Computerized detection of pulmonary nodules in computed tomography images

RATIONALE AND OBJECTIVES: Interpretation of computed tomographic (CT) scans of the lungs is a time-consuming task that involves visual correlation of possible nodules in one section with those in contiguous sections to distinguish actual nodules from blood vessels. Thus, the authors are developing automated methods to detect nodules on CT images of the thorax. METHODS: The computerized technique uses various computer-vision techniques and a priori information of the morphologic characteristics of pulmonary nodules. In each section, the external thoracic wall and lung boundaries are detected, and the features within the lung boundaries are subjected to gray-level thresholding operations. By analyzing the relationships between features arising at different threshold levels with respect to their shape, size, and location, each feature is assigned a likelihood of being a nodule or a vessel. Features in adjacent sections are compared to resolve ambiguous features. Detected nodule candidates are displayed in three dimensions within the lung. RESULTS: The system provided a sensitivity of 94% for nodule detection and an average of 1.25 false-positive results per case. CONCLUSIONS: Continued development of an automated method for detecting pulmonary nodules in CT scans is expected to aid radiologists in the task of locating nodules in three dimensions.     

Grid versus non-grid techniques for the detection of pulmonary nodules in a chest phantom

A partial chest phantom was constructed to compare two commonly employed radiographic techniques, 70 kVp without a grid and 120 kVp with a grid, for the detection of pulmonary nodules. The phantom consisted of human ribs embedded in paraffin, the lungs of a dog injected with silicone rubber, a tissue equivalent wax heart and beeswax nodules. The nodules ranged in size from 3-7 mm. A series of 120 films was exposed, half with each technique, and the films were interpreted by three senior residents and seven staff radiologists. More nodules of all sizes except 3 mm were detected with the 120 kVp technique. The 3 mm nodules were rarely detected with either technique. The disadvantages of the 120 kVp technique were an approximate 50 percent increase in patient exposures and almost twice as many false-positive nodule detections.     

Development of an improved CAD scheme for automated detection of lung nodules in digital chest images

Lung cancer is the leading cause of cancer deaths in men and women in the United States, with a 5-year survival rate of only about 13%. However, this survival rate can be improved to 47% if the disease is diagnosed and treated at an early stage. In this study, we developed an improved computer-aided diagnosis (CAD) scheme for the automated detection of lung nodules in digital chest images to assist radiologists, who could miss up to 30% of the actually positive cases in their daily practice. Two hundred PA chest radiographs, 100 normals and 100 abnormals, were used as the database for our study. The presence of nodules in the 100 abnormal cases was confirmed by two experienced radiologists on the basis of CT scans or radiographic follow-up. In our CAD scheme, nodule candidates were selected initially by multiple gray-level thresholding of the difference image (which corresponds to the subtraction of a signal-enhanced image and a signal-suppressed image) and then classified into six groups. A large number of false positives were eliminated by adaptive rule-based tests and an artificial neural network (ANN). The CAD scheme achieved, on average, a sensitivity of 70% with 1.7 false positives per chest image, a performance which was substantially better as compared with other studies. The CPU time for the processing of one chest image was about 20 seconds on an IBM RISC/6000 Powerstation 590. We believe that the CAD scheme with the current performance is ready for initial clinical evaluation.     

Neural networks for the analysis of small pulmonary nodules

PURPOSE: Small pulmonary nodules can be readily detected by computed tomography (CT). The goal of this detection is to diagnose early lung cancer as the five year survival at this early stage is over 70% in contradistinction to the overall 5-year survival of around 10%. Critical to the efficacy of CT for early lung cancer detection is the ability to distinguish between benign and malignant nodules. We explored the usefulness of neural networks (NNs) to help in this differentiation. METHODS: CT images of 28 pulmonary nodules, 14 benign and 14 malignant, each having a diameter less than 3 cm were selected. All were sufficiently malignant in appearance to require needle biopsy and surgery. The statistical-multiple object detection and location system (S-MODALS) NN technique developed for automatic target recognition (ATR) was used to differentiate between these benign and malignant nodules. RESULTS: S-MODALS was able to correctly identify all but three benign nodules. S-MODALS classified a nodule as malignant because it looked similar to other malignant nodules. It identified the most similar nodules to display them to the radiologist. The specific features of the nodule that determined its classification were also shown, so that S-MODALS is not simply a "black box" technique but gives insight into the NN diagnostics. CONCLUSION: This initial evaluation of S-MODALS NNs using pulmonary nodules whose CT features were very suspicious for lung cancer demonstrated the potential to reduce the number of biopsies without missing malignant nodules. S-MODALS performed well, but additional optimization of the techniques specifically for CT images would further enhance its performance.     

