a novel approach to modeling and monitoring the workflow of surgical interventions. We first propose a new representation of interventions in terms of multidimensional time-series formed by synchronized signals acquired over time. We then introduce methods based on Dynamic Time Warping and Hidden Markov Models to analyze and process this data. This results in workflow models combining low-level signals with high-level information such as predefined phases, which can be used to detect actions and trigger an event. Two methods are presented to train these models, using either fully or partially labeled training surgeries. Results are given based on tool usage recordings from sixteen laparoscopic cholecystectomies performed by several surgeons.

Skin diseases are among the most common health problems worldwide. In this article we proposed a method that uses computer vision based techniques to detect various kinds of dermatological skin diseases. We have used different types of image processing algorithms for feature extraction and feed forward artificial neural network for training and testing purpose. The system works on two phases- first pre-process the colour skin images to extract significant features and later identifies the diseases. The system successfully detects 9 different types of dermatological skin diseases with an accuracy rate of 90%.

Knowledge about the biological variability of anatomical objects is essential for statistical shape analysis and discrimination between healthy and pathological structures. This paper describes a novel approach that incorporates the variability of an object population into the generation of a characteristic 3D shape model. The proposed shape representation is a coarse-scale sampled medial description derived from a fine-scale spherical harmonics (SPHARM) boundary description. This medial description is composed of a net of medial samples (m-rep) with fixed graph properties. The medial model is computed automatically from a predefined shape space using pruned 3D Voronoi skeletons. A new method determines the stable medial branching topology from the shape space. An intrinsic coordinate system and an implicit correspondence between shapes is defined on the medial manifold. Several studies of biological structures clearly demonstrate that the novel representation has the promise to describe shape changes in a natural and intuitive way. A new medial shape similarity study of group differences between monozygotic and dizygotic twins in lateral ventricle shape demonstrates the meaningful and powerful representation of local and global form.

This report describes the design, implementation, evaluation and original enhancements to the Live-Wire method for 2D and 3D image segmentation. Live-Wire 2D employs a semi-automatic paradigm; the user is asked to select a few boundary points of the object to segment, to steer the process in the right direction, while the result is displayed in real time. In our implementation segmentation is extended to three dimensions by performing this process on a slice-by-slice basis. User's time and involvement is further reduced by allowing him to specify object contours in planes orthogonal to the slices. If these planes are chosen strategically, Live-Wire 3D can perform 2D segmentation in the plane of each slice automatically. This report also proposes two improvements to the original method, path heating and a new graph edge feature function based on variance of path properties along the boundary. We show that these improvements lead up to a 33% reduction in interaction with the user, and improved delineation in presence of strong interfering edges.

This article surveys deformable models, a promising and vigorously researched computer-assisted medical image analysis technique. Among model-based techniques, deformable models offer a unique and powerful approach to image analysis that combines geometry, physics, and approximation theory. They have proven to be effective in segmenting, matching, and tracking anatomic structures by exploiting (bottom-up) constraints derived from the image data together with (top-down) a priori knowledge about ...

—Hough transform (HT) is a typical method to detect or segment geometry objects from images. In this paper, we study the principle of Hough Transform and its mathematical expressions, and try to use a new approach based on Hough transform for quick line and circle detection in image processing. Our method accurately detected some simple graphics, such as straight line of different direction, circles of different detection, thickness and different number. The results show that our method is less memory consumption and calculated fast, which could be applied for line detection and segmentation in 3D ultrasonic image.

Many recent high angular resolution diffusion imaging (HARDI) reconstruction techniques have been introduced to infer an orientation distribution function (ODF) of the underlying tissue structure. These methods are more often based on a single-shell (one b-value) acquisition and can only recover angular structure information contained in the ensemble average propagator (EAP) describing the three-dimensional (3D) average diffusion process of water molecules. The EAP can thus provide richer information about complex tissue microstructure properties than the ODF by also considering the radial part of the diffusion signal. In this paper, we present a novel technique for analytical EAP reconstruction from multiple q-shell acquisitions. The solution is based on a Laplace equation by part estimation between the diffusion signal for each shell acquisition. This simplifies greatly the Fourier integral relating diffusion signal and EAP, which leads to an analytical, linear and compact EAP reconstruction. An important part of the paper is dedicated to validate the diffusion signal estimation and EAP reconstruction on real datasets from ex vivo phantoms. We also illustrate multiple q-shell diffusion propagator imaging (mq-DPI) on a real in vivo human brain and perform a qualitative comparison against state-of-the-art diffusion spectrum imaging (DSI) on the same subject. mq-DPI is shown to reconstruct robust EAP from only several different b-value shells and less diffusion measurements than DSI. This opens interesting perspectives for new q-space sampling schemes and tissue microstructure investigation.

