Detecting bone lesions in X-ray under diverse acquisition conditions

Purpose

The diagnosis of primary bone tumors is challenging as the initial complaints are often non-specific. The early detection of bone cancer is crucial for a favorable prognosis. Incidentally, lesions may be found on radiographs obtained for other reasons. However, these early indications are often missed. We propose an automatic algorithm to detect bone lesions in conventional radiographs to facilitate early diagnosis. Detecting lesions in such radiographs is challenging. First, the prevalence of bone cancer is very low; any method must show high precision to avoid a prohibitive number of false alarms. Second, radiographs taken in health maintenance organizations (HMOs) or emergency departments (EDs) suffer from inherent diversity due to different X-ray machines, technicians, and imaging protocols. This diversity poses a major challenge to any automatic analysis method.

Approach

We propose training an off-the-shelf object detection algorithm to detect lesions in radiographs. The novelty of our approach stems from a dedicated preprocessing stage that directly addresses the diversity of the data. The preprocessing consists of self-supervised region-of-interest detection using vision transformer (ViT), and a foreground-based histogram equalization for contrast enhancement to relevant regions only.

Results

We evaluate our method via a retrospective study that analyzes bone tumors on radiographs acquired from January 2003 to December 2018 under diverse acquisition protocols. Our method obtains 82.43% sensitivity at a 1.5% false-positive rate and surpasses existing preprocessing methods. For lesion detection, our method achieves 82.5% accuracy and an IoU of 0.69.

Conclusions

The proposed preprocessing method enables effectively coping with the inherent diversity of radiographs acquired in HMOs and EDs.

An Image Histogram Equalization Acceleration Method for Field-Programmable Gate Arrays Based on a Two-Dimensional Configurable Pipeline

New artificial intelligence scenarios, such as high-precision online industrial detection, unmanned driving, etc., are constantly emerging and have resulted in an increasing demand for real-time image processing with high frame rates and low power consumption. Histogram equalization (HE) is a very effective and commonly used image preprocessing algorithm designed to improve the quality of image processing results. However, most existing HE acceleration methods, whether run on general-purpose CPUs or dedicated embedded systems, require further improvement in their frame rate to meet the needs of more complex scenarios. In this paper, we propose an HE acceleration method for FPGAs based on a two-dimensional configurable pipeline architecture. We first optimize the parallelizability of HE with a fully configurable two-dimensional pipeline architecture according to the principle of adapting the algorithm to the hardware, where one dimension can compute the cumulative histogram in parallel and the other dimension can process multiple inputs simultaneously. This optimization also helps in the construction of a simple architecture that achieves a higher frequency when implementing HE on FPGAs, which consist of configurable input units, calculation units, and output units. Finally, we optimize the pipeline and critical path of the calculation units. In the experiments, we deploy the optimized HE on a VCU118 test board and achieve a maximum frequency of 891 MHz (which is up to 22.6 times more acceleration than CPU implementations), as well as a frame rate of 1899 frames per second for 1080p images.

FPGA-Based Feature Extraction and Tracking Accelerator for Real-Time Visual SLAM

Due to its advantages of low latency, low power consumption, and high flexibility, FPGA-based acceleration technology has been more and more widely studied and applied in the field of computer vision in recent years. An FPGA-based feature extraction and tracking accelerator for real-time visual odometry (VO) and visual simultaneous localization and mapping (V-SLAM) is proposed, which can realize the complete acceleration processing capability of the image front-end. For the first time, we implement a hardware solution that combines features from accelerated segment test (FAST) feature points with Gunnar Farneback (GF) dense optical flow to achieve better feature tracking performance and provide more flexible technical route selection. In order to solve the scale invariance and rotation invariance lacking problems of FAST features, an efficient pyramid module with a five-layer thumbnail structure was designed and implemented. The accelerator was implemented on a modern Xilinx Zynq FPGA. The evaluation results showed that the accelerator could achieve stable tracking of features of violently shaking images and were consistent with the results from MATLAB code running on PCs. Compared to PC CPUs, which require seconds of processing time, the processing latency was greatly reduced to the order of milliseconds, making GF dense optical flow an efficient and practical technical solution on the edge side.

