Automatic detection of abnormalities in chest radiographs using local texture analysis

Automatic screening for tuberculosis in chest radiographs: a survey

Tuberculosis (TB) is a major global health threat. An estimated one-third of the world's population has a history of TB infection, and millions of new infections are occurring every year. The advent of new powerful hardware and software techniques has triggered attempts to develop computer-aided diagnostic systems for TB detection in support of inexpensive mass screening in developing countries. In this paper, we describe the medical background of TB detection in chest X-rays and present a survey of the recent approaches using computer-aided detection. After a thorough research of the computer science literature for such systems or related methods, we were able to identify 16 papers, including our own, written between 1996 and early 2013. These papers show that TB screening is a challenging task and an open research problem. We report on the progress to date and describe experimental screening systems that have been developed.

Clavicle segmentation in chest radiographs

Automated delineation of anatomical structures in chest radiographs is difficult due to superimposition of multiple structures. In this work an automated technique to segment the clavicles in posterior-anterior chest radiographs is presented in which three methods are combined. Pixel classification is applied in two stages and separately for the interior, the border and the head of the clavicle. This is used as input for active shape model segmentation. Finally dynamic programming is employed with an optimized cost function that combines appearance information of the interior of the clavicle, the border, the head and shape information derived from the active shape model. The method is compared with a number of previously described methods and with independent human observers on a large database. This database contains both normal and abnormal images and will be made publicly available. The mean contour distance of the proposed method on 249 test images is 1.1±1.6mm and the intersection over union is 0.86±0.10.

Automated lung segmentation in digital chest tomosynthesis

PURPOSE

The purpose of this study was to develop an automated lung segmentation method for computerized detection of lung nodules in digital chest tomosynthesis.

METHODS

The authors collected 45 digital tomosynthesis scans and manually segmented reference lung regions in each scan to assess the performance of the method. The authors automated the technique by calculating the edge gradient in an original image for enhancing lung outline and transforming the edge gradient image to polar coordinate space. The authors then employed a dynamic programming technique to delineate outlines of the unobscured lungs in the transformed edge gradient image. The lung outlines were converted back to the original image to provide the final segmentation result. The above lung segmentation algorithm was first applied to the central reconstructed tomosynthesis slice because of the absence of ribs overlapping lung structures. The segmented lung in the central slice was then used to guide lung segmentation in noncentral slices. The authors evaluated the segmentation method by using (1) an overlap rate of lung regions, (2) a mean absolute distance (MAD) of lung borders, (3) a Hausdorff distance of lung borders between the automatically segmented lungs and manually segmented reference lungs, and (4) the fraction of nodules included in the automatically segmented lungs.

RESULTS

The segmentation method achieved mean overlap rates of 85.7%, 88.3%, and 87.0% for left lungs, right lungs, and entire lungs, respectively; mean MAD of 4.8, 3.9, and 4.4 mm for left lungs, right lungs, and entire lungs, respectively; and mean Hausdorrf distance of 25.0 mm, 25.5 mm, and 30.1 mm for left lungs, right lungs, and entire lungs, respectively. All of the nodules inside the reference lungs were correctly included in the segmented lungs obtained with the lung segmentation method.

CONCLUSIONS

The method achieved relatively high accuracy for lung segmentation and will be useful for computer-aided detection of lung nodules in digital tomosynthesis.

Sparseness of the trabecular pattern on dental radiographs: visual assessment compared with semi-automated measurements

OBJECTIVE

In diagnostic imaging; human perception is the most prominent, yet least studied, source of error. A better understanding of image perception will help to improve diagnostic performance. This study focuses on the perception of coarseness of trabecular patterns on dental radiographs. Comparison of human vision with machine vision should yield knowledge on human perception.

METHOD

In a study on identifying osteoporotic patients, dental radiographs were made from 505 post-menopausal women aged 45-70 years. Intra-oral radiographs of the lower and upper jaws were made. Five observers graded the trabecular pattern as dense, sparse or mixed. The five gradings were combined into a single averaged observer score per jaw. The radiographs were scanned and a region of interest (ROI) was indicated on each. The ROIs were processed with image analysis software measuring 25 image features. Pearson correlation and multiple linear regression were used to compare the averaged observer score with the image features.

