Medical CT Images Research Articles

PDE based scheme for multi-modal medical image watermarking.

BackgroundThis work deals with copyright protection of digital images, an issue that needs protection of intellectual property rights. It is an important issue with a large number of medical images interchanged on the Internet every day. So, it is a challenging task to ensure the integrity of received images as well as authenticity. Digital watermarking techniques have been proposed as valid solution for this problem.MethodsIt is worth mentioning that the Region Of Interest (ROI)/Region Of Non Interest (RONI) selection can be seen as a significant limitation from which suffers most of ROI/RONI based watermarking schemes and that in turn affects and limit their applicability in an effective way. Generally, the ROI/RONI is defined by a radiologist or a computer-aided selection tool. And thus, this will not be efficient for an institute or health care system, where one has to process a large number of images. Therefore, developing an automatic ROI/RONI selection is a challenge task. The major aim of this work is to develop an automatic selection algorithm of embedding region based on the so called Partial Differential Equation (PDE) method. Thus avoiding ROI/RONI selection problems including: (1) computational overhead, (2) time consuming, and (3) modality dependent selection.ResultsThe algorithm is evaluated in terms of imperceptibility, robustness, tamper localization and recovery using MRI, Ultrasound, CT and X-ray grey scale medical images. From experimental results that we have conducted on a database of 100 medical images of four modalities, it can be inferred that our method can achieve high imperceptibility, while showing good robustness against attacks. Furthermore, the experiment results confirm the effectiveness of the proposed algorithm in detecting and recovering the various types of tampering. The highest PSNR value reached over the 100 images is 94,746 dB, while the lowest PSNR value is 60,1272 dB, which demonstrates the higher imperceptibility nature of the proposed method. Moreover, the Normalized Correlation (NC) between the original watermark and the corresponding extracted watermark for 100 images is computed. We get a NC value greater than or equal to 0.998. This indicates that the extracted watermark is very similar to the original watermark for all modalities.ConclusionThe key features of our proposed method are to (1) increase the robustness of the watermark against attacks; (2) provide more transparency to the embedded watermark. (3) provide more authenticity and integrity protection of the content of medical images. (4) provide minimum ROI/RONI selection complexity.

ZASTOSOWANIE METODY CHAN-VESE W SEGMENTACJI OBRAZÓW MEDYCZNYCH

The article presents the problem of determining the edges of objects enclosed in a medical CT images, which will be subject to further analysis, for the purpose of medical diagnosis. The use of a transformation which introduces two-point thresholding, eliminates presenting pixels of objects for tissues that are not a subject to further analysis. This approach allowed us to sharpen the edges of objects presenting soft tissue. A way to detect the edge of the soft tissue was compared for the original image and processed one using the transformation using the method of Chan-Vese. Sharpening of edges of the image have improved the accuracy of detection of objects presenting the soft tissue.

CT Medical Images Denoising Based on New Wavelet Thresholding Compared with Curvelet and Contourlet

CT Medical Images Denoising Based on New Wavelet Thresholding Compared with Curvelet and Contourlet

Implementation of Image Fusion Algorithms for Clinical Diagnosis

Image Fusion is a process of combining common features of a set of images to get an output image with superior content in terms of subjective as well as objective analysis point of view. Main aim of this work is to present a review on some of the Image Fusion Techniques. A comparison of all techniques are done fusing MRI and CT images and analysis is conducted using various quality measures such as entropy, MSE, PSNR, SSIM and BRISQUE. CT modalities provide information on denser tissues whereas MRI provides information on soft tissues. For medical applications CT and MRI images are fused for diagnostic purposes.

Nonsubsampled shearlet based CT and MR medical image fusion using biologically inspired spiking neural network

This paper presents a new fusion scheme for the CT and MR medical images that utilizes both the features of the nonsubsampled shearlet transform (NSST) and spiking neural network. As a new image representation with the different features, the NSST is utilized to provide an effective representation of the image coefficients. Firstly, the source CT and MR images are decomposed by the NSST into several subimages. The regional energy is used to fuse the low frequency coefficients. High frequency coefficients are also fused using a pulse coupled neural network model that is used as a biologically inspired type neural network. It also retains the edges and detail information from the source images. Finally, the inverse NSST is used to produce the fused image. The performance of the proposed fusion method is evaluated by conducting several experiments on the different CT and MR medical image datasets. Experimental results demonstrate that the proposed method does not only produce better results by successfully fusing the different CT and MR images, but also ensures an improvement in the various quantitative parameters as compared to other existing methods.

Low dose CT image restoration using a database of image patches

Reducing the radiation dose in CT imaging has become an active research topic and many solutions have been proposed to remove the significant noise and streak artifacts in the reconstructed images. Most of these methods operate within the domain of the image that is subject to restoration. This, however, poses limitations on the extent of filtering possible. We advocate to take into consideration the vast body of external knowledge that exists in the domain of already acquired medical CT images, since after all, this is what radiologists do when they examine these low quality images. We can incorporate this knowledge by creating a database of prior scans, either of the same patient or a diverse corpus of different patients, to assist in the restoration process. Our paper follows up on our previous work that used a database of images. Using images, however, is challenging since it requires tedious and error prone registration and alignment. Our new method eliminates these problems by storing a diverse set of small image patches in conjunction with a localized similarity matching scheme. We also empirically show that it is sufficient to store these patches without anatomical tags since their statistics are sufficiently strong to yield good similarity matches from the database and as a direct effect, produce image restorations of high quality. A final experiment demonstrates that our global database approach can recover image features that are difficult to preserve with conventional denoising approaches.