The Development of a Cost-Effective Imaging Device Based on Thermographic Technology

Thermal vision-based devices are nowadays used in a number of industries, ranging from the automotive industry, surveillance, navigation, fire detection, and rescue missions to precision agriculture. This work describes the development of a low-cost imaging device based on thermographic technology. The proposed device uses a miniature microbolometer module, a 32-bit ARM microcontroller, and a high-accuracy ambient temperature sensor. The developed device is capable of enhancing RAW high dynamic thermal readings obtained from the sensor using a computationally efficient image enhancement algorithm and presenting its visual result on the integrated OLED display. The choice of microcontroller, rather than the alternative System on Chip (SoC), offers almost instantaneous power uptime and extremely low power consumption while providing real-time imaging of an environment. The implemented image enhancement algorithm employs the modified histogram equalization, where the ambient temperature sensor helps the algorithm enhance both background objects near ambient temperature and foreground objects (humans, animals, and other heat sources) that actively emit heat. The proposed imaging device was evaluated on a number of environmental scenarios using standard no-reference image quality measures and comparisons against the existing state-of-the-art enhancement algorithms. Qualitative results obtained from the survey of 11 subjects are also provided. The quantitative evaluations show that, on average, images acquired by the developed camera provide better perception quality in 75% of tested cases. According to qualitative evaluations, images acquired by the developed camera provide better perception quality in 69% of tested cases. The obtained results verify the usability of the developed low-cost device for a range of applications where thermal imaging is needed.

Divisive normalization is an efficient code for multivariate Pareto-distributed environments

Divisive normalization is a canonical computation in the brain, observed across neural systems, that is often considered to be an implementation of the efficient coding principle. We provide a theoretical result that makes the conditions under which divisive normalization is an efficient code analytically precise: We show that, in a low-noise regime, encoding an n-dimensional stimulus via divisive normalization is efficient if and only if its prevalence in the environment is described by a multivariate Pareto distribution. We generalize this multivariate analog of histogram equalization to allow for arbitrary metabolic costs of the representation, and show how different assumptions on costs are associated with different shapes of the distributions that divisive normalization efficiently encodes. Our result suggests that divisive normalization may have evolved to efficiently represent stimuli with Pareto distributions. We demonstrate that this efficiently encoded distribution is consistent with stylized features of naturalistic stimulus distributions such as their characteristic conditional variance dependence, and we provide empirical evidence suggesting that it may capture the statistics of filter responses to naturalistic images. Our theoretical finding also yields empirically testable predictions across sensory domains on how the divisive normalization parameters should be tuned to features of the input distribution.

A Secure Artificial Intelligence-Enabled Critical Sars Crisis Management Using Random Sigmoidal Artificial Neural Networks

Since December 2019, the pandemic COVID-19 has been connected to the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). Early identification and diagnosis are essential goals for health practitioners because early symptoms correlate with those of other common illnesses including the common cold and flu. RT-PCR is frequently used to identify SARS-CoV-2 viral infection. Although this procedure can take up to 2 days to complete and sequential monitoring may be essential to figure out the potential of false-negative findings, RT-PCR test kits are apparently in low availability, highlighting the urgent need for more efficient methods of diagnosing COVID-19 patients. Artificial intelligence (AI)-based healthcare models are more effective at diagnosing and controlling large groups of people. Hence, this paper proposes a novel AI-enabled SARS detection framework. Here, the input CT images are collected and preprocessed using a block-matching filter and histogram equalization (HE). Segmentation is performed using Compact Entropy Rate Superpixel (CERS) technique. Features of segmented output are extracted using Histogram of Gradient (HOG). Feature selection is done using Principal Component Analysis (PCA). The suggested Random Sigmoidal Artificial Neural Networks (RS-ANN) based classification approach effectively diagnoses the existence of the disease. The performance of the suggested Artificial intelligence model is analyzed and related to existing approaches. The suggested AI system may help identify COVID-19 patients more quickly than conventional approaches.