RESULTS

14 image features correlated significantly with the observer judgement for both jaws. The strongest correlation was found for the average grey value in the ROI. Other features, describing that osteoporotic patients have fewer but bigger marrow spaces than controls, correlated less with the sparseness of the trabecular pattern than a rather crude measure for structure such as the average grey value.

CONCLUSION

Human perception of the sparseness of trabecular patterns is based more on average grey values of the ROI than on geometric details within the ROI.

Detecting tuberculosis in radiographs using combined lung masks

Tuberculosis (TB) is a major health threat in many regions of the world, while diagnosing tuberculosis still remains a challenge. Mortality rates of patients with undiagnosed TB are high. Modern diagnostic techniques are often too slow or too expensive for highly-populated developing countries that bear the brunt of the disease. In an effort to reduce the burden of the disease, this paper presents an automated approach for detecting TB on conventional posteroanterior chest radiographs. The idea is to provide developing countries, which have limited access to radiological services and radiological expertise, with an inexpensive detection system that allows screening of large parts of the population in rural areas. In this paper, we present results produced by our TB screening system. We combine a lung shape model, a segmentation mask, and a simple intensity model to achieve a better segmentation mask for the lung. With the improved masks, we achieve an area under the ROC curve of more than 83%, measured on data compiled within a tuberculosis control program.

A computerized method for automated identification of erect posteroanterior and supine anteroposterior chest radiographs

A computerized scheme was developed for automated identification of erect posteroanterior (PA) and supine anteroposterior (AP) chest radiographs. The method was based on three features, the tilt angle of the scapula superior border, the tilt angle of the clavicle and the extent of radiolucence in lung fields, to identify the view of a chest radiograph. The three indices A(scapula), A(clavicle) and C(lung) were determined from a chest image for the three features. Linear discriminant analysis was used to classify PA and AP chest images based on the three indices. The performance of the method was evaluated by receiver operating characteristic analysis. The proposed method was evaluated using a database of 600 PA and 600 AP chest radiographs. The discriminant performances Az of A(scapula), A(clavicle) and C(lung) were 0.878 ± 0.010, 0.683 ± 0.015 and 0.962 ± 0.006, respectively. The combination of the three indices obtained an Az value of 0.979 ± 0.004. The results indicate that the combination of the three indices could yield high discriminant performance. The proposed method could provide radiologists with information about the view of chest radiographs for interpretation or could be used as a preprocessing step for analyzing chest images.

Computer-assisted detection of infectious lung diseases: a review

Respiratory tract infections are a leading cause of death and disability worldwide. Although radiology serves as a primary diagnostic method for assessing respiratory tract infections, visual analysis of chest radiographs and computed tomography (CT) scans is restricted by low specificity for causal infectious organisms and a limited capacity to assess severity and predict patient outcomes. These limitations suggest that computer-assisted detection (CAD) could make a valuable contribution to the management of respiratory tract infections by assisting in the early recognition of pulmonary parenchymal lesions, providing quantitative measures of disease severity and assessing the response to therapy. In this paper, we review the most common radiographic and CT features of respiratory tract infections, discuss the challenges of defining and measuring these disorders with CAD, and propose some strategies to address these challenges.

An automatic computer-aided detection scheme for pneumoconiosis on digital chest radiographs

This paper presents an automatic computer-aided detection scheme on digital chest radiographs to detect pneumoconiosis. Firstly, the lung fields are segmented from a digital chest X-ray image by using the active shape model method. Then, the lung fields are subdivided into six non-overlapping regions, according to Chinese diagnosis criteria of pneumoconiosis. The multi-scale difference filter bank is applied to the chest image to enhance the details of the small opacities, and the texture features are calculated from each region of the original and the processed images, respectively. After extracting the most relevant ones from the feature sets, support vector machine classifiers are utilized to separate the samples into the normal and the abnormal sets. Finally, the final classification is performed by the chest-based report-out and the classification probability values of six regions. Experiments are conducted on randomly selected images from our chest database. Both the training and the testing sets have 300 normal and 125 pneumoconiosis cases. In the training phase, training models and weighting factors for each region are derived. We evaluate the scheme using the full feature vectors or the selected feature vectors of the testing set. The results show that the classification performances are high. Compared with the previous methods, our fully automated scheme has a higher accuracy and a more convenient interaction. The scheme is very helpful to mass screening of pneumoconiosis in clinic.

