Method for segmenting chest CT image data using an anatomical model: preliminary results

Computer-aided diagnosis in chest radiography: a survey

The traditional chest radiograph is still ubiquitous in clinical practice, and will likely remain so for quite some time. Yet, its interpretation is notoriously difficult. This explains the continued interest in computer-aided diagnosis for chest radiography. The purpose of this survey is to categorize and briefly review the literature on computer analysis of chest images, which comprises over 150 papers published in the last 30 years. Remaining challenges are indicated and some directions for future research are given.

Knowledge-based segmentation of pediatric kidneys in CT for measurement of parenchymal volume

PURPOSE

The purpose of this work was to develop an automated method for segmenting pediatric kidneys in helical CT images and measuring their volume.

METHOD

An automated system was developed to segment the kidneys. Parametric features of anatomic structures were used to guide segmentation and labeling of image regions. Kidney volumes were calculated by summing included voxels. For validation, the kidney volumes of four swine were calculated using our approach and compared with the "true" volumes measured after harvesting the kidneys. Automated volume calculations were also performed in a cohort of nine children.

RESULTS

The mean difference between the calculated and measured values in the swine kidneys was 1.38 ml. For the pediatric cases, calculated volumes ranged from 41.7 to 252.1 ml/kidney, and the mean ratio of right to left kidney volume was 0.96.

CONCLUSION

These results demonstrate the accuracy of a volumetric technique that may in the future provide an objective assessment of renal damage.

Automatic lung segmentation for accurate quantitation of volumetric X-ray CT images

Segmentation of pulmonary X-ray computed tomography (CT) images is a precursor to most pulmonary image analysis applications. This paper presents a fully automatic method for identifying the lungs in three-dimensional (3-D) pulmonary X-ray CT images. The method has three main steps. First, the lung region is extracted from the CT images by gray-level thresholding. Then, the left and right lungs are separated by identifying the anterior and posterior junctions by dynamic programming. Finally, a sequence of morphological operations is used to smooth the irregular boundary along the mediastinum in order to obtain results consistent with those obtained by manual analysis, in which only the most central pulmonary arteries are excluded from the lung region. The method has been tested by processing 3-D CT data sets from eight normal subjects, each imaged three times at biweekly intervals with lungs at 90% vital capacity. We present results by comparing our automatic method to manually traced borders from two image analysts. Averaged over all volumes, the root mean square difference between the computer and human analysis is 0.8 pixels (0.54 mm). The mean intrasubject change in tissue content over the three scans was 2.75% +/- 2.29% (mean +/- standard deviation).

Automated CT image evaluation of the lung: a morphology-based concept

Computed tomography (CT) provides the most reliable method to detect emphysema in vivo. Commonly used methods only calculate the area of low attenuation [pixel index (PI)], while a radiologist considers the bullous morphology of emphysema. The PI is a good, well-known measure of emphysema. But it is not able to detect emphysema in cases in which emphysema and fibrosis occur at the same time. This is because fibrosis leads to a low number of low-attenuation pixels, while emphysema leads to a high number of pixels. The PI takes the average of both and, consequently, may present a result within the normal range.

METHOD

The main focus of this paper is to present a new algorithm of thoracic CT image evaluation based on pulmonary morphology of emphysema. The PI is extended, in that it is enabled to differentiate between small, medium, and large bullae (continuous low-attenuation areas). It is not a texture-based algorithm. The bullae are sorted by size into four size classes: class 1 being within the typical size of lung parenchyma; classes 2-4 presenting small, medium, and large bullae. It is calculated how much area the different classes take up of all low-attenuation pixels. The bullae index (BI) is derived from the percentage of areas covered, respectively, by small, medium, and large bullae. From the relation of the area of bullae belonging to class 4, to that of those belonging to class 2, a measure of the emphysema type (ET)is calculated. It classifies the lung by the type of emphysema in bullous emphysema or small-sized, diffuse emphysema, respectively.

RESULTS

The BI is as reliable as the PI. In cases in which the PI indicates normal values while in fact emphysema is coexisting with fibrosis, the BI, nevertheless, detects the destruction caused by the emphysema. The BI combined with the ET reflects the visual assessment of the radiological expert.

CONCLUSION

The BI is an objective and reliable index in order to quantify emphysematous destruction, hence, avoiding interobserver variance. This is particularly interesting for follow-up. The classification of the ET is a helpful and unique approach to achieving an exact diagnosis of emphysema.