Cranio-maxillofacial post-operative face prediction by deep spatial multiband VGG-NET CNN

Current plastic and reconstructive surgery computational techniques are not precise and take a long time to perform. Therefore, these limitations reduced the adoption of computational techniques. Although computer-aided surgical preparation systems may help to enhance clinical results, minimize operating time and costs, they are too complicated and require detailed manual information, which restricts their usage in doctor-patient communication and clinical decision-making. In order to obtain the optimal aesthetic and reconstruction treatment results, these techniques must be designed and implemented carefully. Computer-aided modeling, planning, and simulation techniques enable the preoperational evaluation of various therapeutic strategies based on the 3D patient models. We offer the new deep-learning architecture for diagnostics, risk stratification, and post-operative simulation for face prediction. Initially, preprocessing was done by using the weighted adaptive median filter and Laplacian partial differential equation-based histogram equalization. Then the target area was converted to 3D for clear visualization by using the Smart restorative frustum model. Finally, the post-operative face prediction was constructed by using the deep spatial Multiband VGG NET CNN. We obtained a face dataset of 313,318 CT and their clinical records from different centers. The algorithms were developed by 21,095 scans (Qure25k data set). In addition, CQ500 datasets from various centers were compiled in two batches, B1 and B2, to validate the algorithms clinically. Four hundred ninety-one scans used the CQ500 dataset. Initially, we reconstructed the input image and then devised the post-operative face computationally. The suggested deep spatial Multiband VGG NET CNN showed the high range of post-operative face prediction accuracy. Therefore, successful metrics such as the Jaccard and dice scores have shown accurate outcomes compared to other traditional methods. MATLAB was used to obtain the output of proposed work. With the help of the suggested classifier, the prediction accuracy was 93.7%, sensitivity was 99.9%, and specificity was 99.8%, all of which were higher than traditional approaches. Here, the suggested method provides better results for post-operative face prediction to the applied dataset than any other existing mechanisms. It is a generalized attempt that can apply to other similar datasets as well.

A Methodology for Extracting Power-Efficient and Contrast Enhanced RGB Images

Smart devices have become an integral part of people's lives. The most common activities for users of such smart devices that are energy sources are voice calls, text messages (SMS) or email, browsing the World Wide Web, streaming audio/video, and using sensor devices such as cameras, GPS, Wifi, 4G/5G, and Bluetooth either for entertainment or for the convenience of everyday life. In addition, other power sources are the device screen, RAM, and CPU. The need for communication, entertainment, and computing makes the optimal management of the power consumption of these devices crucial and necessary. In this paper, we employ a computationally efficient linear mapping algorithm known as Concurrent Brightness & Contrast Scaling (CBCS), which transforms the initial intensity value of the pixels in the YC_bC_r color system. We introduce a methodology that gives the user the opportunity to select a picture and modify it using the suggested algorithm in order to make it more energy-friendly with or without the application of a histogram equalization (HE). The experimental results verify the efficacy of the presented methodology through various metrics from the field of digital image processing that contribute to the choice of the optimal values for the parameters a,b that meet the user's preferences (low or high-contrast images) and green power. For both low-contrast and low-power images, the histogram equalization should be omitted, and the appropriate a should be much lower than one. To create high-contrast and low-power images, the application of HE is essential. Finally, quantitative and qualitative evaluations have shown that the proposed approach can achieve remarkable performance.