In this work we propose a comprehensive study of Digital Stent Enhancement (DSE), from the analysis of requirements to the validation of the proposed solution. First, we derive the stent visualization requirements in the context of the clinical application and workflow. Then, we propose a DSE algorithm combining automatic detection, tracking, registration and contrast enhancement. The most original parts of our solution: landmark segmentation and non-linear image registration are detailed. Finally, we validate the algorithm on a large number of synthetic and clinical cases. Performance is characterized in terms of image quality, automation, and execution time. This work is, to the best of our knowledge, the first comprehensive article on DSE, covering problem statement, proposed solution, and validation strategies.

Aim-To determine the gender using mental foramen as landmark on a panoramic radiographs in selected North Gujarat population. Objective-1. To evaluate and compare the superior border of mental foramen to lower border of mandible(S-L) and inferior border of mental foramen to lower border of mandible(I-L) value in males and females bilaterally. 2. To compare the S-L and I-L between right and left side in males and female 3. To utilize above measurements for gender determination. Materials and Method-Sixty panoramic radiographs were selected for the analysis of mental foramen. Tangents were drawn through the superior and inferior borders of the foramen (S-L and I-L respectively) and perpendicular from the tangents to the lower border of the mandible bilaterally. Digital verniar caliper was used for the distance measurement from S-L and I-L. The data obtained was tabulated and subjected to statistical analysis. Result-The analyzed data of study showed that the mean values of comparison of S-L as well as I-L in males and females were significantly higher in males as compared to females. The comparison of SL and IL on right and left side in the same patient was without any significant difference. Conclusion-The results of present study concluded a definite sexual dimorphism in the position of the mental foramen from the base of the mandible; this method can applied in mass disaster where the fragments of mandible are available.

We present a new non-uniform sampling method for the accurate estimation of mutual information in multi-modal brain image rigid registration. Most existing density estimators used for mutual information computation incorrectly assume that the intensity of each voxel is independent from its neighborhood. Our method uses the 3D Fast Discrete Curvelet Transform to reduce the sampled voxels' interdependency by sampling voxels that are less dependent on their neighborhood, and thus provide a more accurate estimation of the mutual information and a more accurate registration. The main advantages of our method over other non-uniform sampling schemes are that: (1) it provides more accurate estimation of the image statistics with fewer samples; (2) it is less sensitive to the variability of anatomical structures shapes, orientations, and sizes, and; (3) it yields more accurate registration results. Extensive evaluation on 1000 synthetic registrations between T1 and T2-weighted clinical MRI images and 20 real clinical registrations of brain CT images to Proton Density (PD) and T1 and T2-weighted MRI images from the public RIRE database show the effectiveness of our method. Our method has the lowest mean registration errors recorded to date for CT-MR image registration in the RIRE website for methods tested on more than five datasets. These results indicate that our sampling scheme can be used to achieve more accurate multi-modal registration required for image guided therapy and surgery.

Breast cancer is the most common invasive cancer in women, affecting more than 10% of women worldwide. Microscopic analysis of a biopsy remains one of the most important methods to diagnose the type of breast cancer. This requires specialized analysis by pathologists, in a task that i) is highly time- and cost-consuming and ii) often leads to nonconsensual results. The relevance and potential of automatic classification algorithms using hematoxylin-eosin stained histopathological images has already been demonstrated, but the reported results are still sub-optimal for clinical use. With the goal of advancing the state-of-the-art in automatic classification, the Grand Challenge on BreAst Cancer Histology images (BACH) was organized in conjunction with the 15th International Conference on Image Analysis and Recognition (ICIAR 2018). A large annotated dataset, composed of both microscopy and whole-slide images, was specifically compiled and made publicly available for the BACH challenge...