The Establishment of Three-Dimensional Model of Human Knee Joint

Objective: To discuss a method to establish a three-dimensional model of healthy human knee joint, which can be used for further knee joint biomechanics analysis and simulation. Methods: CT scan and medical image three-dimensional reconstruction software (Mimics) were used to obtain the knee joint three-dimensional finite element model (FEM) according to reverse engineering theory. Results: FEM of knee joint with complete bone structure was established by Mimics. Conclusion: Three-dimensional FEM was established according to CT images exports as IGES file. The model can be used for knee joint biomechanics finite element analysis to provide references and proposals for the clinical diagnoses of knee joint illness, and the design of artificial knee joint prosthesis.

Three-dimensional Representation of a Medical CT Image

Three-dimensional Representation of a Medical CT Image

OS0803-155 Damage Analysis of a Femur with Total Hip Arthroplasty by FEA with Use of Medical CT Images

In this study, a finite element model of a femur with a THA stem was developed using CT images of an old female patient. Damage analysis was then performed under different boundary conditions imitating different daily motions that may cause incident bone fracture. A damage theory was introduced to predict tensile and compressive fracture and also compressive yielding of elements. The FEA results exhibited that the Vancouver classification of bone fracture associated with THA can be predicted by CT-FEA with the damage theory.

Research on Image Technology with Application of K-Means Based on Genetic Simulated Annealing Algorithm in CT Image Segmentation

Aiming at the characteristic of medical images, this paper presents the improved genetic simulated annealing algorithm with K-means clustering analysis and applies in medical CT image segmentation. This improved genetic simulated annealing algorithm can be used to globally optimize k-means image segmentation functions to solve the locality and the sensitiveness of the initial condition. It can automatically adjust the parameters of genetic algorithm according to the fitness values of individuals and the decentralizing degree of individuals of the population and keep the variety of population for rapidly converging, and it can effectively avoid appearing precocity and plunging into local optimum. The example shows that the method is feasible, and better segmentation results have got to satisfy the request for 3D reconstruction, compared with k-means image segmentation and genetic algorithm based image segmentation.

Flow behaviour of supercritical CO2 and brine in Berea sandstone during drainage and imbibition revealed by medical X-ray CT images

Flow behaviour of supercritical CO2 and brine in Berea sandstone during drainage and imbibition revealed by medical X-ray CT images

Medical Image Retrieval Based on Shape Features in DCT Domain

Compressed medical images are widely used in clinical teaching and diagnosis. To save computing cost and storage spaces, research on compressed medical image retrieval is meaningful. This paper proposes a novel medical image retrieval scheme in DCT (Discrete Cosine Transformation) compressed domain. We firstly obtain the multi resolution image by reorganizing the DCT coefficients, then, segment the medical image’s ROI (Region of Interest) and acquires the shape binary image in DCT compressed domain. We use Hu invariant moments to extract shape feature vectors, and measure the similarity by weighting method. Experiments were carried out on an image database which contains 1000 medical CT images. The experimental results show that this algorithm can correctly extract shape features of ROI and get good retrieval performance on JPEG medical images. DOI : http://dx.doi.org/10.11591/telkomnika.v12i2.4413

A New Detail-Preserving Regularization Scheme

It is a challenging task to reconstruct images from their noisy, blurry, and/or incomplete measurements, especially those with important details and features such as medical magnetic resonance (MR) and CT images. We propose a novel regularization model that integrates two recently developed regularization tools: total generalized variation (TGV) by Bredies, Kunisch, and Pock; and shearlet transform by Labate, Lim, Kutyniok, and Weiss. The proposed model recovers both edges and fine details of images much better than the existing regularization models based on the total variation (TV) and wavelets. Specifically, while TV preserves sharp edges but suffers from oil painting artifacts, TGV “selectively regularizes” different image regions at different levels and thus largely avoids oil painting artifacts. Unlike the wavelet transform, which represents isotropic image features much more sparsely than anisotropic ones, the shearlet transform can efficiently represent anisotropic features such as edges, curves, ...

A priori knowledge and probability density based segmentation method for medical CT image sequences.

This paper briefly introduces a novel segmentation strategy for CT images sequences. As first step of our strategy, we extract a priori intensity statistical information from object region which is manually segmented by radiologists. Then we define a search scope for object and calculate probability density for each pixel in the scope using a voting mechanism. Moreover, we generate an optimal initial level set contour based on a priori shape of object of previous slice. Finally the modified distance regularity level set method utilizes boundaries feature and probability density to conform final object. The main contributions of this paper are as follows: a priori knowledge is effectively used to guide the determination of objects and a modified distance regularization level set method can accurately extract actual contour of object in a short time. The proposed method is compared to other seven state-of-the-art medical image segmentation methods on abdominal CT image sequences datasets. The evaluated results demonstrate our method performs better and has the potential for segmentation in CT image sequences.

