A Novel Method for Correcting Non-uniform/Poor Illumination of Color Fundus Photographs

Retinal fundus images are often corrupted by non-uniform and/or poor illumination that occur due to overall imperfections in the image acquisition process. This unwanted variation in brightness limits the pathological information that can be gained from the image. Studies have shown that poor illumination can impede human grading in about 10~15% of retinal images. For automated grading, the effect can be even higher. In this perspective, we propose a novel method for illumination correction in the context of retinal imaging. The method splits the color image into luminosity and chroma (i.e., color) components and performs illumination correction in the luminosity channel based on a novel background estimation technique. Extensive subjective and objective experiments were conducted on publicly available DIARETDB1 and EyePACS images to justify the performance of the proposed method. The subjective experiment has confirmed that the proposed method does not create false color/artifacts and at the same time performs better than the traditional method in 84 out of 89 cases. The objective experiment shows an accuracy improvement of 4% in automated disease grading when illumination correction is performed by the proposed method than the traditional method.     

Quantification of the surface density of a fluorescent label with the optical microscope

Fluorescence microscopy can offer unique advantages for biomaterials characterization. Like spectroscopy or radioactivity, it can be used to quantify specific binding to surfaces, but it can also assess surface homogeneity at the micron scale or detect protein aggregation. To fully utilize the potential of this technique, there must be a way to calibrate the microscope in terms of the moles of a fluorophore per unit area. The method we propose involves the following steps: fluorescent labeling of erythrocytes and quantification of the label by flow cytometry; flattening of fluorescent erythrocytes for microscopic observation; imaging and digital analysis to relate the gray level intensities to the fluorophore density; and using this procedure to characterize a different, more easily obtainable, standard. The latter can be a 50% solution of Na fluorescein that yields a highly reproducible and uniform fluorescence. Concentrated fluorescein solution can also be used to correct images for the spatial nonuniformity of illumination and detection (shading correction). By applying this method to study the binding of IgG and fibrinogen to glass or amidated glass, we showed that protein adsorption to glass may result in protein aggregation that may affect the biological activity of the adsorbed protein.     

How to improve microscopic images obtained with consumer-type digital cameras

AIM: Digital imaging is useful in conventional photography because it immediately provides images, and the image quality can be improved afterwards by the use of computer programs. The major disadvantages of consumer-type digital cameras mounted on microscopes are (i) unequal illumination through the image, and (ii) a coloured background. A computer program was specifically adapted and refined to improve images obtained with consumer-type digital cameras mounted on microscopes. METHODS AND RESULTS: An approach using a division operation between the specimen image and a background image leads to homogeneous illumination throughout the image, with automatically corrected brightness and white background. The correct colour spectrum is preserved by correction of the histogram. This approach was obtained from the freeware computer program 'Image Arithmetic'. In a test, three different consumer-type digital cameras (Sony, Nikon, Olympus) on different microscopes were used to obtain images of different types of histological specimens (cervical smear, bone marrow biopsy, and colonic biopsy). The computer program dramatically improved the quality of images obtained with all tested cameras. CONCLUSION: Using this approach, even low-cost digital cameras mounted on microscopes produce brilliant images with homogeneous illumination and a white background, the image quality being comparable with expensive cameras especially designed for microscopes.     

Quantification of epithelial area by image processing applied to endometrial carcinomas: a comparison with ovarian tumors

In endometrial carcinomas, the epithelial area measured by interactive morphometry is an important feature in the classification of tumors of varying histologic grades. This report describes an image analysis technique for the fully automated estimation of the area percentages of epithelium and stroma in tissue sections of the endometrium obtained from hysterectomy specimens. The method is evaluated using endometrial carcinomas with varying degrees of malignancy. From standard paraffin sections stained with pararosanilin Feulgen and naphthol yellow, a blue-yellow image pair was recorded. The blue image was used to determine the total tissue area and the yellow image was used to determine the epithelial area. Image processing of the blue image was comprised of correction for shading, segmentation of the tissue area, and restoration of the segmented image by removing small artefacts and closing small tears in the tissue. Image processing of the yellow image was based on the fact that epithelial nuclei are generally more tightly packed than stromal nuclei and consists of the following steps: correction for shading, gaussian blurring, segmentation of nuclei, and editing the segmented image by removing small objects and closing small spaces between the epithelial nuclei. These image processing steps are compared with those used for quantification of the epithelial area in ovarian tumors. The performance of the method was evaluated using 120 image pairs from 30 endometrial carcinomas of varying histologic grades. The epithelial area percentages, as assessed by digital image processing, strongly correlate to control percentages that were established by interactive morphometry (r = .987).     