We present an approach to generate 3-D arterial tree models based on physiological principles while at the same time certain morphological properties are enforced at construction time. The driving force of the construction is a simplified angiogenesis model incorporating case-specific information about the metabolic demand within the considered domain. The vascular tree is constructed iteratively by successively adding new segments in chemotactic response to angiogenic growth factors secreted by ischemic cells. Morphometrically confirmed bifurcation statistics of vascular networks are incorporated to optimize the synthetic vasculature. The proposed method is able to generate artificial, yet physiologically plausible, arterial tree models that match the metabolic demand of the embedding tissue and fulfill the prescribed morphological properties at the same time. The proposed tree generation approach is applied in a simulation setup based on the metabolic configuration and anatomy of the macaque visual cortex. We analyze the generated tree models with respect to morphological and physiological aspects including fluid-dynamic simulations. The comparison of our results with the findings of different studies on the structure of cerebral vasculatures demonstrates the plausibility of our method.

Skin diseases are among the most common health
problems worldwide. In this article we proposed a method that
uses computer vision based techniques to detect various kinds of dermatological skin diseases. We have used different types of image processing algorithms for feature extraction and feed
forward artificial neural network for training and testing purpose. The system works on two phases- first pre-process the
colour skin images to extract significant features and later
identifies the diseases. The system successfully detects 9 different types of dermatological skin diseases with an accuracy rate of 90%.

one of the most common malignant tumors in the world today is lung cancer, and it is the primary cause of death from cancer. With the continuous advancement of urbanization and industrialization, the problem of air pollution has become more and more serious. The best treatment period for lung cancer is the early stage. However, the early stage of lung cancer often does not have any clinical symptoms and is difficult to be found. In this paper, lung nodule classification has been performed; the data have used of CT image is SPIE AAPM-Lung. In recent years, deep learning (DL) was a popular approach to the classification process. One of the DL approaches that have used is Transfer Learning (TL) to eliminate training costs from scratch and to train for deep learning with small training data. Nowadays, researchers have been trying various deep learning techniques to improve the efficiency of CAD (computer-aided system) with computed tomography in lung cancer screening. In this work, we implemented pre-trained Convolutional Neural Networks include: AlexNet, ResNet18, Googlenet, and ResNet50 models. These networks are used for training the network and CT image classification. CNN and TL are used to achieve high performance resulting and specify lung cancer detection on CT images. The evaluation of models is calculated by some matrices such as confusion matrix, precision, recall, specificity, and f1-score.

A computer aided neural network classification of regions of suspicion (ROS) on digitized mammograms is presented in this paper which employs features extracted by a new technique based on independent component analysis. Our approach is concentrated in finding a set of independent source regions that generate the observed mammograms. The coefficients of the linear transformation of the source regions are used as features that describe effectively any normal and abnormal region in digital mammograms as well as benign and malignant ROS in the latter case. Extensive experiments in the MIAS Database have shown a recognition accuracy of 88.23% in the detection of all kinds of abnormalities and 79.31% in the task of distinguishing between benign and malignant regions, outperforming in both cases standard textural features, widely used for cancer detection in mammograms.

Abdominal organ segmentation is the segregation of a single or multiple abdominal organ(s) into semantic image segments of pixels identified with homogeneous features such as color and texture, and intensity. The abdominal organ(s) condition is mostly connected with greater amount of morbidity and mortality since most patients often have asymptomatic abdominal condition and symptoms, which is often recognized late hence, the abdomen has been the third most common cause of damage to the human body. That notwithstanding, there may be improved outcome when the condition of an abdominal organ is detected earlier. Over the years supervised and semi-supervised machine learning methods have been used to segment abdominal organ(s) in order to detect the organ(s) condition. The supervised methods performs well when the training data used is a representative of the data targeted but, the methods require large manual annotated data and has adaptation problem. The semi-supervised methods are fast but records poor performance than the supervised if assumptions made about the data fails to hold. Current state-of-the art methods of supervised segmentation are largely based on deep learning techniques due to its good accuracy and success in real world applications though it requires large amount of training data for automatic feature extraction else deep learning can hardly be used. As regards the semi-supervised methods of segmentation self-training and graph-based techniques have attracted much research attention. Self-training can be used with any classifier but does not have a mechanism to rectify mistakes early. Graph-based techniques thrives on its convexity, scalability, and effectiveness in application but have an out-of-sample problem. In this review paper, a study has been carried out on supervised and semi-supervised methods of performing abdominal organ segmentation. An observation of the current approaches connection and gaps are identified, and prospective future research opportunities are enumerated.

