Given a general digital shape of high-resolution, its analog perimeter of the pre-digitized shape (APPS) can be adequately estimated using the classic chain-code based methods. For a digital shape of low resolution, however, these methods may not provide accurate or consistent estimates due to the variations of APPS with shape orientations, which are inversely proportional to the digitization resolutions. Aiming at improving the accuracy and consistency in estimating APPS for low-resolution digital shapes, this paper presents a method to find the median values of digital perimeter curves (DPC) obtained from rotating the shapes. Examples are given to illustrate the proposed method.
A new method for estimating the analog surface area and the volume of a general 3D shape is presented. The proposed method takes advantage of known boundary estimation techniques for 2D shapes, which would eliminate most, if not all, of the complex interpolation procedures and estimation schemes employed by the conventional methods. After taking into consideration the variation of digital boundary with shape orientations, the estimated perimeters are used to measure the lateral area of the 3D shape through single integration. The same approach can be applied to estimating the volume of the 3D shape.
The shape classification methods derived from similarity measures based on the shape-transformation-variant descriptors often require shape normalization/standardization that involves complicated computations and contour or code matching schemes. In this paper, we introduce a quantitative similarity measure and a new model-based shape classification method which uses exclusively the shape-transformation-invariant descriptors. This method eliminates all possible variations and potential problems caused by shape transformation, and complicated contour matching and/or shape normalization/standardization procedures.
This paper first presents a new scientific accuracy measure (denoted by G) for assessing/evaluating the performance of computer medical diagnostic (CMD) systems by incorporating the true positives (TP), true negatives (TN), false positives (FP), and false negatives (FN) of human and computer's diagnoses with respect to each other. Based on G, a formula for computing a multi-parameter sensitivity vector S(G), with the assumption that the system parameter percentage variations are small, is then proposed. For a given set of parameter percentage errors, from the expression of S(G), we can compute the error bound of G and assess the reliability of the system with human and/or computer errors being taken into consideration. It has been demonstrated that the new measure G is capable of providing consistent performance evaluation of a CMD system in general. Based on the value of G, a CMD system can be classified as having 'good', 'fair', or 'poor' performance. Even though the proposed basic accuracy measure and its sensitivity study are derived based on the diagnosis using two diagnostic categories (positive and negative) compared by two observers (a human expert and a computer system), however, its methodology can be extended to CMD systems with multiple diagnostic categories and observers. The formulas for measuring the performance of such systems are discussed and present.
The purpose of this paper is to present a method for automatic detection of venous beadings in the spatial domain. The method consists of three steps: (1) creating an accurate vein map, (2) creating an accurate vein width map where the width of every vein indicated by a string of numbers, each of which indicates the width of the vein in pixels at that location, and (3) introducing an automatic venous beading detection algorithm. The parameters used in the beading detection algorithm include the widths of the veins at two adjacent local maxima and minima, the difference between the two widths, and the lengths of the broad and narrow sections. The ranges of the values of these parameters were obtained empirically. Standard Photographs 6B were used to test the algorithm and the result was quite satisfactory.
Unlike the existing automatic retinal blood vessel detection methods in which the vessels are detected by edge detection, thresholding or both (such as successive local probing) in the spatial domain, this paper presents a frequency-domain approach to the vessel detection problem. By having a frequency-domain analysis of the vessel signals, we found that the vessel signals between 0.1 and 0.25 on the normalized frequency scale showed a relatively high signal-to-noise ratio, and thus could be filtered out from the other image signals by using a band-pass filter. Instead of using a conventional digital filter, a band of Local-Mean-Interpolation (LMI) filters were employed. They provide not only the function of a band-pass filter that is needed, but also a number of desirable features from practical point of view, such as easy to implement, computationally fast, and high filtering performance. Twenty randomly selected color retinal images were used in testing the proposed method. The results showed that the vessel details could be successfully detected by this new method. When compared with the hand-labeled ground-truth segmentation and measured by the Figure of Merit (FOM = true positive/(1+false positive)), it was found that the method achieved an FOM of up to 0.79. As a final note, with some modifications, the method presented may be extended to the automatic detection of vessels (or other features/objects) in other 2D or 3D medical images, such as ultra-sound, CAT, MRI images.
