After years of establishment of computed radiography (CR) and digital radiography (DR), manufacturers have introduced exposure indicator/index (EI) as a feedback mechanism for patient dose. However, EI consistency is uncertain for CR. Most manufacturers recommended EI values in a range of numbers for all examination, instead of giving the exact range for a specific body part, raising a concern of inappropriate exposure given to the patient in clinical practice. The aims of this study were to investigate the EI consistency in DR systems produced in constant exposure parameters and clinical condition, and to determine the interaction between the anatomical part and EI. A phantom study of skull, chest, abdomen and hand was carried out and four systems were used for comparison-Fuji CR, Carestream CR, Siemens DR and Carestream DR. For each projection, the phantom positioning and exposure parameters were set according to the standard clinical practice. All exposure parameters and clinical conditions were kept constant. Twenty (20) exposures were taken for each projection and the EI was recorded. Findings showed that EI is not consistent in DR systems despite constant exposure parameters and clinical condition except in Siemens DR, through skull examination. Statistical analysis showed a significant interaction between anatomical parts and EI values (P < 0.05). EI alone was proven to be less reliable to provide technologist a correct feedback on exposure level. The interaction between anatomical parts and EI values intensifies the need for an anatomical-specific EI values set by all manufacturers for accurate feedback on the exposure parameters used and the detector entrance dose.
The advent of multislice computed tomography (CT) has revolutionised the performance of body CT and allowed the development of CT angiography (CTA). CTA is a robust and minimally invasive method of visualizing the arterial vascular system. The newer generation of multidetector scans has allowed for shorter scanning times with no respiratory misregistration at peak vascular opacification following peripheral contrast injection. The volume of data obtained from these scans can be further manipulated to generate two-dimensional (2D) and three-dimensional (3D) images with no increase in radiation to the patient. Hence, CTA has gained popularity and importance as the alternative diagnostic tool especially for ill patients in which conventional angiography is inadvisable.We present an infant with coarctation of the aorta and hypoplastic aortic arch, in which CT angiography was used to pinpoint the diagnosis. The CT findings were subsequently confirmed at surgery.
The study aimed to investigate the effects of different tube potentials and concentrations of iodinated contrast media (CM) on the image enhancement, contrast-to-noise ratio (CNR) and noise in micro-computed tomography (µCT) images. A phantom containing of five polyethylene tube was filled with 2 mL of deionized water and iodinated CM (Omnipaque 300 mgI/mL) at four different concentrations: 5, 10, 15, and 20 mol/L, respectively. The phantom was scanned with a µCT machine (SkyScan 1176) using various tube potentials: 40, 50, 60, 70, 80, and 90 kVp, a fixed tube current; 100 µA, and filtration of 0.2 mm aluminum (Al). The percentage difference of image enhancement, CNR and noise of all images, acquired at different kVps and concentrations, were calculated. The image enhancement, CNR and noise curves with respect to tube potential and concentration were plotted and analysed. The highest image enhancement was found at the lowest tube potential of 40 kVp. At this kVp setting, the percentage difference of image enhancement [Hounsfield Unit (HU) of 20 mol/L iodine concentration over HU of deionized water] was 43%. By increasing the tube potential, it resulted with the reduction of HU, where only 17.5% different were noticed for 90 kVp. Across all iodine concentrations (5-20 M), CNR peaked at 80 kVp and then these values showed a slight decreasing pattern, which might be due insufficient tube current compensation. The percentage difference of image noise obtained at 40 and 90 kVp was 72.4%. Lower tube potential setting results in higher image enhancement (HU) in conjunction with increasing concentration of iodinated CM. Overall, the tube potential increment will substantially improve CNR and reduce image noise.