The disorders identified with retina of the eye such as: Diabetic Retinopathy (DR), age-related Macular Degeneration (AMD), Glaucoma, etc. can cause visual impairments. The retinal fundus pictures of the patients can be acquired with a computerized fundus camera. It can then be used as machine learning application against the manual technique for the detection and prevention of DR. In this research, the retinal fundus image obtained from Himalaya Eye Hospital Pokhara, MESSIDOR database and EyePACS are used for the detection of DR along with its severity label. In the preprocessing phase, the images are first converted to grayscale images. Histogram equalization technique is performed to adjust image intensity in order to enhance contrast. Median filtering, a non-linear digital filtering technique, is implemented to remove noise present in the image. It too helps to improve the result for further processing. Blood vessels are detected and optic discs are identified and removed. Exuda...

Przedstawiony tekst zawiera streszczenie referatu, wygłoszonego na zaproszenie organizatorów konferencji „Narzędzia teleinformatyczne w diagnostyce. Rozwój środowiska e-Health z wykorzystaniem technologii cyfrowych”. Konferencję zorganizowali łącznie Centrum Promocji Informatyki oraz Centrum Edukacji Medycznej. W materiałach konferencji (drukowanych oraz na CD) po przedstawionym tu streszczeniu zamieszczona jest pełna prezentacja PPT, zajmująca stronice aż do 273 włącznie.

Retinal images are routinely acquired and assessed to provide diagnostic evidence for many important diseases, e.g. diabetes or hypertension. Because of the acquisition process, very often these images are non-uniformly illuminated and exhibit local luminosity and contrast variability. This problem may seriously affect the diagnostic process and its outcome, especially if an automatic computer-based procedure is used to derive diagnostic parameters. We propose here a new method to normalize luminosity and contrast in retinal images, both intra- and inter-image. The method is based on the estimation of the luminosity and contrast variability in the background part of the image and the subsequent compensation of this variability in the whole image. The application of this method on 33 fundus images showed an average 19% (max. 45%) reduction of luminosity variability and an average 34% (max. 85%) increment of image contrast, with a remarkable improvement, e.g., over low-pass correction. The proposed image normalization technique will definitely improve automatic fundus images analysis but will also be very useful to eye specialists in their visual examination of retinal images.

Classification of skull fracture is a challenging task for both radiologists and researchers. Skull fractures result in broken pieces of bone, which can cut into the brain and cause bleeding and other injury types. So it is vital to detect and classify the fracture very early. In real world, often fractures occur at multiple sites. This makes it harder to detect the fracture type where many fracture types might summarize a skull fracture. Unfortunately, manual detection of skull fracture and the classification process is time-consuming, threatening a patient's life. Because of the emergence of deep learning, this process could be automated. Convolutional Neural Networks (CNNs) are the most widely used deep learning models for image categorization because they deliver high accuracy and outstanding outcomes compared to other models. We propose a new model called SkullNetV1 comprising a novel CNN by taking advantage of CNN for feature extraction and lazy learning approach which acts as a classifier for classification of skull fractures from brain CT images to classify five fracture types. Our suggested model achieved a subset accuracy of 88%, an F1 score of 93%, the Area Under the Curve (AUC) of 0.89 to 0.98, a Hamming score of 92% and a Hamming loss of 0.04 for this seven-class multi-labeled classification.

Downloaded from www.medrech.com " Rehabilitation of cleft lip and palate patients with a systematic approach " Sherawat Abstract: The oral rehabilitation of lip and palate patients is challenging and many of these patients are suffer if they don't receive sufficient dental treatment. Several techniques, including orthodontic appliances, surgeries, advanced prosthodontic rehabilitation and alveolar bone grafts have been proposed for the oral rehabilitation of these patients. There are still some difficulties in prosthetic rehabilitation of cleft lip and palate patients with conventional prostheses or implant retained prostheses because of insufficient alveolar bone quality and quantity, inadequate soft tissue, and abutment teeth. This paper is an attempt to review the systematic approach in management of cleft lip and palate patients.

