Novel thoracic imaging augments diagnosis of bronchial obstruction.
Explore the source record for details and available documents.
Airway Obstruction↗
Biomedical subjects
Ronald M Summers
Publications and source records attributed to Ronald M Summers.
Multiple neural network classification scheme for detection of colonic polyps in CT colonography data sets.
RATIONALE AND OBJECTIVES: A new classification system for colonic polyp detection, designed to increase sensitivity and reduce the number of false-positive findings with computed tomographic colonography, was developed and tested in this study. MATERIALS AND METHODS: The system involves classification by a committee of neural networks (NNs), each using largely distinct subsets of features selected from a general set. Back-propagation NNs trained with the Levenberg-Marquardt algorithm were used as primary classifiers (committee members). The set of features included region density, Gaussian and mean curvature and sphericity, lesion size, colon wall thickness, and the means and standard deviations of all of these values. Subsets of variables were initially selected because of their effectiveness according to training and test sample misclassification rates. The final decision for each case is based on the majority vote across the networks and reflects the weighted votes of all networks. The authors also introduce a smoothed cross-validation method designed to improve estimation of the true misclassification rates by reducing bias and variance. RESULTS: This committee method reduced the false-positive rate by 36%, a clinically meaningful reduction, and improved sensitivity by an average of 6.9% compared with decisions made by any single NN. The overall sensitivity and specificity were 82.9% and 95.3%, respectively, when sensitivity was estimated by means of smoothed cross-validation. CONCLUSION: The proposed method of using multiple classifiers and majority voting is recommended for classification tasks with large sets of input features, particularly when selected feature subsets may not be equally effective and do not provide satisfactory true- and false-positive rates. This approach reduces variance in estimates of misclassification rates.
Algorithms↗
Computer-assisted detection of colonic polyps with CT colonography using neural networks and binary classification trees.
Detection of colonic polyps in CT colonography is problematic due to complexities of polyp shape and the surface of the normal colon. Published results indicate the feasibility of computer-aided detection of polyps but better classifiers are needed to improve specificity. In this paper we compare the classification results of two approaches: neural networks and recursive binary trees. As our starting point we collect surface geometry information from three-dimensional reconstruction of the colon, followed by a filter based on selected variables such as region density, Gaussian and average curvature and sphericity. The filter returns sites that are candidate polyps, based on earlier work using detection thresholds, to which the neural nets or the binary trees are applied. A data set of 39 polyps from 3 to 25 mm in size was used in our investigation. For both neural net and binary trees we use tenfold cross-validation to better estimate the true error rates. The backpropagation neural net with one hidden layer trained with Levenberg-Marquardt algorithm achieved the best results: sensitivity 90% and specificity 95% with 16 false positives per study.
Algorithms↗
Sharing images.
Explore the source record for details and available documents.
Information Dissemination↗
Science to practice: Detection of active colonic hemorrhage with use of helical CT: findings in a swine model.
Explore the source record for details and available documents.
Animals↗
Decreased aerobic capacity in children with juvenile dermatomyositis.
OBJECTIVE: To determine whether patients with juvenile dermatomyositis (DM) have limited aerobic capacity compared with healthy controls. METHODS: Fourteen juvenile DM patients with inactive to moderately active, stable disease (age range 7-17 years) and 14 age- and sex-matched controls performed a maximal exercise test using a cycle ergometer. Oxygen uptake and power were measured at peak exercise (VO(2peak) and W(peak), respectively) and at anaerobic threshold (AT and W(AT)). Juvenile DM disease activity and damage were also assessed. RESULTS: Patients with juvenile DM had significantly reduced VO(2peak) (19.6 ml O(2)/kg/minute in juvenile DM versus 31.1 ml O(2)/kg/minute in controls), peak heart rate (166 versus 184 beats per minute), W(peak) (1.6 versus 2.7 watts/kg), AT (11.1 versus 18.0 ml O(2)/kg/minute) and W(AT) (0.6 versus 1.4 watts/kg), compared to controls (P <or= 0.05 for each). Aerobic exercise parameters correlated with physician global disease activity and damage, T1-weighted magnetic resonance imaging, and Childhood Myositis Assessment Scale scores (r(s) = 0.58 - 0.82, P <or= 0.05). CONCLUSION: Patients with juvenile DM with a range of disease activity have a decreased aerobic and work capacity compared to healthy children. Aerobic exercise limitation in juvenile DM correlates best with measures of disease damage (global damage assessment, T1-weighted magnetic resonance imaging, and disease duration). Aerobic exercise testing may be valuable in the assessment of physical endurance, and aerobic training may be indicated as part of the therapeutic regimen in myositis patients with inactive to moderately active, stable disease.