Cephalometric analyses using computer software have more advantages than manual analyses. However, the software should be evaluated for the accuracy and reproducibility before it can be used. The aims of the present study were: 1) to compare the differences in accuracy and precision between utilizing scanned images and soft copy images with the software 2) to assess the reproducibility of software and manual cephalometric analyses. Fifteen cephalograms were selected randomly from the Record Unit, Hospital Universiti Sains Malaysia. All films had 10 fiducial points marked and were scanned at 75 dots per inch (dpi) and 300 dpi. Manual and digital measurements were compared to obtain magnification factors. Seven digital x-ray images of a caliper were taken. The mean differences were measured between the fixed caliper measurement and digital measurements. Subsequently, 37 cephalograms were traced manually and digitally with Computer-Assisted Simulation System for Orthognathic Surgery (CASSOS) software to assess its accuracy and reproducibility after applying the obtained magnification factor. Steiner analysis was utilized and T tests were used to evaluate the mean difference. P
A critical step in detection of primary intracerebral haemorrhage (ICH) is an accurate assessment of computed tomography (CT) brain images. The correct diagnosis relies on imaging modality and quality of acquired images. The authors present an enhancement algorithm which can improve the clarity of edges on CT images. About 40 samples of CT brain images with final diagnosis of primary ICH were obtained from the UKM Medical Centre in Digital Imaging and Communication in Medicine format. The images resized from 512 × 512 to 256 × 256 pixel resolution to reduce processing time. This Letter comprises of two main sections; the first is denoising using Wiener filter, non-local means and wavelet; the second section focuses on image enhancement using a modified unsharp masking (UM) algorithm to improve the visualisation of ICH. The combined approach of Wiener filter and modified UM algorithm outperforms other combinations with average values of mean square error, peak signal-to-noise ratio, variance and structural similarity index of 2.89, 31.72, 0.12 and 0.98, respectively. The reliability of proposed algorithm was evaluated by three blinded assessors which achieved a median score of 65%. This approach provides reliable validation for the proposed algorithm which has potential in improving image analysis.
Different diseases are observed in vegetables, fruits, cereals, and commercial crops by farmers and agricultural experts. Nonetheless, this evaluation process is time-consuming, and initial symptoms are primarily visible at microscopic levels, limiting the possibility of an accurate diagnosis. This paper proposes an innovative method for identifying and classifying infected brinjal leaves using Deep Convolutional Neural Networks (DCNN) and Radial Basis Feed Forward Neural Networks (RBFNN). We collected 1100 images of brinjal leaf disease that were caused by five different species (Pseudomonas solanacearum, Cercospora solani, Alternaria melongenea, Pythium aphanidermatum, and Tobacco Mosaic Virus) and 400 images of healthy leaves from India's agricultural form. First, the original plant leaf is preprocessed by a Gaussian filter to reduce the noise and improve the quality of the image through image enhancement. A segmentation method based on expectation and maximization (EM) is then utilized to segment the leaf's-diseased regions. Next, the discrete Shearlet transform is used to extract the main features of the images such as texture, color, and structure, which are then merged to produce vectors. Lastly, DCNN and RBFNN are used to classify brinjal leaves based on their disease types. The DCNN achieved a mean accuracy of 93.30% (with fusion) and 76.70% (without fusion) compared to the RBFNN (82%-without fusion, 87%-with fusion) in classifying leaf diseases.
Realistic rendering techniques of outdoor Augmented Reality (AR) has been an attractive topic since the last two decades considering the sizeable amount of publications in computer graphics. Realistic virtual objects in outdoor rendering AR systems require sophisticated effects such as: shadows, daylight and interactions between sky colours and virtual as well as real objects. A few realistic rendering techniques have been designed to overcome this obstacle, most of which are related to non real-time rendering. However, the problem still remains, especially in outdoor rendering. This paper proposed a much newer, unique technique to achieve realistic real-time outdoor rendering, while taking into account the interaction between sky colours and objects in AR systems with respect to shadows in any specific location, date and time. This approach involves three main phases, which cover different outdoor AR rendering requirements. Firstly, sky colour was generated with respect to the position of the sun. Second step involves the shadow generation algorithm, Z-Partitioning: Gaussian and Fog Shadow Maps (Z-GaF Shadow Maps). Lastly, a technique to integrate sky colours and shadows through its effects on virtual objects in the AR system, is introduced. The experimental results reveal that the proposed technique has significantly improved the realism of real-time outdoor AR rendering, thus solving the problem of realistic AR systems.