Real-time vision is central to many embedded applications (e.g. vehicle guidance). It is a computationally intensive task well beyond current general purpose computing platforms such as PCs and workstations. Thus, most real time vision systems need special high performance computing platforms, commonly provided in the form of parallel processing engines or dedicated hardware. The proposed architecture uses new generations of re-programmable logic devices and modularised hardware, thereby gaining the performance advantage of hard-wired logic with the flexibility and associated economies of programmable systems. The architecture takes the form of an extensive processing hierarchy consisting of a set of tightly coupled parallel processors, each processing a portion of the image using a classic pipeline arrangement. A programmable image splitting (and reconstruction) engine feeds this array and offers the potential of further enhancing the performance of the engines by restructuring the...

The ability of Minkowski Functionals to characterize local structure in different biological tissue types has been demonstrated in a variety of medical image processing tasks. We introduce anisotropic Minkowski Functionals (AMFs) as a novel variant that captures the inherent anisotropy of the underlying gray-level structures. To quantify the anisotropy characterized by our approach, we further introduce a method to compute a quantitative measure motivated by a technique utilized in MR diffusion tensor imaging, namely fractional anisotropy. We showcase the applicability of our method in the research context of characterizing the local structure properties of trabecular bone micro-architecture in the proximal femur as visualized on multi-detector CT. To this end, AMFs were computed locally for each pixel of ROIs extracted from the head, neck and trochanter regions. Fractional anisotropy was then used to quantify the local anisotropy of the trabecular structures found in these ROIs and to compare its distribution in different anatomical regions. Our results suggest a significantly greater concentration of anisotropic trabecular structures in the head and neck regions when compared to the trochanter region (p < 10-4). We also evaluated the ability of such AMFs to predict bone strength in the femoral head of proximal femur specimens obtained from 50 donors. Our results suggest that such AMFs, when used in conjunction with multi-regression models, can outperform more conventional features such as BMD in predicting failure load. We conclude that such anisotropic Minkowski Functionals can capture valuable information regarding directional attributes of local structure, which may be useful in a wide scope of biomedical imaging applications.

Image registration is an important enabling technology in medical image analysis. The current emphasis is on development and validation of application-specific non-rigid techniques, but there is already a plethora of techniques and terminology in use. In this paper we discuss the current state of the art of non-rigid registration to put on-going research in context and to highlight current and future clinical applications that might benefit from this technology. The philosophy and motivation underlying non-rigid registration is discussed and a guide to common terminology is presented. The core components of registration systems are described and outstanding issues of validity and validation are confronted.

Cancer has become a leading cause of death worldwide. To deal with medical images to discover tumors and their types, Authors need a distinct experience in understanding medical images. Authors need machine learning techniques to reach great accuracy and speed to analyse these images to avoid a lack of experience or errors. In this paper, Authors will study a (SVM) of machine learning techniques used to classify brain images. SVM will be used in this paper to analyse brain images and discover Benign Tumor and Malignant tumor by using Matlab software. The results of the experiments conducted showed the accuracy of the system provided for the classification of tumor types (Benign, Malignant) found in medical brain images. Authors will adhere in this research that the images to be classified are limited by the presence of only two types of tumors. In the future, some pre-processing procedures will be added to the brain's medical images prior to the classification process.

Over the past three decades, significant developments have been made in hyperspectral imaging due to which it has emerged as an effective tool in numerous civil, environmental, and military applications. Modern sensor technologies are capable of covering large surfaces of earth with exceptional spatial, spectral, and temporal resolutions. Due to these features, hyperspectral imaging has been effectively used in numerous remote sensing applications requiring estimation of physical parameters of many complex surfaces and identification of visually similar materials having fine spectral signatures. In the recent years, ground based hyperspectral imaging has gained immense interest in the research on electronic imaging for food inspection, forensic science, medical surgery and diagnosis, and military applications. This review focuses on the fundamentals of hyperspectral image analysis and its modern applications such as food quality and safety assessment, medical diagnosis and image guided surgery, forensic document examination, defense and homeland security, remote sensing applications such as precision agriculture and water resource management and material identification and mapping of artworks. Moreover, recent research on the use of hyperspectral imaging for examination of forgery detection in questioned documents, aided by deep learning, is also presented. This review can be a useful baseline for future research in hyperspectral image analysis.