Digital image motion correction by spatial warp methods

A technique for correction of motion between images which are obtained in high-speed digital subtraction or cine angiographic acquisitions is being tested. The method is based on the application of quadratic polynomial equations which transform one image so that it matches a reference image. Images which have been processed in this manner can be summed to improve the signal-to-noise ratios over individual images. The technique for motion correction currently being tested uses operator interaction to establish the appropriate polynomial transformation. An operator selects fiducial (reference) points on an image which will be the reference. Then he selects the corresponding fiducial points on the image to be processed. The algorithm calculates the coefficients of a pair of quadratic polynomial equations and applies them to each pixel in the image. Results demonstrate the application of the technique in phantoms and in digitized cine angiograms.     

最小二乘法的未知控制点检测

背景：数字减影血管造影系统使用X射线影像增强器作为图像检测器,获取的投影图像与真实图像之间存在几何失真。 目的：为实现脑血管的三维重建,对数字减影血管造影图像的几何失真进行校正。 方法：基于数学形态学检测可视控制点,在此基础上采用最小二乘法曲线拟合进行非可视控制点检测,利用获取的672个控制点对原始图像进行非线性局部校正。 结果与结论：实验结果表明在边缘校正的结果较好,圆弧区域基本不失真。使用最小二乘法曲线拟合得到的控制点坐标准确性高,图像校正结果好,可用于脑血管数字减影血管造影图像的校正,为后续的三维重建提供保证。     

Prior image constrained scatter correction in cone-beam computed tomography image-guided radiation therapy

X-ray scatter is a significant problem in cone-beam computed tomography when thicker objects and larger cone angles are used, as scattered radiation can lead to reduced contrast and CT number inaccuracy. Advances have been made in x-ray computed tomography (CT) by incorporating a high quality prior image into the image reconstruction process. In this paper, we extend this idea to correct scatter-induced shading artifacts in cone-beam CT image-guided radiation therapy. Specifically, this paper presents a new scatter correction algorithm which uses a prior image with low scatter artifacts to reduce shading artifacts in cone-beam CT images acquired under conditions of high scatter. The proposed correction algorithm begins with an empirical hypothesis that the target image can be written as a weighted summation of a series of basis images that are generated by raising the raw cone-beam projection data to different powers, and then, reconstructing using the standard filtered backprojection algorithm. The weight for each basis image is calculated by minimizing the difference between the target image and the prior image. The performance of the scatter correction algorithm is qualitatively and quantitatively evaluated through phantom studies using a Varian 2100 EX System with an on-board imager. Results show that the proposed scatter correction algorithm using a prior image with low scatter artifacts can substantially mitigate scatter-induced shading artifacts in both full-fan and half-fan modes.     

Automated estimation of epithelial volume in breast cancer sections. A comparison with the image processing steps applied to gynecologic tumors.

The paper describes an image analysis technique for automated estimation of the epithelial percentage in standard paraffin tissue sections of invasive ductal breast cancers. Two staining procedures are evaluated: Feulgen (pararosanilin) and CAM 5.2-demonstrating the presence of cytokeratin 8 and 18-, both counterstained with naphthol yellow. In the technique, one image is recorded with a filter to visualize where the epithelium lies. This filter is chosen corresponding to the type of staining: it is yellow for Feulgen and blue for anti-cytokeratin CAM 5.2. To visualize where the stroma lies, the same image can be used for anti-cytokeratin CAM 5.2, whereas for Feulgen, a second image has to be recorded from the same microscope field with a blue filter. The image processing steps to determine the total tissue area comprise correction for shading, segmentation of the tissue area, and restoration of the segmented image by removal of small artefacts and closure of small tears in the tissue. The method for determination of the epithelial area consists of the following steps: correction for shading, gaussian blurring, segmentation of nuclei or epithelial cells, and editing of the segmented image by removal of small objects and closure of small spaces between the epithelial nuclei or cells. These image processing steps are compared to those for quantification of the epithelial percentage in gynecologic tumors of epithelial origin. For the Feulgen stain, the method is evaluated on 30 breast cancers of the ductal type (4 grade I, 12 grade II, and 14 grade III).(ABSTRACT TRUNCATED AT 250 WORDS)     