Well-defined image can assist user to identify region of interest during segmentation. However, complex medical image is usually characterized by poor tissue contrast and low background luminance. The contrast improvement can lift image visual quality, but the fundamental contrast enhancement methods often overlook the sudden jump problem. In this work, the proposed bihistogram Bezier curve contrast enhancement introduces the concept of "adequate contrast enhancement" to overcome sudden jump problem in knee magnetic resonance image. Since every image produces its own intensity distribution, the adequate contrast enhancement checks on the image's maximum intensity distortion and uses intensity discrepancy reduction to generate Bezier transform curve. The proposed method improves tissue contrast and preserves pertinent knee features without compromising natural image appearance. Besides, statistical results from Fisher's Least Significant Difference test and the Duncan test have consistently indicated that the proposed method outperforms fundamental contrast enhancement methods to exalt image visual quality. As the study is limited to relatively small image database, future works will include a larger dataset with osteoarthritic images to assess the clinical effectiveness of the proposed method to facilitate the image inspection.
Despite the fact that the two texture descriptors, the completed modeling of Local Binary Pattern (CLBP) and the Completed Local Binary Count (CLBC), have achieved a remarkable accuracy for invariant rotation texture classification, they inherit some Local Binary Pattern (LBP) drawbacks. The LBP is sensitive to noise, and different patterns of LBP may be classified into the same class that reduces its discriminating property. Although, the Local Ternary Pattern (LTP) is proposed to be more robust to noise than LBP, however, the latter's weakness may appear with the LTP as well as with LBP. In this paper, a novel completed modeling of the Local Ternary Pattern (LTP) operator is proposed to overcome both LBP drawbacks, and an associated completed Local Ternary Pattern (CLTP) scheme is developed for rotation invariant texture classification. The experimental results using four different texture databases show that the proposed CLTP achieved an impressive classification accuracy as compared to the CLBP and CLBC descriptors.
The purpose of this study was to retrospectively evaluate the sensitivity, specificity and accuracy of identifying methamphetamine (MA) internal payloads in "drug mules" by plain abdominal digital radiography (DR).
The high variations of background luminance, low contrast and excessively enhanced contrast of hand bone radiograph often impede the bone age assessment rating system in evaluating the degree of epiphyseal plates and ossification centers development. The Global Histogram equalization (GHE) has been the most frequently adopted image contrast enhancement technique but the performance is not satisfying. A brightness and detail preserving histogram equalization method with good contrast enhancement effect has been a goal of much recent research in histogram equalization. Nevertheless, producing a well-balanced histogram equalized radiograph in terms of its brightness preservation, detail preservation and contrast enhancement is deemed to be a daunting task.
Standard X-ray images using conventional screen-film technique have a limited field of view that is insufficient to show the full bone structure of large hands on a single frame. To produce images containing the whole hand structure, digitized images from the X-ray films can be assembled using image stitching. This paper presents a new medical image stitching method that utilizes minimum average correlation energy filters to identify and merge pairs of hand X-ray medical images. The effectiveness of the proposed method is demonstrated in the experiments involving two databases which contain a total of 40 pairs of overlapping and non-overlapping hand images. The experimental results are compared with that of the normalized cross-correlation (NCC) method. It is found that the proposed method outperforms the NCC method in classifying and merging the overlapping and non-overlapping medical images. The efficacy of the proposed method is further indicated by its average execution time, which is about five times shorter than that of the other method.
This paper focuses on the detection of retinal blood vessels which play a vital role in reducing the proliferative diabetic retinopathy and for preventing the loss of visual capability. The proposed algorithm which takes advantage of the powerful preprocessing techniques such as the contrast enhancement and thresholding offers an automated segmentation procedure for retinal blood vessels. To evaluate the performance of the new algorithm, experiments are conducted on 40 images collected from DRIVE database. The results show that the proposed algorithm performs better than the other known algorithms in terms of accuracy. Furthermore, the proposed algorithm being simple and easy to implement, is best suited for fast processing applications.