Over the past three decades, significant developments have been made in hyperspectral imaging due to which it has emerged as an effective tool in numerous civil, environmental, and military applications. Modern sensor technologies are capable of covering large surfaces of earth with exceptional spatial, spectral, and temporal resolutions. Due to these features, hyperspectral imaging has been effectively used in numerous remote sensing applications requiring estimation of physical parameters of many complex surfaces and identification of visually similar materials having fine spectral signatures. In the recent years, ground based hyperspectral imaging has gained immense interest in the research on electronic imaging for food inspection, forensic science, medical surgery and diagnosis, and military applications. This review focuses on the fundamentals of hyperspectral image analysis and its modern applications such as food quality and safety assessment, medical diagnosis and image guided surgery, forensic document examination, defense and homeland security, remote sensing applications such as precision agriculture and water resource management and material identification and mapping of artworks. Moreover, recent research on the use of hyperspectral imaging for examination of forgery detection in questioned documents, aided by deep learning, is also presented. This review can be a useful baseline for future research in hyperspectral image analysis. INDEX TERMS Agriculture, document images, food quality and safety, hyperspectral imaging, medical imaging, remote sensing.

The outbreak of novel coronavirus disease (COVID- 19) has claimed millions of lives and has affected all aspects of human life. This paper focuses on the application of deep learning (DL) models to medical imaging and drug discovery for managing COVID-19 disease. In this article, we detail various medical imaging-based studies such as X-rays and computed tomography (CT) images along with DL methods for classifying COVID-19 affected versus pneumonia. The applications of DL techniques to medical images are further described in terms of image localization, segmentation, registration, and classification leading to COVID-19 detection. The reviews of recent papers indicate that the highest classification accuracy of 99.80% is obtained when InstaCovNet-19 DL method is applied to an X-ray dataset of 361 COVID-19 patients, 362 pneumonia patients and 365 normal people. Furthermore, it can be seen that the best classification accuracy of 99.054% can be achieved when EDL_COVID DL method is appl...

The research presented in this thesis revolves around the digital watermarking and its application to medical images. Digital watermarking is an evolving technology, which has great promise for addressing multimedia information security. Digital medical images, on the other hand, are the outcome of the advanced imaging technology that has enabled modern health care to seamlessly offer many distant medical services. Thereby, with the remote access and distribution, medical images are subject to many complex and new legal and ethical issues. Under this circumstance, while the security need of the medical images is critical, the conventional tools seem to fall short of providing necessary protection. Digital watermarking has thus been studied to address this problem for this research.
Several research gaps have been identified. They are: (i) requirements for the watermarking of medical images are not well defined; (ii) there is no known construction of a complete or formal watermarking model that helps identify and evaluate the state-of-the-art watermarking scheme for an application; (iii) watermarking properties are not well defined and some of them (e.g., robustness, security) are naturally misinterpreted in practice; (iv) security levels of existing watermarking schemes are mostly unknown; and (iv) there is no watermark embedding scheme available which is equally suitable for various medical image modalities.
This research has started with a comprehensive literature review on digital watermarking schemes and their applications to medical images. A general watermarking model for digital image applications has then been developed and a set of fundamental watermarking properties (e.g., perceptual similarity, robustness, etc.) has been defined. Models for a set of expected attacks in digital image application scenarios have been developed using the proposed watermarking model. The current state of watermarking security has been reviewed and the need for complete security analysis of watermarking schemes has been identified. To this, three new counterfeiting attack models have been developed and validated for some image authentication schemes. Thereby, the watermarking based self-authentication schemes have been shown to violate the systematic definition of security.
For defending against the counterfeiting weaknesses and proposed attacks, a set of fundamental requirements has been determined and a tentative construction of a self-authentication scheme is proposed. Considering that construction, a novel medical image embedding scheme is developed that avoids the limitations of existing schemes. A watermarking capacity control framework is developed and validated using the asymptotic analysis. Experimental results demonstrate that the proposed scheme has higher capacity-distortion performance and more efficient capacity control ability than some prominent existing schemes. Being irreversible and general RONI (region of non-interest) based, the proposed scheme would help provide continuous security protection and minimize legal-ethical impacts, and thereby could be commercially viable in the future for different medical image applications.
This research advances knowledge in the area of digital image watermarking and its applications. Developing a formal model and defining fundamental parameters and possible attacks presented in this thesis, are the first steps toward a unified and intuitive watermarking theory. The developed model would allow a unified treatment of all practically meaningful variants of digital image watermarking schemes. The developed new attack models and their uses in rigorously analysing security of watermarking schemes can be used as principles to determine the security levels of watermarking schemes. The proposed watermarking scheme for medical images and its validation create knowledge of an efficient embedding approach, which can be used for different applications such as content authentication, tampering detection and localization, and annotation. Further, the generalized notion of watermarking capacity control and the use of asymptotic analysis for studying computational aspects of watermarking schemes would create a new era in watermarking research.
In summary, the findings, theoretical development and analyses, and experimental evidence of this research represent a comprehensive source of information, which can be assimilated and disseminated towards standardizing future research in the formal modelling, complete security analysis and computational aspects, of watermarking schemes.

