Semiautomatic detection of scoliotic rib borders from posteroanterior chest radiographs

3-D assessment of scoliotic deformities relies on an accurate 3-D reconstruction of bone structures from biplanar X-rays, which requires a precise detection and matching of anatomical structures in both views. In this paper, we propose a novel semiautomated technique for detecting complete scoliotic rib borders from PA-0° and PA-20° chest radiographs, by using an edge-following approach with multiple-path branching and oriented filtering. Edge-following processes are initiated from user starting points along upper and lower rib edges and the final rib border is obtained by finding the most parallel pair among detected edges. The method is based on a perceptual analysis leading to the assumption that no matter how bent a scoliotic rib is, it will always present relatively parallel upper and lower edges. The proposed method was tested on 44 chest radiographs of scoliotic patients and was validated by comparing pixels from all detected rib borders against their reference locations taken from the associated manually delineated rib borders. The overall 2-D detection accuracy was 2.64 ± 1.21 pixels. Comparing this accuracy level to reported results in the literature shows that the proposed method is very well suited for precisely detecting borders of scoliotic ribs from PA-0° and PA-20° chest radiographs.     

Automatic detection of abnormalities in chest radiographs using local texture analysis

A fully automatic method is presented to detect abnormalities in frontal chest radiographs which are aggregated into an overall abnormality score. The method is aimed at finding abnormal signs of a diffuse textural nature, such as they are encountered in mass chest screening against tuberculosis (TB). The scheme starts with automatic segmentation of the lung fields, using active shape models. The segmentation is used to subdivide the lung fields into overlapping regions of various sizes. Texture features are extracted from each region, using the moments of responses to a multiscale filter bank. Additional "difference features" are obtained by subtracting feature vectors from corresponding regions in the left and right lung fields. A separate training set is constructed for each region. All regions are classified by voting among the k nearest neighbors, with leave-one-out. Next, the classification results of each region are combined, using a weighted multiplier in which regions with higher classification reliability weigh more heavily. This produces an abnormality score for each image. The method is evaluated on two databases. The first database was collected from a TB mass chest screening program, from which 147 images with textural abnormalities and 241 normal images were selected. Although this database contains many subtle abnormalities, the classification has a sensitivity of 0.86 at a specificity of 0.50 and an area under the receiver operating characteristic (ROC) curve of 0.820. The second database consist of 100 normal images and 100 abnormal images with interstitial disease. For this database, the results were a sensitivity of 0.97 at a specificity of 0.90 and an area under the ROC curve of 0.986.     

Automatic image hanging protocol for chest radiographs in PACS.

Chest radiography is one of the most widely used techniques in diagnostic imaging. It comprises at least one-third of all diagnostic radiographic procedures in hospitals. However, in the picture archive and communication system, images are often stored with the projection and orientation unknown or mislabeled, which causes inefficiency for radiologists' interpretation. To address this problem, an automatic hanging protocol for chest radiographs is presented. The method targets the most effective region in a chest radiograph, and extracts a set of size-, rotation-, and translation-invariant features from it. Then, a well-trained classifier is used to recognize the projection. The orientation of the radiograph is later identified by locating the neck, heart, and abdomen positions in the radiographs. Initial experiments are performed on the radiographs collected from daily routine chest exams in hospitals and show promising results. Using the presented protocol, 98.2% of all cases could be hung correctly on projection view (without protocol, 62%), and 96.1% had correct orientation (without protocol, 75%). A workflow study on the protocol also demonstrates a significant improvement in efficiency for image display.     