Biplane correlation imaging: a feasibility study based on phantom and human data

The objective of this study was to implement and evaluate the performance of a biplane correlation imaging (BCI) technique aimed to reduce the effect of anatomic noise and improve the detection of lung nodules in chest radiographs. Seventy-one low-dose posterior-anterior images were acquired from an anthropomorphic chest phantom with 0.28° angular separations over a range of ±10° along the vertical axis within an 11 s interval. Similar data were acquired from 19 human subjects with institutional review board approval and informed consent. The data were incorporated into a computer-aided detection (CAD) algorithm in which suspect lesions were identified by examining the geometrical correlation of the detected signals that remained relatively constant against variable anatomic backgrounds. The data were analyzed to determine the effect of angular separation, and the overall sensitivity and false-positives for lung nodule detection. The best performance was achieved for angular separations of the projection pairs greater than 5°. Within that range, the technique provided an order of magnitude decrease in the number of false-positive reports when compared with CAD analysis of single-view images. Overall, the technique yielded ~1.1 false-positive per patient with an average sensitivity of 75%. The results indicated that the incorporation of angular information can offer a reduction in the number of false-positives without a notable reduction in sensitivity. The findings suggest that the BCI technique has the potential for clinical implementation as a cost-effective technique to improve the detection of subtle lung nodules with lowered rate of false-positives.

Multiple kernel learning for classification of diffuse lung disease using HRCT lung images

A novel algorithm is presented for classification of four patterns of diffuse lung disease: normal, emphysema, honeycombing and ground glass opacity, on the basis of textural analysis of high resolution computed tomography (HRCT) lung images. The algorithm incorporates scale-space features based on Gaussian derivative filters and multi-dimensional multi-scale features based on wavelet and contourlet transforms of the original images. The mean, standard deviation, skewness and kurtosis along with generalized Gaussian density are used to model the output of filters and transforms, and construct feature vectors. Multi-class multiple kernel learning (m-MKL) classifier is used to evaluate the performance of the feature extraction scheme. The method is tested on a collection of 89 slices from 38 patients, each slice of size 512×512, 16 bits/pixel in DICOM format. The dataset contains 70,000 ROIs from slices already marked by experienced radiologists. The average sensitivity and specificity achieved is 94.16% and 98.68%, respectively.

Applying a statistical PTB detection procedure to complement the gold standard

This paper investigates a novel statistical discrimination procedure to detect PTB when the gold standard requirement is taken into consideration. Archived data were used to establish two groups of patients which are the control and test group. The control group was used to develop the statistical discrimination procedure using four vectors of wavelet coefficients as feature vectors for the detection of pulmonary tuberculosis (PTB), lung cancer (LC), and normal lung (NL). This discrimination procedure was investigated using the test group where the number of sputum positive and sputum negative cases that were correctly classified as PTB cases were noted. The proposed statistical discrimination method is able to detect PTB patients and LC with high true positive fraction. The method is also able to detect PTB patients that are sputum negative and therefore may be used as a complement to the gold standard.

Image analysis for classification of dysplasia in Barrett's esophagus using endoscopic optical coherence tomography

Barrett's esophagus (BE) and associated adenocarcinoma have emerged as a major health care problem. Endoscopic optical coherence tomography is a microscopic sub-surface imaging technology that has been shown to differentiate tissue layers of the gastrointestinal wall and identify dysplasia in the mucosa, and is proposed as a surveillance tool to aid in management of BE. In this work a computer-aided diagnosis (CAD) system has been demonstrated for classification of dysplasia in Barrett's esophagus using EOCT. The system is composed of four modules: region of interest segmentation, dysplasia-related image feature extraction, feature selection, and site classification and validation. Multiple feature extraction and classification methods were evaluated and the process of developing the CAD system is described in detail. Use of multiple EOCT images to classify a single site was also investigated. A total of 96 EOCT image-biopsy pairs (63 non-dysplastic, 26 low-grade and 7 high-grade dysplastic biopsy sites) from a previously described clinical study were analyzed using the CAD system, yielding an accuracy of 84% for classification of non-dysplastic vs. dysplastic BE tissue. The results motivate continued development of CAD to potentially enable EOCT surveillance of large surface areas of Barrett's mucosa to identify dysplasia.