Rozdział w książce "Podstawy inżynierii biomedycznej" poświęcony metodom automatycznego rozpoznawania obrazów. Omówiono ogólny schemat systemu rozpoznawania, wprowadzono i omówiono przestrzeń cech i zdefiniowano proces rozpoznawania obrazów na poziomie formalnym. Następnie omówiono wybrane metody rozpoznawania oraz wprowadzono ich klasyfikację.

Objective: This paper focuses on the use of image-based machine learning techniques in medical image analysis. In particular, we present some variants of local binary patterns (LBP), which are widely considered the state of the art among texture descriptors. After we provide a detailed review of the literature about existing LBP variants and discuss the most salient approaches, along with their pros and cons, we report new experiments using several LBP-based descriptors and propose a set of novel texture descriptors for the representation of biomedical images. The standard LBP operator is defined as a grayscale invariant texture measure, derived from a general definition of texture in a local neighborhood. Our variants are obtained by considering different shapes for the neighborhood calculation and different encodings for the evaluation of the local gray-scale difference. These sets of features are then used for training a machine-learning classifier (a stand-alone support vector machine). Methods and materials: Extensive experiments are conducted using the following three datasets:

One of the most common malignant tumors in the world today is lung cancer, and it is the primary cause of death from cancer. With the continuous advancement of urbanization and industrialization, the problem of air pollution has become more and more serious. The best treatment period for lung cancer is the early stage. However, the early stage of lung cancer often does not have any clinical symptoms and is difficult to be found. In this paper, lung nodule classification has been performed; the data have used of CT image is SPIE AAPM-Lung. In recent years, deep learning (DL) was a popular approach to the classification process. One of the DL approaches that have used is Transfer Learning (TL) to eliminate training costs from scratch and to train for deep learning with small training data. Nowadays, researchers have been trying various deep learning techniques to improve the efficiency of CAD (computer-aided system) with computed tomography in lung cancer screening. In this work, we i...

Data mining and knowledge discovery in databases have been attracting a significant amount of research, industry, and media attention of late. There is an urgent need for a new generation of computational theories and tools to assist researchers in extracting useful information from the rapidly growing volumes of digital data

The ever-growing numbers of medical digital images and the need to share them among specialists and hospitals for better and more accurate diagnosis require that patients’ privacy be protected. As a result of this, there is a need for medical image watermarking (MIW). However, MIW needs to be performed with special care for two reasons. Firstly, the watermarking procedure cannot compromise the quality of the image. Secondly, confidential patient information embedded within the image should be flawlessly retrievable without risk of error after image decompressing. Despite extensive research undertaken in this area, there is still no method available to fulfill all the requirements of MIW. This paper aims to provide a useful survey on watermarking and offer a clear perspective for interested researchers by analyzing the strengths and weaknesses of different existing methods.