The performance of a digital mammography system (Siemens Mammomat Novation) using different target/filter combinations and tube voltage has been assessed. The objective of this study is to optimize beam quality selection based on contrast-to-noise ratio (CNR) and mean glandular dose (MGD). Three composition of breast were studied with composition of glandular/adipose of 30/70, 50/50, and 70/30. CNR was measured using 2, 4 and 6 cm-thick simulated breast phantoms with an aluminium sheet of 0.1 mm thickness placed on top of the phantom. Three target/filter combinations, namely molybdenum/molybdenum (Mo/Mo), molybdenum/rhodium (Mo/Rh) and tungsten/rhodium (W/Rh) with various tube voltage and mAs were tested. MGD was measured for each exposure. For 50/50 breast composition, Mo/Rh combination with tube voltage 26 kVp is optimal for 2 cm-thick breast. W/Rh combination with tube voltage 27 and 28 kVp are optimal for 4 and 6 cm-thick breast, respectively. For both 30/70 and 70/30 breast composition, W/Rh combination is optimal with tube voltage 25, 26 and 27 kVp, respectively. From our study it was shown that there are potential of dose reduction up to 11% for a set CNR of 3.0 by using beam quality other than that are determined by AEC selection. Under the constraint of lowest MGD, for a particular breast composition, calcification detection is optimized by using a softer X-ray beam for thin breast and harder X-ray beam for thick breast. These experimental results also indicate that for breast with high fibroglandular tissues (70/30), the use of higher beam quality does not always increase calcification detection due to additional structured noise caused by the fibroglandular tissues itself.
This paper presents an approach for breast cancer diagnosis in digital mammogram using curvelet transform. After decomposing the mammogram images in curvelet basis, a special set of the biggest coefficients is extracted as feature vector. The Euclidean distance is then used to construct a supervised classifier. The experimental results gave a 98.59% classification accuracy rate, which indicate that curvelet transformation is a promising tool for analysis and classification of digital mammograms.
We present an efficient method for the fusion of medical captured images using different modalities that enhances the original images and combines the complementary information of the various modalities. The contourlet transform has mainly been employed as a fusion technique for images obtained from equal or different modalities. The limitation of directional information of dual-tree complex wavelet (DT-CWT) is rectified in dual-tree complex contourlet transform (DT-CCT) by incorporating directional filter banks (DFB) into the DT-CWT. The DT-CCT produces images with improved contours and textures, while the property of shift invariance is retained. To improve the fused image quality, we propose a new method for fusion rules based on principle component analysis (PCA) which depend on frequency component of DT-CCT coefficients (contourlet domain). For low frequency components, PCA method is adopted and for high frequency components, the salient features are picked up based on local energy. The final fusion image is obtained by directly applying inverse dual tree complex contourlet transform (IDT-CCT) to the fused low and high frequency components. The experimental results showed that the proposed method produces fixed image with extensive features on multimodality.
Information about retinal vasculature morphology is used in grading the severity and progression of diabetic retinopathy. An image analysis system can help ophthalmologists make accurate and efficient diagnoses. This paper presents the development of an image processing algorithm for detecting and reconstructing retinal vasculature. The detection of the vascular structure is achieved by image enhancement using contrast limited adaptive histogram equalization followed by the extraction of the vessels using bottom-hat morphological transformation. For reconstruction of the complete retinal vasculature, a region growing technique based on first-order Gaussian derivative is developed. The technique incorporates both gradient magnitude change and average intensity as the homogeneity criteria that enable the process to adapt to intensity changes and intensity spread over the vasculature region. The reconstruction technique reduces the required number of seeds to near optimal for the region growing process. It also overcomes poor performance of current seed-based methods, especially with low and inconsistent contrast images as normally seen in vasculature regions of fundus images. Simulations of the algorithm on 20 test images from the DRIVE database show that it outperforms many other published methods and achieved an accuracy range (ability to detect both vessel and non-vessel pixels) of 0.91 - 0.95, a sensitivity range (ability to detect vessel pixels) of 0.91 - 0.95 and a specificity range (ability to detect non-vessel pixels) of 0.88 - 0.94.
Legendre moments are continuous moments, hence, when applied to discrete-space images, numerical approximation is involved and error occurs. This paper proposes a method to compute the exact values of the moments by mathematically integrating the Legendre polynomials over the corresponding intervals of the image pixels. Experimental results show that the values obtained match those calculated theoretically, and the image reconstructed from these moments have lower error than that of the conventional methods for the same order. Although the same set of exact Legendre moments can be obtained indirectly from the set of geometric moments, the computation time taken is much longer than the proposed method.
The systematic monitoring of image quality and radiation dose is an ultimate solution to ensuring the continuously high quality of mammography examination. At present several protocols exist around the world, and different test objects are used for quality control (QC) of the physical and technical aspects of screen-film mammography. This situation may lead to differences in radiation image quality and dose reported. This article reviews the global QC perspective for the physical and technical aspects of screen-film mammography with regard to image quality and radiation dose. It points out issues that must be resolved in terms of radiation dose and that also affect the comparison.