数字化X线成像系统的成像特性及其校正技术

随着一些新的Ｘ线图像处理方法的出现，对数字Ｘ互图像性能的要求将越来越高，本文从分析数字化Ｘ线成像系统的物理机制出发，提出了数字化Ｘ线成像系统的数学模型，并根据这一模型导出了Ｘ线成像的非线性规律及面不均匀性的规律，给出了对这些不利因素的校正方法，为进行数字Ｘ线图像的后续处理打下了坚实的基础。     

A New Method for Human Microcirculation Image Enhancement

Microcirculation images often have uneven illumination and low contrast in the acquisition process, which affect the image reorganization and following process. This paper presents a new method for microcireulatory image illumination correction and contrast enhancement based on the Contourlet transform. Initially, the image illumination model is extracted by Contourlet transform and then uneven illumination is corrected. Next, in order to restrain noise and enhance image contrast, the probability function associated with noise coefficient and edge coefficient is established and applied to all Contourlet coefficients. Then, a nonlinear enhancement function is applied to modified Contourlet coefficient to adaptively enhance image contrast. Finally, the enhanced image is obtained by inverse Contourlet transform. We compare this approach with other contrast enhancement methods, result showing that our method has a better effect than other enhancement methods, which might be helpful for clinical diagnostics of microcirculation.     

Analysis and correction of imperfections in the image intensifier-TV-digitizer imaging chain

Image intensifier-television-video digitizer (IITVD) systems are commonly used for digital planar image acquisition in radiology. However, the well-known distortions inherent in these systems limit their utility in research and in some clinical applications where quantitatively correct images are required. Software correction techniques have been implemented which restore both the spatial and grey scale quantitative integrity, allowing IITVD systems to be used as analytical research tools. Previously reported and novel correction techniques were used to reduce veiling glare, pincushion distortion, dc bias, and residual shading effects. The results indicate that excellent quantitative integrity can be achieved when these straightforward artifact reduction techniques are employed.     

Use of a digital film scanner to enhance low-power bright field photomicrography

 Low-power bright field photomicrographs often suffer from insufficient sharpness, uneven illumination, and colour hues. Using a film scanner, commercially available and designed for digitizing 35-mm transparencies, we directly scanned microscopic slides that carried dye-labelled and stained sections. The digital images covered a field of up to 24×36 mm and revealed excellent sharpness, absolutely even illumination and superior colour reproduction as compared to conventional photomicrographs taken with binoculars, macro lenses, or microscopes. As the method requires neither specialized instrumentation nor expert knowledge of photomicrographic techniques, it reduces costs and saves time. The high-quality digital survey micrographs can easily be used for image processing, image analysis and morphometry. Thus, this new method is valuable not only for pathology, embryology, histochemistry, and the neurosciences, but also for the exchange of low-power micrographs via the internet and for computer media that are increasingly used in medical education. Accepted: 17 April 1998     

An Unsupervised Approach for Extraction of Blood Vessels from Fundus Images

Pathological disorders may happen due to small changes in retinal blood vessels which may later turn into blindness. Hence, the accurate segmentation of blood vessels is becoming a challenging task for pathological analysis. This paper offers an unsupervised recursive method for extraction of blood vessels from ophthalmoscope images. First, a vessel-enhanced image is generated with the help of gamma correction and contrast-limited adaptive histogram equalization (CLAHE). Next, the vessels are extracted iteratively by applying an adaptive thresholding technique. At last, a final vessel segmented image is produced by applying a morphological cleaning operation. Evaluations are accompanied on the publicly available digital retinal images for vessel extraction (DRIVE) and Child Heart And Health Study in England (CHASE_DB1) databases using nine different measurements. The proposed method achieves average accuracies of 0.957 and 0.952 on DRIVE and CHASE_DB1 databases respectively.     