Adolescent↗
Virtual bronchoscopy for evaluation of malignant tumors of the thorax.
OBJECTIVE: Virtual bronchoscopy is a novel technique making use of 3-dimensional reconstruction of 2-dimensional helical computed tomographic images for noninvasive evaluation of the tracheobronchial tree. This study was undertaken to evaluate the diagnostic potential of virtual bronchoscopy by comparing virtual bronchoscopic images with fiberoptic bronchoscopic findings in patients with thoracic malignant disease. METHODS: Thirty-two consecutive patients with thoracic malignant tumors underwent virtual bronchoscopy for evaluation of suspected tracheobronchial lesions. For each virtual bronchoscopic examination, 200 to 300 contiguous 1.25-mm images of the thorax were obtained in only one or two 17-second breath holds by using a multislice computed tomographic scanner. Virtual bronchoscopy images were reconstructed and interpreted blind to the actual endoscopic findings. Results of virtual bronchoscopy were compared with fiberoptic bronchoscopic findings in 20 patients. RESULTS: Anatomic computer simulation of the bronchial tree was successfully created in all patients. In 7 (35%) of 20 patients, results of fiberoptic bronchoscopy were found to be within normal limits. In all patients with normal anatomy, virtual bronchoscopy accurately correlated with the fiberoptic findings. Thirteen (65%) patients had a total of 22 abnormal findings on fiberoptic bronchoscopy. Virtual bronchoscopy detected 18 of 22 abnormal fiberoptic bronchoscopic findings: 13 of 13 obstructive lesions, 5 of 6 endoluminal lesions, and 0 of 3 mucosal lesions. The sensitivity of virtual bronchoscopy was 100% for obstructive lesions, 83% for endoluminal lesions, 0% for mucosal lesions, and 82% for all abnormalities; the specificity of virtual bronchoscopy was 100%. CONCLUSIONS: Preliminary evaluation indicates that virtual bronchoscopy may be a promising and noninvasive modality for identifying bronchial obstructions and endoluminal lesions, as well as for assessing the tracheobronchial tree beyond stenoses. However, at present, virtual bronchoscopy does not enable the detection of subtle mucosal lesions, and as such, this modality may not be appropriate for identifying premalignant lesions in the respiratory tract. Although fiberoptic bronchoscopy remains the standard modality for evaluating airway patency and mucosal lesions, virtual bronchoscopy may provide additional information that may be useful in the management of pulmonary malignant tumors.
Adult↗
Colonic polyps: complementary role of computer-aided detection in CT colonography.
PURPOSE: To apply a computer-aided detection (CAD) algorithm to supine and prone multisection helical computed tomographic (CT) colonographic images to confirm if there is any added benefit provided by CAD over that of standard clinical interpretation. MATERIALS AND METHODS: CT colonography (with patients in both supine and prone positions) was performed with a multisection helical CT scanner in 40 asymptomatic high-risk patients. There were two consecutive series of patients, 20 of whom had at least one polyp 1.0 cm in size or larger and 20 of whom had normal colons at conventional colonoscopy performed the same day. The CT colonographic images were interpreted with an automated CAD algorithm and by two radiologists who were blinded to colonoscopy findings. RESULTS: For 25 polyps at least 1.0 cm in size ("large" polyps), sensitivity for detection by at least one radiologist was 48% (12 of 25). The sensitivity of CAD for detecting large polyps was also 48% (12 of 25), but the CAD algorithm detected four of 13 large polyps that were not detected by either radiologist (31%, 95% two-sided CI: 9, 61), increasing the potential sensitivity to 64% (16 of 25). For polyps identifiable retrospectively, sensitivity of CAD was 67% (12 of 18), and sensitivity of the combination of detection with the CAD algorithm or by at least one radiologist was 89% (16 of 18). There were an average of 11 false-positive detections per patient for CAD. CONCLUSION: In this series of patients in whom radiologists had difficulties detecting polyps (compared with sensitivities of 75%-90% reported in the literature), this CAD algorithm played a complementary role to conventional interpretation of CT colonographic images by detecting a number of large polyps missed by trained observers.