Three-Dimensional Image Registration as a Tool for Forensic Odontology

Frequently, human dentition is utilized for victim identification. This report introduces a new human identification technique based on the principle of 3-dimensional (3D) image registration of the dentition. With the aid of a dry human skull, postmortem (PM) and antemortem (AM) scenarios were assumed. The skull in its initial state composed the PM scenario. Virtual 3D PM images were reconstructed from medical CT images. The AM scenario was achieved by reconstructing the missing hard and soft tissues of the skull by dental waxes. Virtual 3D AM images were obtained by laser surface scanning. The virtual PM and AM images were registered at 2 levels: arch level and tooth level. At arch level, the deviation between the 2 images was 0.147 mm for the maxilla and 0.166 mm for the mandible. At tooth level, the deviation average ranged from 0.077 to 0.237 mm. Qualitatively, even image fit was observed for the arches, intact teeth, and teeth with minimal deficiencies. As the tooth defect increased, the alignment discrepancy increased. It is concluded that 3D image registration ensured an accurate superimposition of the 3D images and can be used as a robust tool for forensic identification.

Optimization of K-Means Clustering Segmentation in Head CT Images

We optimized the k-clustering program with MATLAB language in order to improve the stability and quality of k-clustering algorithm in medical CT image segmentation. One hundred and sixty-five head nodule thoracic computed tomography scans are used to test the proposed method and compare with the k-means function of the MATLAB R2012a Statistics Toolbox. We analyzed the difference of the two kinds program running time using single factor variance analysis method and observed the stability and quality of the images segmentation. The experimental results show that the optimized k-means clustering algorithm programming has higher stability and quality of segmentation. In the environment of Windows operation system and hardware of personal computer configuration, the segmenting times are about only one second, significantly lower than the original segmentation procedures. These can eliminate the feeling of waiting and improve the users comfort and efficiency.

A New Contour Initialization of CT Image Sequences in GVF Model

In order to overcome the shortcomings that GVF model is susceptible to structures with slender topology, an improved watershed algorithm is proposed to determine initial contour of GVF Snake model. The organs in medical CT images often were irregular and had deep boundary concavities, and CT serial images were up to hundreds pieces. Firstly, in a CT image the improved watershed algorithm grows an organ from a seed block by the principle of the similarity between gray scale and texture, then using its edge as the start contour of the adjacent CT sequence, with GVF algorithm segment the organ from a sequence of images, the process is repeated until get all slices of the entire abdomen. Experiment results which are the basic of 3-D reconstruction and cancer detection show that the new contour initialization algorithm can obtain segmentation result efficiently, accurately and cost less time.

The Ontology-Based Medical CT Image Semantic Retrieval System

With the development of multimedia technology, the medical CT images become more important in the process of diagnostic cases, at the same time, how to retrieve the medical images that we need becomes more and more important. Usually, images could be got precisely but not intelligently using database. Therefore, this paper, taking advantages of both ontology and data structure of the medical image, introduces a semantic retrieval system programmed by Java and helps to achieve the intelligent retrieval of medical CT images and provides better reference pictures to the doctors.

Reversible and High-Capacity Data Hiding in High Quality Medical Images

Via the Internet, the information infrastructure of modern health care has already established medical information systems to share electronic health records among patients and health care providers. Data hiding plays an important role to protect medical images. Because modern medical devices have improved, high resolutions of medical images are provided to detect early diseases. The high quality medical images are used to recognize complicated anatomical structures such as soft tissues, muscles, and internal organs to support diagnosis of diseases. For instance, 16-bit depth medical images will provide 65,536 discrete levels to show more details of anatomical structures. In general, the feature of low utilization rate of intensity in 16-bit depth will be utilized to handle overflow/underflow problem. Nowadays, most of data hiding algorithms are still experimenting on 8-bit depth medical images. We proposed a novel reversible data hiding scheme testing on 16-bit depth CT and MRI medical image. And the peak point and zero point of a histogram are applied to embed secret message k bits without salt-and-pepper.

Segmentation of Medical Serial Images Based on K-means and GVF Model

The medical CT images are irregular and have deep boundary concavities. So how to get the organ picture from serial images quickly and accurately is a difficult process. The paper discusses the shortcoming of GVF model being sus- ceptible to structures with slender topology. For the better convergence we improve GVF model by setting the initial con- tour as the actual contour. The new algorithm combines k-means cluster with GVF model. Firstly, the target organ is ex- tracted from a CT slice through k-means cluster and morphological reconstruction, and then its edge is set as an initial contour of the adjacent CT sequence, finally, the organ is segmented from a sequence of images with GVF algorithm. The process is repeated until all slices from entire CT sequences are obtained. The new algorithm has higher segmentation ac- curacy and lower complexity.