Scatter correction algorithm for digitally acquired radiographs: theory and results

A scatter correction algorithm for digitally acquired radiographs (SCADAR) is presented. SCADAR requires the acquisition of two digital images, taken at different object-to-detector distances. These two images are digitally magnification compensated, and subtracted. The primary component in the resulting difference image delta is mathematically eliminated, and hence the delta image is used as a measure of the local contribution of scattered radiation. A gray scale transformation is used to transform the delta image to a scattered component image, which is then smoothed by Fourier filtering, using a matched filter to increase the signal-to-noise ratio. The smoothed scatter image is then subtracted from its corresponding original image, resulting in the corrected SCADAR image. Implementation of SCADAR can result in a large increase in image contrast, and a significant reduction in shading due to scattered radiation effects. The mathematical derivation of the algorithm is developed, and experimental verification is given for some of the principles used. Using experimental images acquired from scattering phantoms, the results of SCADAR on various image parameters such as contrast and detail signal-to-noise ratio are discussed.     

The effect of the antiscatter grid on full-field digital mammography phantom images

Computer Analysis of Mammography Phantom Images (CAMPI) is a method for making quantitative measurements of image quality. This article reports on a recent application of this method to a prototype full-field digital mammography (FFDM) machine. Images of a modified ACR phantom were acquired on the General Electric Diagnostic Molybdenum Rhodium (GE-DMR) FFDM machine at a number of x-ray techniques, both with and without the scatter reduction grid. The techniques were chosen so that one had sets of grid and non-grid images with matched doses (200 mrads) and matched gray-scale values (1500). A third set was acquired at constant 26 kVp and varying mAs for both grid conditions. Analyses of the images yielded signal-to-noise-ratio (SNR), contrast and noise corresponding to each target object, and a non-uniformity measure. The results showed that under conditions of equal gray-scale value the grid images were markedly superior, albeit at higher doses than the non-grid images. Under constant dose conditions, the non-grid images were slightly superior in SNR (7%) but markedly less uniform (60%). Overall, the grid images had substantially greater contrast and superior image uniformity. These conclusions applied to the whole kVp range studied for the Mo-Mo target filter combination and 4 cm of breast equivalent material of average composition. These results suggest that use of the non-grid technique in digital mammography with the GE-DMR-FFDM unit, is presently not warranted. With improved uniformity correction procedure, this conclusion would change and one should be able to realize a 14% reduction in patient dose at the same SNR by using a non-grid technique.     

Content-based histopathology image retrieval using a kernel-based semantic annotation framework

Large amounts of histology images are captured and archived in pathology departments due to the ever expanding use of digital microscopy. The ability to manage and access these collections of digital images is regarded as a key component of next generation medical imaging systems. This paper addresses the problem of retrieving histopathology images from a large collection using an example image as query. The proposed approach automatically annotates the images in the collection, as well as the query images, with high-level semantic concepts. This semantic representation delivers an improved retrieval performance providing more meaningful results. We model the problem of automatic image annotation using kernel methods, resulting in a unified framework that includes: (1) multiple features for image representation, (2) a feature integration and selection mechanism (3) and an automatic semantic image annotation strategy. An extensive experimental evaluation demonstrated the effectiveness of the proposed framework to build meaningful image representations for learning and useful semantic annotations for image retrieval.     

Digital TV tomography: description and physical assessment

A digital TV tomography system, capable of retrospective reconstruction of multiple digital tomographic images, has been developed and its basic physical characteristics have been evaluated. The multiple tomographic images were formed through retrospective reconstruction of digital data acquired on a linear tomographic x-ray unit and an image intensifier-television system. Digital data were obtained with a series of 30 pulsed exposures during linear motion of the system. A distortion correction algorithm for the convex surface of the image intensifier was developed in order to reduce image distortion. A phantom study showed that the square-wave response at the fulcrum plane was slightly inferior to that in conventional tomography. There was also a slight decrease in the square-wave response away from the fulcrum plane and upon application of a correction algorithm, as compared with the response of the original reconstructed image at the fulcrum plane. The exposure dose for a single image was approximately half that in conventional tomography. Because of many advantages, including low exposure, short examination time, digital image manipulation, and applicability to picture archiving and communication systems, this is likely to become an important method in radiology when further technical refinements have been made.     