A fully automated method for lung nodule detection from postero-anterior chest radiographs

In the past decades, a great deal of research work has been devoted to the development of systems that could improve radiologists' accuracy in detecting lung nodules. Despite the great efforts, the problem is still open. In this paper, we present a fully automated system processing digital postero-anterior (PA) chest radiographs, that starts by producing an accurate segmentation of the lung field area. The segmented lung area includes even those parts of the lungs hidden behind the heart, the spine, and the diaphragm, which are usually excluded from the methods presented in the literature. This decision is motivated by the fact that lung nodules may be found also in these areas. The segmented area is processed with a simple multiscale method that enhances the visibility of the nodules, and an extraction scheme is then applied to select potential nodules. To reduce the high number of false positives extracted, cost-sensitive support vector machines (SVMs) are trained to recognize the true nodules. Different learning experiments were performed on two different data sets, created by means of feature selection, and employing Gaussian and polynomial SVMs trained with different parameters; the results are reported and compared. With the best SVM models, we obtain about 1.5 false positives per image (fp/image) when sensitivity is approximately equal to 0.71; this number increases to about 2.5 and 4 fp/image when sensitivity is = 0.78 and = 0.85, respectively. For the highest sensitivity (= 0.92 and 1.0), we get 7 or 8 fp/image.     

Enhancement of chest radiographs with gradient operators

Reference is made to the Sobel and Roberts gradient operators used to enhance image edges. Overall, the Sobel operator was found to be superior to the Roberts operator in edge enhancement. A theoretical explanation for the superior performance of the Sobel operator was developed based on the concept of analyzing the x and y Sobel masks as linear filters. By applying pill-box, Gaussian, or median filtering prior to applying a gradient operator, noise was reduced. The pill-box and Gaussian filters were more computationally efficient than the median filter with approximately equal effectiveness in noise reduction.     

Simultaneous detection of both coronary borders

A method for simultaneous detection of both coronary borders that is based on three-dimensional graph searching principles is presented. The simultaneous method and the authors' previously reported conventional method were applied to 29 coronary images, of which 19 were selected because conventional methods might be expected to have difficulty. Coronary borders identified by the two methods were visually compared. In the 19 difficult images, simultaneous border detection yielded superior results in 7 images and equivalent results in 12 images. Superior or equivalent results were obtained in the remaining 10 typical images. In a set of 43 uncomplicated images, minimal lumen diameters derived using simultaneous border detection correlated well with diameters derived using conventional border detection (r=0.97), diameters obtained from observer-defined borders (r=0.91), and diameters obtained using the Brown-Dodge quantitative coronary arteriography method (r=0.85). Thus simultaneous detection of left and right coronary borders provides improved accuracy in the detection of vessel borders in difficult coronary angiograms.     

Robust simultaneous detection of coronary borders in complex images

Visual estimation of coronary obstruction severity from angiograms suffers from poor inter- and intraobserver reproducibility and is often inaccurate. In spite of the widely recognized limitations of visual analysis, automated methods have not found widespread clinical use, in part because they too frequently fail to accurately identify vessel borders. The authors have developed a robust method for simultaneous detection of left and right coronary borders that is suitable for analysis of complex images with poor contrast, nearby or overlapping structures, or branching vessels. The reliability of the simultaneous border detection method and that of the authors' previously reported conventional border detection method were tested in 130 complex images, selected because conventional automated border detection might be expected to fail. Conventional analysis failed to yield acceptable borders in 65/130 or 50% of images. Simultaneous border detection was much more robust (p<.001) and failed in only 15/130 or 12% of complex images. Simultaneous border detection identified stenosis diameters that correlated significantly better with observer-derived stenosis diameters than did diameters obtained with conventional border detection (p<0.001), Simultaneous detection of left and right coronary borders is highly robust and has substantial promise for enhancing the utility of quantitative coronary angiography in the clinical setting.     

Enhancement of chest and breast radiographs by automatic spatial filtering

The authors present a new algorithm to enhance the edges and contrast of chest and breast radiographs while minimally amplifying image noise. The algorithm consists of a linear combination of an original image and two smoothed images obtained from it by using different masks and parameters, followed by the application of nonlinear contrast stretching. The result is an image which retains the high median frequency local variations (edge and contrast-enhancing).     

Fully automated lung segmentation from chest radiographs using SLICO superpixels

This project aims to create a computer-aided diagnosis (CAD) system that can be used to identify tuberculosis (TB) from chest radiographs (CXRs) and, in particular, to observe the progress of the disease where patients have had multiple images over a period of time. Such a CAD tool, if sufficiently automated could run in the background checking every CXR taken, regardless of whether the patient is a suspected carrier of TB. This paper outlines the first phase of the project: segmenting the lung region from a CXR. This is a challenge because of the variation in the appearance of the lung in different patients and even in images of the same patient.     