Derived fuzzy knowledge model for estimating the depth of anesthesia

Reliable and noninvasive monitoring of the depth of anesthesia (DOA) is highly desirable. Based on adaptive network-based fuzzy inference system (ANFIS) modeling, a derived fuzzy knowledge model is proposed for quantitatively estimating the DOA and validate it by 30 experiments using 15 dogs undergoing anesthesia with three different anesthetic regimens (propofol, isoflurane, and halothane). By eliciting fuzzy if-then rules, the model provides a way to address the DOA estimation problem by using electroencephalogram-derived parameters. The parameters include two new measures (complexity and regularity) extracted by nonlinear quantitative analyses, as well as spectral entropy. The model demonstrates good performance in discriminating awake and asleep states for three common anesthetic regimens (accuracy 90.3 % for propofol, 92.7 % for isoflurane, and 89.1% for halothane), real-time feasibility, and generalization ability (accuracy 85.9% across the three regimens). The proposed fuzzy knowledge model is a promising candidate as an effective tool for continuous assessment of the DOA.

Problem-oriented prefetching for an integrated clinical imaging workstation

Prefetching methods have traditionally been used to restore archived images from picture archiving and communication systems to diagnostic imaging workstations prior to anticipated need, facilitating timely comparison of historical studies and patient management. The authors describe a problem-oriented prefetching scheme, detailing 1) a mechanism supporting selection of patients for prefetching via characterizations of clinical problems, using multiple data sources (picture archiving and communication systems, hospital information systems, and radiology information systems), classifying patients into cohorts on the basis of their medical conditions (e.g., lung cancer); and 2) prefetching of multimedia data (imaging, laboratory, and medical reports) from clinical databases to enable the viewing of an integrated patient record. Preliminary evaluation of the prefetching algorithm using classic information retrieval measures showed that the system had high recall (100 percent), correctly identifying and retrieving data for all patients belonging to a target cohort, but low precision (50 percent). A key finding during testing was that the recall of the system was increased through the use of multiple data sources (compared with one data source), because of better patient descriptors. Medical problems and patient cohorts were more specifically defined by combining information from heterogeneous databases.

Automatic detection and quantification of ground-glass opacities on high-resolution CT using multiple neural networks: comparison with a density mask

OBJECTIVE

We compared multiple neural networks with a density mask for the automatic detection and quantification of ground-glass opacities on high-resolution CT under clinical conditions.

SUBJECTS AND METHODS

Eighty-four patients (54 men and 30 women; age range, 18-82 years; mean age, 49 years) with a total of 99 consecutive high-resolution CT scans were enrolled in the study. The neural network was designed to detect ground-glass opacities with high sensitivity and to omit air-tissue interfaces to increase specificity. The results of the neural network were compared with those of a density mask (thresholds, -750/-300 H), with a radiologist serving as the gold standard.

RESULTS

The neural network classified 6% of the total lung area as ground-glass opacities. The density mask failed to detect 1.3%, and this percentage represented the increase in sensitivity that was achieved by the neural network. The density mask identified another 17.3% of the total lung area to be ground-glass opacities that were not detected by the neural network. This area represented the increase in specificity achieved by the neural network. Related to the extent of the ground-glass opacities as classified by the radiologist, the neural network (density mask) reached a sensitivity of 99% (89%), specificity of 83% (55%), positive predictive value of 78% (18%), negative predictive value of 99% (98%), and accuracy of 89% (58%).

CONCLUSION

Automatic segmentation and quantification of ground-glass opacities on high-resolution CT by a neural network are sufficiently accurate to be implemented for the preinterpretation of images in a clinical environment; it is superior to a double-threshold density mask.

A medical digital library to support scenario and user-tailored information retrieval

Current large-scale information sources are designed to support general queries and lack the ability to support scenario-specific information navigation, gathering, and presentation. As a result, users are often unable to obtain desired specific information within a well-defined subject area. Today's information systems do not provide efficient content navigation, incremental appropriate matching, or content correlation. We are developing the following innovative technologies to remedy these problems: 1) scenario-based proxies, enabling the gathering and filtering of information customized for users within a pre-defined domain; 2) context-sensitive navigation and matching, providing approximate matching and similarity links when an exact match to a user's request is unavailable; 3) content correlation of documents, creating semantic links between documents and information sources; and 4) user models for customizing retrieved information and result presentation. A digital medical library is currently being constructed using these technologies to provide customized information for the user. The technologies are general in nature and can provide custom and scenario-specific information in many other domains (e.g., crisis management).

Computer-aided diagnosis for lung cancer

CAD methods may provide radiologists with tools to obtain more accurate diagnoses for lung cancer. Considerable effort has been devoted to developing CAD tools for CXR; however, these are limited by the fundamental constraints of the projective CXR modality. CT provides far more detailed information that can be exploited better by CAD systems. There has been very little work done in this area to date, although the basic technology has already been developed through the more extensive research in the computer vision areas supported by industry and the military. Initial prototype CT CAD systems have been described that are highly effective in detecting small pulmonary nodules and in predicting malignancy of nodules. CT is now achieving momentum in the study of lung cancer. It has taken time for this modality to gain acceptance because of several factors: higher radiation dose, higher cost, and the novelty of use in this application. It is important to note that the technology for CT scanners is still rapidly evolving. As the speed, resolution, and cost of CT scanners continue to improve, computer techniques for the measurement and analysis of nodules will also achieve corresponding improvements in accuracy and diagnostic utility. Future knowledge-based CT CAD systems will provide detailed analysis of the related conditions of the lungs, such as emphysema, and diagnostic analysis of nodules. The issue is not whether CAD will improve the performance and capabilities of the radiologist, but at what rate their development and the corresponding improvement will occur. Current prototype CAD systems may be considered as tools. As such they will improve the performance of the user/radiologist if they are well engineered and if the user understands their capabilities and limitations. These systems need to be improved by knowledge-based engineering, which is notoriously difficult to implement robustly and requires model refinement and optimization based on a large database of cases. Research should be directed at developing these methods rather than comparing prototype systems with current practices. Future performance should be expected to exceed that of today's grand masters.