A hybrid knowledge-guided detection technique for screening of infectious pulmonary tuberculosis from chest radiographs

Tuberculosis (TB) is a deadly infectious disease and the presence of cavities in the upper lung zones is a strong indicator that the disease has developed into a highly infectious state. Currently, the detection of TB cavities is mainly conducted by clinicians observing chest radiographs. Diagnoses performed by radiologists are labor intensive and very often there is insufficient healthcare personnel available, especially in remote communities. After assessing existing approaches, we propose an automated segmentation technique which takes a hybrid knowledge-based Bayesian classification approach to detect TB cavities automatically. We apply gradient inverse coefficient of variation (GICOV) and circularity measures to classify detected features and confirm true TB cavities. By comparing with non hybrid approaches and the classical active contour techniques for feature extraction in medical images, experimental results demonstrate that our approach achieves high accuracy with a low false positive rate in detecting TB cavities.

Global and local multi-valued dissimilarity-based classification: application to computer-aided detection of tuberculosis

In many applications of computer-aided detection (CAD) it is not possible to precisely localize lesions or affected areas in images that are known to be abnormal. In this paper a novel approach to computer-aided detection is presented that can deal effectively with such weakly labeled data. Our approach is based on multi-valued dissimilarity measures that retain more information about underlying local image features than single-valued dissimilarities. We show how this approach can be extended by applying it locally as well as globally, and by merging the local and global classification results into an overall opinion about the image to be classified. The framework is applied to the detection of tuberculosis (TB) in chest radiographs. This is the first study to apply a CAD system to a large database of digital chest radiographs obtained from a TB screening program, including normal cases, suspect cases and cases with proven TB. The global dissimilarity approach achieved an area under the ROC curve of 0.81. The combination of local and global classifications increased this value to 0.83.

Image dissimilarity-based quantification of lung disease from CT

In this paper, we propose to classify medical images using dissimilarities computed between collections of regions of interest. The images are mapped into a dissimilarity space using an image dissimilarity measure, and a standard vector space-based classifier is applied in this space. The classification output of this approach can be used in computer aided-diagnosis problems where the goal is to detect the presence of abnormal regions or to quantify the extent or severity of abnormalities in these regions. The proposed approach is applied to quantify chronic obstructive pulmonary disease in computed tomography (CT) images, achieving an area under the receiver operating characteristic curve of 0.817. This is significantly better compared to combining individual region classifications into an overall image classification, and compared to common computerized quantitative measures in pulmonary CT.

Toward precise pulmonary nodule descriptors for nodule type classification

A framework for nodule feature-based extraction is presented to classify lung nodules in low-dose CT slices (LDCT) into four categories: juxta, well-circumscribed, vascularized and pleural-tail, based on the extracted information. The Scale Invariant Feature Transform (SIFT) and an adaptation to Daugman's Iris Recognition algorithm are used for analysis. The SIFT descriptor results are projected to lower-dimensional subspaces using PCA and LDA. Complex Gabor wavelet nodule response obtained from an adopted Daugman Iris Recognition algorithm revealed improvements from the original Daugman binary iris code. This showed that binarized nodule responses (codes) are inadequate for classification since nodules lack texture concentration as seen in the iris, while the SIFT algorithm projected using PCA showed robustness and precision in classification.

Computer-aided detection of pulmonary pathology in pediatric chest radiographs

A scheme for triaging pulmonary abnormalities in pediatric chest radiographs for specialist interpretation would be useful in resource-poor settings, especially those with a high tuberculosis burden. We assess computer-aided detection of pulmonary pathology in pediatric digital chest X-ray images. The method comprises four phases suggested in the literature: lung field segmentation, lung field subdivision, feature extraction and classification. The output of the system is a probability map for each image, giving an indication of the degree of abnormality of every region in the lung fields; the maps may be used as a visual tool for identifying those cases that need further attention. The system is evaluated on a set of anterior-posterior chest images obtained using a linear slot-scanning digital X-ray machine. The classification results produced an area under the ROC of 0.782, averaged over all regions.