Segmentation of the posterior ribs in chest radiographs using iterated contextual pixel classification

The task of segmenting the posterior ribs within the lung fields of standard posteroanterior chest radiographs is considered. To this end, an iterative, pixel-based, supervised, statistical classification method is used, which is called iterated contextual pixel classification (ICPC). Starting from an initial rib segmentation obtained from pixel classification, ICPC updates it by reclassifying every pixel, based on the original features and, additionally, class label information of pixels in the neighborhood of the pixel to be reclassified. The method is evaluated on 30 radiographs taken from the JSRT (Japanese Society of Radiological Technology) database. All posterior ribs within the lung fields in these images have been traced manually by two observers. The first observer's segmentations are set as the gold standard; ICPC is trained using these segmentations. In a sixfold cross-validation experiment, ICPC achieves a classification accuracy of 0.86 +/- 0.06, as compared to 0.94 +/- 0.02 for the second human observer.     

Evaluation of digital unsharp masking and local contrast stretchingas applied to chest radiographs

The first six digital radiographs of the human chest generated by the Diode Array Digital Radiography scanner of the University of Pittsburg have been evaluated using a statistically designed experiment to study image-processing methods for displaying different anatomical landmarks. Linear and nonlinear unsharp masking and local contrast stretching were used. The experimental procedure, statistical analysis of the data obtained, and the results obtained are described and discussed     

Automatic anatomically selective image enhancement in digital chest radiography

A technique for automatic anatomically selective enhancement of digital chest radiographs is developed. Anatomically selective enhancement is motivated by the desire to simultaneously meet the different enhancement requirements of the lung field and the mediastinum. A recent peak detection algorithm and a set of rules are applied to the image histogram to determine automatically a gray-level threshold between the lung field and mediastinum. The gray-level threshold facilitates anatomically selective gray-scale modification and/or unsharp masking. Further, in an attempt to suppress possible white-band or black-band artifacts due to unsharp masking at sharp edges, local contrast adaptively is incorporated into anatomically selective unsharp masking by designing an anatomy-selective emphasis parameter which varies asymmetrically with positive and negative values of the local image contrast     

Automatic image orientation detection

We present an algorithm for automatic image orientation estimation using a Bayesian learning framework. We demonstrate that a small codebook (the optimal size of codebook is selected using a modified MDL criterion) extracted from a learning vector quantizer (LVQ) can be used to estimate the class-conditional densities of the observed features needed for the Bayesian methodology. We further show how principal component analysis (PCA) and linear discriminant analysis (LDA) can be used as a feature extraction mechanism to remove redundancies in the high-dimensional feature vectors used for classification. The proposed method is compared with four different commonly used classifiers, namely k-nearest neighbor, support vector machine (SVM), a mixture of Gaussians, and hierarchical discriminating regression (HDR) tree. Experiments on a database of 16 344 images have shown that our proposed algorithm achieves an accuracy of approximately 98% on the training set and over 97% on an independent test set. A slight improvement in classification accuracy is achieved by employing classifier combination techniques.     

恒电位仪自动测量的设计

采用了以MSP430单片机作为核心控制模块的方法,在恒电位仪手动测量基础上实现了自动测量和数据采集、接收及存储的目的。使得系统具备了小型、快速、低功耗等特点,方案设计中详细介绍了监测系统的设计原理和软硬件设计,并通过实验测量得到与腐蚀深度的相关电压、电流数据,同时指出了在实际应用中的方法以及改进措施。     

Automatic bifurcation detection in coronary IVUS sequences

In this paper, we present a fully automatic method which identifies every bifurcation in an intravascular ultrasound (IVUS) sequence, the corresponding frames, the angular orientation with respect to the IVUS acquisition, and the extension. This goal is reached using a two-level classification scheme: first, a classifier is applied to a set of textural features extracted from each image of a sequence. A comparison among three state-of-the-art discriminative classifiers (AdaBoost, random forest, and support vector machine) is performed to identify the most suitable method for the branching detection task. Second, the results are improved by exploiting contextual information using a multiscale stacked sequential learning scheme. The results are then successively refined using a-priori information about branching dimensions and geometry. The proposed approach provides a robust tool for the quick review of pullback sequences, facilitating the evaluation of the lesion at bifurcation sites. The proposed method reaches an F-Measure score of 86.35%, while the F-Measure scores for inter- and intraobserver variability are 71.63% and 76.18%, respectively. The obtained results are positive. Especially, considering the branching detection task is very challenging, due to high variability in bifurcation dimensions and appearance.     