A New Photographic Reproduction Method Based on Feature Fusion and Virtual Combined Histogram Equalization

A desirable photographic reproduction method should have the ability to compress high-dynamic-range images to low-dynamic-range displays that faithfully preserve all visual information. However, during the compression process, most reproduction methods face challenges in striking a balance between maintaining global contrast and retaining majority of local details in a real-world scene. To address this problem, this study proposes a new photographic reproduction method that can smoothly take global and local features into account. First, a highlight/shadow region detection scheme is used to obtain prior information to generate a weight map. Second, a mutually hybrid histogram analysis is performed to extract global/local features in parallel. Third, we propose a feature fusion scheme to construct the virtual combined histogram, which is achieved by adaptively fusing global/local features through the use of Gaussian mixtures according to the weight map. Finally, the virtual combined histogram is used to formulate the pixel-wise mapping function. As both global and local features are simultaneously considered, the output image has a natural and visually pleasing appearance. The experimental results demonstrated the effectiveness of the proposed method and the superiority over other seven state-of-the-art methods.

Hue-Preserving Saturation Improvement in RGB Color Cube

This paper proposes a method for improving saturation in the context of hue-preserving color image enhancement. The proposed method handles colors in an RGB color space, which has the form of a cube, and enhances the contrast of a given image by histogram manipulation, such as histogram equalization and histogram specification, of the intensity image. Then, the color corresponding to a target intensity is determined in a hue-preserving manner, where a gamut problem should be taken into account. We first project any color onto a surface in the RGB color space, which bisects the RGB color cube, to increase the saturation without a gamut problem. Then, we adjust the intensity of the saturation-enhanced color to the target intensity given by the histogram manipulation. The experimental results demonstrate that the proposed method achieves higher saturation than that given by related methods for hue-preserving color image enhancement.

Photographic Reproduction and Enhancement Using HVS-Based Modified Histogram Equalization

Photographic reproduction and enhancement is challenging because it requires the preservation of all the visual information during the compression of the dynamic range of the input image. This paper presents a cascaded-architecture-type reproduction method that can simultaneously enhance local details and retain the naturalness of original global contrast. In the pre-processing stage, in addition to using a multiscale detail injection scheme to enhance the local details, the Stevens effect is considered for adapting different luminance levels and normally compressing the global feature. We propose a modified histogram equalization method in the reproduction stage, where individual histogram bin widths are first adjusted according to the property of overall image content. In addition, the human visual system (HVS) is considered so that a luminance-aware threshold can be used to control the maximum permissible width of each bin. Then, the global tone is modified by performing histogram equalization on the output modified histogram. Experimental results indicate that the proposed method can outperform the five state-of-the-art methods in terms of visual comparisons and several objective image quality evaluations.

Recognition of Heterogeneous Edges in Multiwavelength Transmission Images Based on the Weighted Constraint Decision Method

Multiwavelength light transmission imaging provides a possibility for early detection of breast cancer. However, due to strong scattering during the transmission process of breast tissue analysis, the transmitted image signal is weak and the image is blurred and this makes heterogeneous edge detection difficult. This paper proposes a method based on the weighted constraint decision (WCD) method to eliminate the erosion and checkerboard effects in image histogram equalization (HE) enhancement and to improve the recognition of heterogeneous edge. Multiwavelength transmission images of phantom are acquired on the designed experimental system and the mask image with high signal-to-noise ratio (SNR) is obtained by frame accumulation and an Otsu thresholding model. Then, during image enhancement the image is divided into low-gray-level (LGL) and high-gray-level (HGL) regions according to the distribution of light intensity in image. And the probability density distribution of gray level in the LGL and HGL regions are redefined respectively according to the WCD method. Finally, the reconstructed image is obtained based on the modified HE. The experimental results show that compared with traditional image enhancement methods, the WCD method proposed in this paper can greatly improve the contrast between heterogeneous region and normal region. Moreover, the correlation between the original image data is maintained to the greatest extent, so that the edge of the heterogeneity can be detected more accurately. In conclusion, the WCD method not only accurately identifies the edge of heterogeneity in multiwavelength transmission images, but it also could improve the clinical application of multiwavelength transmission images in the early detection of breast cancer.