Computerized detection of diffuse lung disease in MDCT: the usefulness of statistical texture features

Accurate detection of diffuse lung disease is an important step for computerized diagnosis and quantification of this disease. It is also a difficult clinical task for radiologists. We developed a computerized scheme to assist radiologists in the detection of diffuse lung disease in multi-detector computed tomography (CT). Two radiologists selected 31 normal and 37 abnormal CT scans with ground glass opacity, reticular, honeycombing and nodular disease patterns based on clinical reports. The abnormal cases in our database must contain at least an abnormal area with a severity of moderate or severe level that was subjectively rated by the radiologists. Because statistical texture features may lack the power to distinguish a nodular pattern from a normal pattern, the abnormal cases that contain only a nodular pattern were excluded. The areas that included specific abnormal patterns in the selected CT images were then delineated as reference standards by an expert chest radiologist. The lungs were first segmented in each slice by use of a thresholding technique, and then divided into contiguous volumes of interest (VOIs) with a 64 x 64 x 64 matrix size. For each VOI, we determined and employed statistical texture features, such as run-length and co-occurrence matrix features, to distinguish abnormal from normal lung parenchyma. In particular, we developed new run-length texture features with clear physical meanings to considerably improve the accuracy of our detection scheme. A quadratic classifier was employed for distinguishing between normal and abnormal VOIs by the use of a leave-one-case-out validation scheme. A rule-based criterion was employed to further determine whether a case was normal or abnormal. We investigated the impact of new and conventional texture features, VOI size and the dimensionality for regions of interest on detecting diffuse lung disease. When we employed new texture features for 3D VOIs of 64 x 64 x 64 voxels, our system achieved the highest performance level: a sensitivity of 86% and a specificity of 90% for the detection of abnormal VOIs, and a sensitivity of 89% and a specificity of 90% for the detection of abnormal cases. Our computerized scheme would be useful for assisting radiologists in the diagnosis of diffuse lung disease.

Computer-aided diagnosis in chest radiography: beyond nodules

Chest radiographs are the most common exam in radiology. They are essential for the management of various diseases associated with high mortality and morbidity and display a wide range of findings, many of them subtle. In this survey we identify a number of areas beyond pulmonary nodules that could benefit from computer-aided detection and diagnosis (CAD) in chest radiography. These include interstitial infiltrates, catheter tip detection, size measurements, detection of pneumothorax and detection and quantification of emphysema. Recent work in these areas is surveyed, but we conclude that the amount of research devoted to these topics is modest. Reasons for the slow pace of CAD development in chest radiography beyond nodules are discussed.

Investigation of breast cancer using two-dimensional MRS

Proton (1H) MRS enables non-invasive biochemical assay with the potential to characterize malignant, benign and healthy breast tissues. In vitro studies using perchloric acid extracts and ex vivo magic angle spinning spectroscopy of intact biopsy tissues have been used to identify detectable metabolic alterations in breast cancer. The challenges of 1H MRS in vivo include low sensitivity and significant overlap of resonances due to limited chemical shift dispersion and significant inhomogeneous broadening at most clinical magnetic field strengths. Improvement in spectral resolution can be achieved in vivo and in vitro by recording the MR spectra spread over more than one dimension, thus facilitating unambiguous assignment of metabolite and lipid resonances in breast cancer. This article reviews the recent progress with two-dimensional MRS of breast cancer in vitro, ex vivo and in vivo. The discussion includes unambiguous detection of saturated and unsaturated fatty acids, as well as choline-containing groups such as free choline, phosphocholine, glycerophosphocholine and ethanolamines using two-dimensional MRS. In addition, characterization of invasive ductal carcinomas and healthy fatty/glandular breast tissues non-invasively using the classification and regression tree (CART) analysis of two-dimensional MRS data is reviewed.