Image subtraction by solid state electroradiography

An analog radiographic image subtraction technique is presented. A selenium photoconductor is used as the radiation sensitive medium and image subtraction is achieved by electrostatically adding latent images of opposite polarities to get a latent image of the region of interest. In principle, the technique is simple and a comparison with commercial digital techniques shows a similar image quality, suggesting that the electrostatic subtraction technique could be developed into a clinical tool as an inexpensive alternative to digital radiography.     

Improved image quality in digital mammography with image processing

PURPOSE: The effect of image processing, specifically Bayesian image estimation (BIE), on digital mammographic images is studied. BIE is an iterative, nonlinear statistical estimation technique that has previously been used in chest radiography to reduce image scatter content and improve the contrast-to-noise ratio (CNR). We adapt this technique to digital mammography and examine its effect. METHODS/MATERIALS: Images of the American College of Radiologists (ACR) breast phantom were acquired on a calibrated digital mammography system at a normal mammographic exposure both with and without a grid. An iterative Bayesian estimation algorithm was formulated and used to process the images acquired without a grid. Quantitative scatter fractions were measured and compared for the image acquired with the grid, the image acquired without the grid, and the image acquired without the grid and processed by the Bayesian algorithm. CNR values were also computed for the four visible masses in the ACR phantom before and after processing and compared to a grid. RESULTS: Initial images acquired without an antiscatter grid had scatter fractions of 0.46. Processing this image with BIE reduced the scatter content to under 0.04. In comparison, the image acquired with a grid had scatter of 0.19. BIE processing accounted for CNR improvements from 29% to 219% for the masses seen in the ACR phantom as compared to the unprocessed image. Visibility of the four masses in the phantom was improved. CONCLUSIONS: Bayesian image estimation can be used with digital mammography to reduce scatter fractions. This technique is very useful as it can reduce scatter content effectively without introducing any adverse effects, such as grid line aliasing. Bayesian processing can also increase image CNR, which may potentially increase the visualization of subtle masses. Preliminary work shows an improvement in CNR to values greater than that provided by a standard grid.     

Fuzzy clustering-based segmented attenuation correction in whole-body PET imaging

Segmented attenuation correction is now a widely accepted technique to reduce noise propagation from transmission scanning in positron emission tomography (PET). In this paper, we present a new method for segmenting transmission images in whole-body scanning. This reduces the noise in the correction maps while still correcting for differing attenuation coefficients of specific tissues. Based on the fuzzy C-means (FCM) algorithm, the method segments the PET transmission images into a given number of clusters to extract specific areas of differing attenuation such as air, the lungs and soft tissue, preceded by a median filtering procedure. The reconstructed transmission image voxels are, therefore, segmented into populations of uniform attenuation based on knowledge of the human anatomy. The clustering procedure starts with an overspecified number of clusters followed by a merging process to group clusters with similar properties (redundant clusters) and removal of some undesired substructures using anatomical knowledge. The method is unsupervised, adaptive and allows the classification of both pre- or post-injection transmission images obtained using either coincident 68Ge or single-photon 137Cs sources into main tissue components in terms of attenuation coefficients. A high-quality transmission image of the scanner bed is obtained from a high statistics scan and added to the transmission image. The segmented transmission images are then forward projected to generate attenuation correction factors to be used for the reconstruction of the corresponding emission scan. The technique has been tested on a chest phantom simulating the lungs, heart cavity and the spine, the Rando-Alderson phantom, and whole-body clinical PET studies showing a remarkable improvement in image quality, a clear reduction of noise propagation from transmission into emission data allowing for reduction of transmission scan duration. There was very good correlation (R2 = 0.96) between maximum standardized uptake values (SUVs) in lung nodules measured on images reconstructed with measured and segmented attenuation correction with a statistically significant decrease in SUV (17.03% +/- 8.4%, P < 0.01) on the latter images, whereas no proof of statistically significant differences on the average SUVs was observed. Finally, the potential of the FCM algorithm as a segmentation method and its limitations as well as other prospective applications of the technique are discussed.