Incremental Pose Map Optimization for Monocular Vision SLAM Based on Similarity Transformation

The novel contribution of this paper is to propose an incremental pose map optimization for monocular vision simultaneous localization and mapping (SLAM) based on similarity transformation, which can effectively solve the scale drift problem of SLAM for monocular vision and eliminate the cumulative error by global optimization. With the method of mixed inverse depth estimation based on a probability graph, the problem of the uncertainty of depth estimation is effectively solved and the robustness of depth estimation is improved. Firstly, this paper proposes a method combining the sparse direct method based on histogram equalization and the feature point method for front-end processing, and the mixed inverse depth estimation method based on a probability graph is used to estimate the depth information. Then, a bag-of-words model based on the mean initialization K-means is proposed for closed-loop feature detection. Finally, the incremental pose map optimization method based on similarity transformation is proposed to process the back end to optimize the pose and depth information of the camera. When the closed loop is detected, global optimization is carried out to effectively eliminate the cumulative error of the system. In this paper, indoor and outdoor environmental experiments are carried out using open data sets, such as TUM and KITTI, which fully proves the effectiveness of this method. Closed-loop detection experiments using hand-held cameras verify the importance of closed-loop detection. This method can effectively solve the scale drift problem of monocular vision SLAM and has strong robustness.

[Research on Improved Algorithm of DR Image Enhancement Based on Gauss-Laplacian Pyramid]

OBJECTIVE

In order to obtain more decision information from Digital Radiography(DR) images, an improved image enhancement algorithm is proposed based on the algorithm of Gauss-Laplacian pyramid.

METHODS

The original algorithm is improved on the basis of the human visual characteristics and better enhancements, the low frequency components of the image is histogram equalized to make the image gray scale more balanced, and the high frequency component is enhanced by a hierarchical exponential enhancement to make the details of the image clearer.

RESULTS

The improved algorithm improves the contrast of DR images in chest, pelvic and spine, and makes the image more layered and obtains good image enhancement effect.

CONCLUSIONS

The results show that the improved algorithm is superior to the traditional algorithm in terms of image enhancement.

A New Breast Border Extraction and Contrast Enhancement Technique with Digital Mammogram Images for Improved Detection of Breast Cancer

Purpose:

Breast cancer can be cured if diagnosed early, with digital mammography which is one of the most effective imaging modalities for early detection. However mammogram images often come with low contrast, high background noises and artifacts, making diagnosis difficult. The purpose of this research is to preprocess mammogram images to improve results with a computer aided diagnosis system. The focus is on three preprocessing methods: a breast border segmentation method; a contrast enhancement method; and a pectoral muscle removal method.

Methods:

The proposed breast border extraction method employs a threshold based segmentation technique along with a combination of morphological operations. The contrast enhancement method presented here is divided into two phages. In phase I, a bi-level histogram modification technique is applied to enhance the image globally and in phase II a non-linear filter based on local mean and local standard deviation for each pixel is applied to the histogram modified image. The pectoral muscle removal method discussed here is implemented by applying a region growing algorithm.

Results:

The proposed techniques are tested with the Mini MIAS dataset. The breast border extraction method is applied to 322 images and achieved 98.7% segmentation accuracy. The contrast enhancement method is evaluated based on quantitative measures like measure of enhancement, absolute mean brightness error, combined enhancement measure and discrete entropy. The proposed contrast enhancement method when applied to 14 images with different types of masses, the quantitative measures showed an optimum level of contrast enhancement compared to other enhancement methods with preservation of local detail. Removal of the pectoral muscle from MLO mammogram images reduced the search region while identifying abnormalities like masses and calcification.

Conclusions:

The preprocessing steps proposed here show promising results in terms of both qualitative and quantitative analysis.