Blood vessels in retinal images are often spread wildly across the image surface. By using this feature, this paper presents a novel approach for illumination normalization of retinal images. With the assumption that the reflectance of the vessels (including both major and small vessels) is a constant, it was found in our study that the illumination distribution of a retinal image can be estimated based on the locations of the vessel pixels and their intensity values. The procedures for estimating the illumination consists of two steps: (1) obtain the vessel map of the retinal image, and (2) estimate the illumination function (IF) of the image by interpolating the intensity values (luminance) of non-vessel pixels using a bicubic model function based on the locations of the vessel pixels and their intensity values. The illumination-normalized image can then be obtained by subtracting the original image from the estimated IF.20 non-uniformly illuminated sample retinal images that were tested using the proposed method. The results showed that the over-all standard deviation of the illumination for the image background reduced by 56.8% from 19.82 to 8.56, and the signal-to-noise ratio of the normalized images was greatly improved in the application of the global thresholding for image/region segmentation. Furthermore, when measured by the local luminosity histograms, the contrast of regions with low illumination containing features that are normally difficult to detect (such as small lesions and vessels) was also enhanced significantly. Therefore, it is concluded that the proposed method can be used to produce a desirable illumination- normalized image, from which region segmentation can be made easier and more accurate.
This paper presents a computer algorithm for automatic quantification of HMAs in a color retinal image. The algorithm begins with an image quality test. If the image is determined to be useful (normal), image processing and pattern recognition techniques are then applied. The image processing techniques employed are designed to achieve three purposes, image enhancement, noise removal, and most importantly, image normalization. It is followed by the detection of (1) optic disc and macula, (2) flame and blot hemorrhages, and (3) dot hemorrhages and microaneurysms. A special polar coordinate system centered at the macula is proposed. Such a coordinate system is particularly attractive in describing the location of a lesion relative to the center of the macula. In addition, it can be viewed as a 'spider net' and thus can be used to catch hemorrhages of large size, e.g., flame and blot hemorrhages, they way a spider net to catch insects. The spider net, however, will not work for the detection of microaneurysms and dot hemorrhages, because their sizes are too small to be caught by the net. A method specially designed for the detection of microaneurysms and dot hemorrhages is presented. It uses a sequence of seven automatically globally- thresholding binary images, obtained from the pre-processed normalized image, and a set of matched filters using only binary coefficients for differentiating HMAs and blood vessels. At the end, a computer printout of list of all the HMAs detected and their sizes and locations is given. Over four hundred color fundus photographs including standard fundus photographs are used to test the system. It should be pointed out that the sensitivity of this system can be adjusted by the user. By comparing the computer detected and quantified HMAs with the manual counts, it is found that the results are quite satisfactory. Therefore, we conclude that with the sensitivity of the system adjusted to human experts, this system can provide an automatic, objective, and repeatable way to quantify HMAs accurately.
This paper describes a method for machine (computer) assessment of the quality of a retinal image. The method provides an over-all quantitative and objective measure using a quality index Q. The Q of a retinal image is calculated by the convolution of a template intensity histogram obtained from a set of typically good retinal images and the intensity histogram of the retinal image. After normalization, the Q has a maximum value of 1, indicating excellent quality, and a minimum value of 0, indicating bad quality. The paper also presents several application examples of Q in image enhancement. It is shown that the use of Q can help computer scientists evaluate the suitability and effectiveness of image enhancement methods, both quantitatively and objectively. It can further help computer scientists improve retinal image quality on a more scientific basis. Additionally, this machine image quality measure can also help physicians make medical diagnosis with more certainty and higher accuracy. Finally, it should be noted that although retinal images are used in this study, the methodology is applicable to the image quality assessment and enhancement of other types of medical images.