Computer-aided detection of interstitial abnormalities in chest radiographs using a reference standard based on computed tomography

A computer-aided detection (CAD) system is presented for the localization of interstitial lesions in chest radiographs. The system analyzes the complete lung fields using a two-class supervised pattern classification approach to distinguish between normal texture and texture affected by interstitial lung disease. Analysis is done pixel-wise and produces a probability map for an image where each pixel in the lung fields is assigned a probability of being abnormal. Interstitial lesions are often subtle and ill defined on x-rays and hence difficult to detect, even for expert radiologists. Therefore a new, semiautomatic method is proposed for setting a reference standard for training and evaluating the CAD system. The proposed method employs the fact that interstitial lesions are more distinct on a computed tomography (CT) scan than on a radiograph. Lesion outlines, manually drawn on coronal slices of a CT scan of the same patient, are automatically transformed to corresponding outlines on the chest x-ray, using manually indicated correspondences for a small set of anatomical landmarks. For the texture analysis, local structures are described by means of the multiscale Gaussian filter bank. The system performance is evaluated with ROC analysis on a database of digital chest radiographs containing 44 abnormal and 8 normal cases. The best performance is achieved for the linear discriminant and support vector machine classifiers, with an area under the ROC curve (A(z)) of 0.78. Separate ROC curves are built for classification of abnormalities of different degrees of subtlety versus normal class. Here the best performance in terms of A(z) is 0.90 for differentiation between obviously abnormal and normal pixels. The system is compared with two human observers, an expert chest radiologist and a chest radiologist in training, on evaluation of regions. Each lung field is divided in four regions, and the reference standard and the probability maps are converted into region scores. The system performance does not significantly differ from that of the observers, when the perihilar regions are excluded from evaluation, and reaches A(z) = 0.85 for the system, with A(z) = 0.88 for both observers.

Minimal shape and intensity cost path segmentation

A new generic model-based segmentation algorithm is presented, which can be trained from examples akin to the active shape model (ASM) approach in order to acquire knowledge about the shape to be segmented and about the gray-level appearance of the object in the image. Whereas ASM alternates between shape and intensity information during search, the proposed approach optimizes for shape and intensity characteristics simultaneously. Local gray-level appearance information at the landmark points extracted from feature images is used to automatically detect a number of plausible candidate locations for each landmark. The shape information is described by multiple landmark-specific statistical models that capture local dependencies between adjacent landmarks on the shape. The shape and intensity models are combined in a single cost function that is optimized noniteratively using dynamic programming, without the need for initialization. The algorithm was validated for segmentation of anatomical structures in chest and hand radiographs. In each experiment, the presented method had a significant higher performance when compared to the ASM schemes. As the method is highly effective, optimally suited for pathological cases and easy to implement, it is highly useful for many medical image segmentation tasks.

Improvement of lung abnormality detection in computed radiography using multi-objective frequency processing: Evaluation by receiver operating characteristics (ROC) analysis

Computed radiography (CR) has been shown to have relatively low sensitivity for detection of pulmonary nodules. This poor sensitivity precludes its use as a screening modality despite the low cost, low dose and wide distribution of devices. The purpose of this study was to apply multi-objective frequency processing (MFP) to CR images and to evaluate its usefulness for diagnosing subtle lung abnormalities. Fifty CR images with simulated subtle lung abnormalities were obtained from 50 volunteers. Each image was processed with MFP. We cut chest images. The chest image was divided into two rights and left. A total of 200 half-chest images (100 MFP-processed images and 100 MFP-unprocessed images) were prepared. Five radiologists participated in this study. ROC analyses demonstrated that the detection rate of simulated subtle lung abnormalities on the CR images was significantly better with MFP (Az=0.8508) than without MFP (Az=0.7925). The CR images processed with MFP could be useful for diagnosing subtle lung abnormalities. In conclusion, MFP appears to be useful for increasing the sensitivity and specificity in the detection of pulmonary nodules, ground-glass opacity (GGO) and reticular shadow.

Computer-aided diagnosis in chest radiography

We have developed computer-aided diagnosis (CAD) schemes for the detection of lung nodules, interstitial lung diseases, interval changes, and asymmetric opacities, and also for the differential diagnosis of lung nodules and interstitial lung diseases on chest radiographs. Observer performance studies indicate clearly that radiologists' diagnostic accuracy was improved significantly when radiologists used a computer output in their interpretations of chest radiographs. In addition, the automated recognition methods for the patient and the projection view by use of chest radiographs were useful for integrating the chest CAD schemes into the picture-archiving and communication system (PACS).