Automatic license plate detection in hazardous condition

Automatic detection of license plate (LP) is to localize a license plate region from an image without human involvement. So far a number of methods have been introduced for automatic license plate detection (ALPD), but most of them do not consider various hazardous image conditions that exist in many real driving situations. Hazardous image condition means an image can have rainy or foggy weather effects, low contrast environments, objects similar to LP in the background, and horizontally tilted LP area. All these issues create challenges in developing effective ALPD method. In this paper, we propose a new ALPD method which effectively detects LP area from an image in the hazardous conditions. For rain removal we apply a novel method that uses frequency domain mask to filter rain streaks from an image. A new contrast enhancement method with a statistical binarization approach is introduced in the proposed ALPD for handling low contrast indoor, night, blurry and foggy images. For correcting tilted LP, we apply Radon transform based tilt correction method for the first time. To filter non-LP regions, a new condition is used which is based on image entropy. We test the proposed ALPD method on 850 car images having different hazardous conditions, and achieve satisfactory results in LP detection.     

Automatic detection of intraoperative neurological injury

Neurological injuries occurring during high-risk surgical procedures can be detected by monitoring intraoperative evoked potential signals. In this communication, an automatic injury detection algorithm is proposed in which the EP signal is modeled as a pole-zero filter and then the model parameters are applied as inputs to a classifier type neural network. A recognition rate of 96% is achieved using an experimental model of brain injury.     

Automatic detection of mass-resolved ion conics

A processing algorithm for automatically detecting a specific type of ion distribution (called the ion conic distribution) in data obtained from a space-based mass spectrometer has been devised. Automation of this task is necessary due to the sparseness of conic events within the very large databases typical of space plasma instruments. The algorithm used to perform this automated analysis and the methods used to verify the algorithm are described. Initial results on the characterization of the near-Earth space plasma are summarized     

Image-processing technique for suppressing ribs in chest radiographs by means of massive training artificial neural network (MTANN)

When lung nodules overlap with ribs or clavicles in chest radiographs, it can be difficult for radiologists as well as computer-aided diagnostic (CAD) schemes to detect these nodules. In this paper, we developed an image-processing technique for suppressing the contrast of ribs and clavicles in chest radiographs by means of a multiresolution massive training artificial neural network (MTANN). An MTANN is a highly nonlinear filter that can be trained by use of input chest radiographs and the corresponding "teaching" images. We employed "bone" images obtained by use of a dual-energy subtraction technique as the teaching images. For effective suppression of ribs having various spatial frequencies, we developed a multiresolution MTANN consisting of multiresolution decomposition/composition techniques and three MTANNs for three different-resolution images. After training with input chest radiographs and the corresponding dual-energy bone images, the multiresolution MTANN was able to provide "bone-image-like" images which were similar to the teaching bone images. By subtracting the bone-image-like images from the corresponding chest radiographs, we were able to produce "soft-tissue-image-like" images where ribs and clavicles were substantially suppressed. We used a validation test database consisting of 118 chest radiographs with pulmonary nodules and an independent test database consisting of 136 digitized screen-film chest radiographs with 136 solitary pulmonary nodules collected from 14 medical institutions in this study. When our technique was applied to nontraining chest radiographs, ribs and clavicles in the chest radiographs were suppressed substantially, while the visibility of nodules and lung vessels was maintained. Thus, our image-processing technique for rib suppression by means of a multiresolution MTANN would be potentially useful for radiologists as well as for CAD schemes in detection of lung nodules on chest radiographs.