Investigating the Role of Global Histogram Equalization Technique for 99mTechnetium-Methylene diphosphonate Bone Scan Image Enhancement

Purpose of the Study:

^99mTechnetium-methylene diphosphonate (^99mTc-MDP) bone scan images have limited number of counts per pixel, and hence, they have inferior image quality compared to X-rays. Theoretically, global histogram equalization (GHE) technique can improve the contrast of a given image though practical benefits of doing so have only limited acceptance. In this study, we have investigated the effect of GHE technique for ^99mTc-MDP-bone scan images.

Materials and Methods:

A set of 89 low contrast ^99mTc-MDP whole-body bone scan images were included in this study. These images were acquired with parallel hole collimation on Symbia E gamma camera. The images were then processed with histogram equalization technique. The image quality of input and processed images were reviewed by two nuclear medicine physicians on a 5-point scale where score of 1 is for very poor and 5 is for the best image quality. A statistical test was applied to find the significance of difference between the mean scores assigned to input and processed images.

Results:

This technique improves the contrast of the images; however, oversaturation was noticed in the processed images. Student's t-test was applied, and a statistically significant difference in the input and processed image quality was found at P < 0.001 (with α = 0.05). However, further improvement in image quality is needed as per requirements of nuclear medicine physicians.

Conclusion:

GHE techniques can be used on low contrast bone scan images. In some of the cases, a histogram equalization technique in combination with some other postprocessing technique is useful.

[Improved Algorithm of Histogram Equalization for Image Enhancement]

An improved algorithm of histogram equalization for image enhancement is discussed. After the image containing noises was wavelets transformed, the low frequency wavelet coefficients are equalized, and then all the wavelets are inverse transformed to enhance the image. This improved algorithm of histogram equalization gets a better image enhancement effect by test verification.

Brain early infarct detection using gamma correction extreme-level eliminating with weighting distribution

According to the statistic from World Health Organization (WHO), stroke is one of the major causes of death globally. Computed tomography (CT) scan is one of the main medical diagnosis system used for diagnosis of ischemic stroke. CT scan provides brain images in Digital Imaging and Communication in Medicine (DICOM) format. The presentation of CT brain images is mainly relied on the window setting (window center and window width), which converts an image from DICOM format into normal grayscale format. Nevertheless, the ordinary window parameter could not deliver a proper contrast on CT brain images for ischemic stroke detection. In this paper, a new proposed method namely gamma correction extreme-level eliminating with weighting distribution (GCELEWD) is implemented to improve the contrast on CT brain images. GCELEWD is capable of highlighting the hypodense region for diagnosis of ischemic stroke. The performance of this new proposed technique, GCELEWD, is compared with four of the existing contrast enhancement technique such as brightness preserving bi-histogram equalization (BBHE), dualistic sub-image histogram equalization (DSIHE), extreme-level eliminating histogram equalization (ELEHE), and adaptive gamma correction with weighting distribution (AGCWD). GCELEWD shows better visualization for ischemic stroke detection and higher values with image quality assessment (IQA) module. SCANNING 38:842-856, 2016. © 2016 Wiley Periodicals, Inc.

Receiver operating characteristic study of image preprocessing for teleradiology and digital workstations

The purpose of this study was to evaluate whether digitized analog images displayed on a digital workstation can be improved by using a preprocessing algorithm, and if so, whether the quality of the resulting images can reach that of the original films. The material contained 120 difficult cases (about 50% with selected pathology). Four radiologists each evaluated half of the randomly ordered cases with the digital workstation and half of the cases with the original radiographs. The data were compared with a previous similar study, where the workstation had no option for preprocessed images. Preprocessed digital images were clearly superior to digital images without preprocessing, although for those of the highest diagnostic difficulty they were inferior to the original films. The preprocessing algorithm has improved the diagnostic quality of the digital workstation. There is room yet for improvement compared to plain films, although the current setup may be sufficient in some settings.