Recent Advances in Chest Radiography

There have been many remarkable advances in conventional thoracic imaging over the past decade. Perhaps the most remarkable is the rapid conversion from film-based to digital radiographic systems. Computed radiography is now the preferred imaging modality for bedside chest imaging. Direct radiography is rapidly replacing film-based chest units for in-department posteroanterior and lateral examinations. An exciting aspect of the conversion to digital radiography is the ability to enhance the diagnostic capabilities and influence of chest radiography. Opportunities for direct computer-aided detection of various lesions may enhance the radiologist's accuracy and improve efficiency. Newer techniques such as dual-energy and temporal subtraction radiography show promise for improved detection of subtle and often obscured or overlooked lung lesions. Digital tomosynthesis is a particularly promising technique that allows reconstruction of multisection images from a short acquisition at very low patient dose. Preliminary data suggest that, compared with conventional radiography, tomosynthesis may also improve detection of subtle lung lesions. The ultimate influence of these new technologies will, of course, depend on the outcome of rigorous scientific validation.

A KNOWLEDGE-BASED LUNG NODULE DETECTION SYSTEM FOR HELICAL CT IMAGES

In this paper, we describe a knowledge-based system for segmenting and labeling lung nodule on helical CT images. The system was developed under a blackboard environment that incorporates a lung knowledge model, image processing model, inference engine and a blackboard. Lung model, which contains both analogical and propositional knowledge about lung in the form of semantic networks, was used to guide the interpretation process. The system works in a hierarchical structure, from large structures to the final nodule candidates by focusing on the interested region step by step. The symbolic variables, introduced to accomplish high-level inference, were defined by fuzzy confidence functions in the lung model. Composite fuzzy functions were applied to evaluate the plausibility of the mapping between the image and lung model objects. Anatomical lung segments knowledge was embedded in the system to direct 3D validation of suspicious objects. Structures were identified and abnormal objects were reported. The experimental results obtained demonstrate the proof of concept and the potential of the automated knowledge-based lung nodule detection system.

Segmentation of anatomical structures in chest radiographs using supervised methods: a comparative study on a public database

The task of segmenting the lung fields, the heart, and the clavicles in standard posterior-anterior chest radiographs is considered. Three supervised segmentation methods are compared: active shape models, active appearance models and a multi-resolution pixel classification method that employs a multi-scale filter bank of Gaussian derivatives and a k-nearest-neighbors classifier. The methods have been tested on a publicly available database of 247 chest radiographs, in which all objects have been manually segmented by two human observers. A parameter optimization for active shape models is presented, and it is shown that this optimization improves performance significantly. It is demonstrated that the standard active appearance model scheme performs poorly, but large improvements can be obtained by including areas outside the objects into the model. For lung field segmentation, all methods perform well, with pixel classification giving the best results: a paired t-test showed no significant performance difference between pixel classification and an independent human observer. For heart segmentation, all methods perform comparably, but significantly worse than a human observer. Clavicle segmentation is a hard problem for all methods; best results are obtained with active shape models, but human performance is substantially better. In addition, several hybrid systems are investigated. For heart segmentation, where the separate systems perform comparably, significantly better performance can be obtained by combining the results with majority voting. As an application, the cardio-thoracic ratio is computed automatically from the segmentation results. Bland and Altman plots indicate that all methods perform well when compared to the gold standard, with confidence intervals from pixel classification and active appearance modeling very close to those of a human observer. All results, including the manual segmentations, have been made publicly available to facilitate future comparative studies.

Projection profile analysis for automated detection of abnormalities in chest radiographs

Abnormalities in chest images often present as abnormal opacity or abnormal asymmetry. We have developed a novel method for automated detection of abnormalities in chest radiographs by use of these features. Our method is based on an analysis of the projection profile obtained by projecting the pixels data of a frontal chest image on to the mediolateral axis. Two indices, lung opacity index and lung symmetry index, are computed from the projection profile. Lung opacity index and lung symmetry index are then combined to detect gross abnormalities in chest radiographs. The values of lung opacity index are found to be 0.38 +/- 0.05 and 0.37 +/- 0.06 for normal right and left lung, respectively. The values of lung symmetry index are found to be 0.018 +/- 0.014 for normal chest images. The discrimination for the combination of the two indices is evaluated by linear discriminant analysis and receiver operating characteristic (ROC) analysis. Area Az under the ROC curve with the combination of the two indices in the classification of normal and abnormal chest images is 0.963.