Computer-aided diagnosis of small pulmonary nodules

Computer-aided methods are now being developed for the detection and characterization of pulmonary nodules found in CT images, based on techniques from computer vision, image processing, and pattern classification. With the increasing resolution of modern CT scanners, computer methods provide continually improving accuracy, reproducibility, and utility in analyzing the larger numbers of images acquired in a lung screening exam or diagnostic study. This article describes the fundamental tools and issues involved in computer-aided nodule detection and characterization, as we move from two-dimensional toward three-dimensional automated methods. In particular, we focus on the new domain of "small" pulmonary nodules.

Knowledge-based segmentation of thoracic computed tomography images for assessment of split lung function

The assessment of differential left and right lung function is important for patients under consideration for lung resection procedures such as single lung transplantation. We developed an automated, knowledge-based segmentation algorithm for purposes of deriving functional information from dynamic computed tomography (CT) image data. Median lung attenuation (HU) and area measurements were automatically calculated for each lung from thoracic CT images acquired during a forced expiratory maneuver as indicators of the amount and rate of airflow. The accuracy of these derived measures from fully automated segmentation was validated against those from segmentation using manual editing by an expert observer. A total of 1313 axial images were analyzed from 49 patients. The images were segmented using our knowledge-based system that identifies the chest wall, mediastinum, trachea, large airways and lung parenchyma on CT images. The key components of the system are an anatomical model, an inference engine and image processing routines, and segmentation involves matching objects extracted from the image to anatomical objects described in the model. The segmentation results from all images were inspected by the expert observer. Manual editing was required to correct 183 (13.94%) of the images, and the sensitivity, specificity, and accuracy of the knowledge-based segmentation were greater than 98.55% in classifying pixels as lung or nonlung. There was no significant difference between median lung attenuation or area values from automated and edited segmentations (p > 0.70). Using the knowledge-based segmentation method we can automatically derive indirect quantitative measures of single lung function that cannot be obtained using conventional pulmonary function tests.

Content-based retrieval in picture archiving and communication systems

A COntent-Based Retrieval Architecture (COBRA) for picture archiving and communication systems (PACS) is introduced. COBRA improves the diagnosis, research, and training capabilities of PACS systems by adding retrieval by content features to those systems. COBRA is an open architecture based on widely used health care and technology standards. In addition to regular PACS components, COBRA includes additional components to handle representation, storage, and content-based similarity retrieval. Within COBRA, an anatomy classification algorithm is introduced to automatically classify PACS studies based on their anatomy. Such a classification allows the use of different segmentation and image-processing algorithms for different anatomies. COBRA uses primitive retrieval criteria such as color, texture, shape, and more complex criteria including object-based spatial relations and regions of interest. A prototype content-based retrieval system for MR brain images was developed to illustrate the concepts introduced in COBRA.

Automated measurement of single and total lung volume from CT

PURPOSE

The goal of this work was to develop an automated method for calculating single (SLV) and total (TLV) lung volumes from CT images.

METHOD

Patients underwent volumetric CT scanning through the entire chest in a single breath-hold, as well as pulmonary function tests. An automated, knowledge-based system was developed to segment the lungs in the CT images. Image-processing routines were used to extract sets of voxels from the image data that were identified by matching them to anatomical objects defined in a model. SLV and TLV were calculated by summing included voxels.

RESULTS

For 43 patients analyzed, TLV from CT and total lung capacity from body plethysmography were strongly correlated (r = 0.90). On average, the CT-derived volume of the left lung accounted for 47.2% of the total.

CONCLUSION

A knowledge-based approach to segmentation of the lungs in CT can be used to automatically estimate SLV and TLV.

Knowledge-based method for segmentation and analysis of lung boundaries in chest X-ray images

We present a knowledge-based approach to segmentation and analysis of the lung boundaries in chest X-rays. Image edges are matched to an anatomical model of the lung boundary using parametric features. A modular system architecture was developed which incorporates the model, image processing routines, an inference engine and a blackboard. Edges associated with the lung boundary are automatically identified and abnormal features are reported. In preliminary testing on 14 images for a set of 18 detectable abnormalities, the system showed a sensitivity of 88% and a specificity of 95% when compared with assessment by an experienced radiologist.