Aged↗
CT virtual bronchoscopy of the central airways in patients with Wegener's granulomatosis.
OBJECTIVES: To compare CT virtual bronchoscopy (VB) to CT alone and to conventional bronchoscopy for evaluation of central airway stenoses in patients with Wegener's granulomatosis. DESIGN: Prospective observer study, in which 18 thin-section helical CT scans of the trachea and bronchi of 11 patients with Wegener's granulomatosis were obtained. VB was performed using surface rendering and was evaluated by one bronchoscopist and one radiologist in a blinded fashion. Bronchoscopic correlation within an average of 1.8 days of CT was available. MEASUREMENTS AND RESULTS: VB displayed 188 of 198 bronchi (95%). Thirty-two of 40 stenoses (80%) were detected by VB by at least one of two physicians (double reading), and 22 of 40 stenoses (55%) were detected by a third physician reading only the CT. CONCLUSIONS: VB depicts bronchi to the segmental level and detects the majority of central airway stenoses in patients with Wegener's granulomatosis. A team approach is useful to attain optimal clinical benefit from VB for these patients.
Adult↗
Neopterin and quinolinic acid are surrogate measures of disease activity in the juvenile idiopathic inflammatory myopathies.
OBJECTIVE: We evaluated the utility of neopterin and quinolinic acid (QUIN) as surrogate measures of disease activity in juvenile idiopathic inflammatory myopathies (IIMs). METHODS: Plasma and first morning void urine samples were measured for neopterin and QUIN using commercial ELISA, HPLC, or gas chromatography-mass spectrometry in 45 juvenile IIM patients and 79 healthy controls. Myositis disease activity assessments were obtained. RESULTS: Plasma and urine neopterin and QUIN concentrations were increased in juvenile IIM patients compared with healthy controls (P <0.017). Urine neopterin and QUIN highly correlated with each other (r(s) = 0.73; P <0.0001). Urine neopterin and QUIN correlated moderately with myositis disease activity assessments, including physician and parent global activity assessments, muscle strength testing, functional assessments (Childhood Myositis Assessment Scale, Childhood Health Assessment Questionnaire), skin global activity, and edema on magnetic resonance imaging (r(s) = 0.42-0.62; P <0.05), but generally not with muscle-associated enzymes in serum. Urine neopterin or QUIN, in combination with either serum lactate dehydrogenase (LD) or aspartate aminotransferase (AST), significantly predicted global disease activity (R(2) =0.40-0.56; P <0.002), and both were more sensitive to change than these serum enzymes (standardized response means, -0.41 to -0.48). CONCLUSIONS: Urinary neopterin and QUIN are candidate measures of disease activity in juvenile IIM patients and add significantly to the prediction of global disease activity in combination with serum LD or AST values. Measurement of these markers in first morning void urine specimens appears to be as good as, or possibly better than, measurements of their concentrations in plasma.
Adolescent↗
Computer-aided detection of polyps in a colon phantom: effect of scan orientation, polyp size, collimation, and dose.
PURPOSE: To determine the importance of polyp size, orientation to the scan plane, collimation, scanner type (single or multislice helical), and radiation dose on computed tomography (CT) colonography computer-aided detection. MATERIALS AND METHODS: Eight tissue-equivalent simulated polyps were placed into the interior of an air-filled acrylic tube placed within a water-filled box. Their sizes, expressed by diameter and height in millimeters, were 10 x 10, 10 x 7, 10 x 5, 10 x 3, 7 x 7, 7 x 5, 7 x 3, and 5 x 5. Detection of the polyps was performed by applying our prototype automated polyp detector software to 48 CT colonography data sets of the phantom acquired with different CT scanner settings. RESULTS: We detected at least six of the eight polyps in 47 of 48 experiments. The two most frequently undetected polyps (7 x 7 and 5 x 5) had extreme eccentricity (their height was twice the radius of the base) and were most commonly missed for 90 degrees tube orientation, 5-mm collimation, and high table speed. False-positive detections occurred in only 5 of 48 experiments. CONCLUSION: Clinically significant 10-mm polyps can be detected with 100% sensitivity in all orientations, doses, collimations, and modes that we examined.
Artifacts↗