RR, Trad CS. Caracterização de lesões intersticiais de pulmão em radiograma de tórax utilizando análise local de textura

OBJETIVO: Caracterizar lesões intersticiais em radiografias frontais de tórax, com base na análise de atributos estatísticos de textura, os quais permitem detectar sinais de anormalidades com natureza difusa. MATERIAIS E MÉTODOS: O esquema começa com a segmentação semi-automática dos campos pulmonares, sendo o contorno externo marcado manualmente, com posterior divisão automática de cada pulmão em seis regiões. O banco de imagens utilizado neste trabalho é composto por 482 regiões obtidas de exames contendo lesões e 324 regiões obtidas de exames normais. Os atributos de textura são extraídos automaticamente de cada uma dessas regiões e uma seleção das melhores combinações de atributos é feita através da distância Jeffries-Matusita. A classificação das regiões em normal ou suspeita é feita pela comparação com os k vizinhos mais próximos e o treinamento do classificador é baseado na técnica de treino e teste "half-half" e correlação cruzada. RESULTADOS: Os resultados obtidos foram analisados através do valor da área sob a curva ROC ("receiver operating characteristic"), a qual indica um sistema perfeito para uma área igual a 1. Os resultados forneceram uma área sob a curva ROC (A Z) igual a 0,887, com valores de sensibilidade igual a 0,804 e especificidade igual a 0,793. CONCLUSÃO: Os resultados indicam que o sistema de caracterização baseado em atributos de textura possui bom potencial para o auxílio ao diagnóstico de lesões intersticiais de pulmão.

A computer-aided diagnosis system for detection of lung nodules in chest radiographs with an evaluation on a public database

A computer algorithm for nodule detection in chest radiographs is presented. The algorithm consists of four main steps: (i) image preprocessing; (ii) nodule candidate detection; (iii) feature extraction; (iv) candidate classification. Two optional extensions to this scheme are tested: candidate selection and candidate segmentation. The output of step (ii) is a list of circles, which can be transformed into more detailed contours by the extra candidate segmentation step. In addition, the candidate selection step (which is a classification step using a small number of features) can be used to reduce the list of nodule candidates before step (iii). The algorithm uses multi-scale techniques in several stages of the scheme: Candidates are found by looking for local intensity maxima in Gaussian scale space; nodule boundaries are detected by tracing edge points found at large scales down to pixel scale; some of the features used for classification are taken from a multi-scale Gaussian filterbank. Experiments with this scheme (with and without the segmentation and selection steps) are carried out on a previously characterized, publicly available database, that contains a large number of very subtle nodules. For this database, counting as detections only those nodules that were indicated with a confidence level of 50% or more, radiologists previously detected 70% of the nodules. For our algorithm, it turns out that the selection step does have an added value for the system, while segmentation does not lead to a clear improvement. With the scheme with the best performance, accepting on average two false positives per image results in the identification of 51% of all nodules. For four false positives, this increases to 67%. This is close to the previously reported 70% detection rate of the radiologists.

Non-rigid image registration using a statistical spline deformation model

We propose a statistical spline deformation model (SSDM) as a method to solve non-rigid image registration. Within this model, the deformation is expressed using a statistically trained B-spline deformation mesh. The model is trained by principal component analysis of a training set. This approach allows to reduce the number of degrees of freedom needed for non-rigid registration by only retaining the most significant modes of variation observed in the training set. User-defined transformation components, like affine modes, are merged with the principal components into a unified framework. Optimization proceeds along the transformation components rather then along the individual spline coefficients. The concept of SSDM's is applied to the temporal registration of thorax CR-images using pattern intensity as the registration measure. Our results show that, using 30 training pairs, a reduction of 33% is possible in the number of degrees of freedom without deterioration of the result. The same accuracy as without SSDM's is still achieved after a reduction up to 66% of the degrees of freedom.