An improved shift-invariant artificial neural network for computerized detection of clustered microcalcifications in digital mammograms

A shift-invariant artificial neutral network (SIANN) has been applied to eliminate the false-positive detections reported by a rule-based computer aided-diagnosis (CAD) scheme developed in our laboratory. Regions of interest (ROIs) were selected around the centers of the rule-based CAD detections and analyzed by the SIANN. In our previous study, background-trend correction and pixel-value normalization were used as the preprocessing of the ROIs prior to the SIANN. A ROI is classified as a positive ROI, if the total number of microcalcifications detected in the ROI is greater than a certain number. In this study, modifications were made to improve the performance of the SIANN. First, the preprocessing is removed because the result of the background-trend correction is affected by the size of ROIs. Second, image-feature analysis is employed to the output of the SIANN in an effort to eliminate some of the false detections by the SIANN. In order to train the SIANN to detect microcalcifications and also to extract image features of microcalcifications, the zero-mean-weight constraint and training-free-zone techniques have been developed. A cross-validation training method was also applied to avoid the overtraining problem. The performance of the SIANN was evaluated by means of ROC analysis using a database of 39 mammograms for training and 50 different mammograms for testing. The analysis yielded an average area under the ROC curve (A(z)) of 0.90 for the testing set. Approximately 62% of false-positive clusters detected by the rule-based scheme were eliminated without any loss of the true-positive clusters by using the improved SIANN with image feature analysis techniques.     

Computer-aided diagnoses: automatic detection of lung nodules

This work describes a computational scheme for automatic detection of suspected lung nodules in a chest radiograph. A knowledge-based system extracts the lung masks over which we will apply the nodule detection process. First we obtain the normalized cross-correlation image. Next we detect suspicious regions by assuming a threshold. We examine the suspicious regions using a variable threshold which results in the growth of the suspicious areas and an increase in false positives. We reduce the large number of false positives by applying the facet model to the suspicious regions of the image. An algorithmic classification process gives a confidence factor that a suspicious region is a nodule. Five chest images containing 30 known nodules were used as a training set. We evaluated the system by analyzing 30 chest images with 40 confirmed nodules of varying contrast and size located in various parts of the lungs. The system detected 100% of the nodules with a mean of six false positives per image. The accuracy and specificity were 96%.     

Maximum intensity projection images in the detection of simulated pulmonary nodules by spiral CT

This study was undertaken to investigate the use of maximum intensity projection (MIP) images in the detection of pulmonary nodules by spiral CT (SCT). 40 pulmonary nodules of high density were created by endobronchial deployment of 2 and 4 mm beads in the peripheral airways of five anesthetized dogs. Standard SCT was performed with 5 mm collimation, pitch 2 and reconstruction of contiguous slices. MIP images were generated from overlapped slabs of seven consecutive 3 mm slices, reconstructed at 2 mm intervals and acquired at pitch 2. Scans were reviewed by six radiologists. The data were modelled using ordinal logistic regression for repeated measures, and the Wald chi 2 statistic used to test if there was a difference in nodule detection and reader confidence level between the two techniques. MIP imaging increased the odds of nodule detection by 2.18 (p = 0.0002). Reader confidence level for nodule detection was significantly higher with MIP images (p < 0.00001). MIP images improve the detection rate for small high density pulmonary nodules and increase reader confidence level, when compared with standard SCT.     

Computer-aided diagnosis in chest radiography. Preliminary experience

RATIONALE AND OBJECTIVES: Computer-aided diagnosis (CAD) schemes for chest radiography are being developed with which to alert radiologists to possible lesions, and thus potentially improve diagnostic accuracy. However, CAD schemes have not been tested on a large number of clinical cases. The authors identify design parameters that would be required for development of an intelligent workstation. METHODS: Computer-aided diagnosis programs were applied for the automated detection of lung nodules, cardiomegaly, and interstitial infiltrates to 310 consecutive chest radiographs, and were analyzed for potential usefulness and limitations. Computer-aided diagnosis output was evaluated by radiologists and physicists for accuracy and technical problems, respectively. RESULTS: Approximately 70% of the results were judged to be potentially acceptable; however, the number of false-positive findings was relatively high. Technical problems included failure to detect subtle abnormalities and the occurrence of false-positive detections caused by normal anatomical structures. CONCLUSION: Computer-aided diagnosis has the potential to be a valuable aid to radiologists in clinical practice, if certain technical problems can be overcome and if optimal operating points can be defined for clinical use.     

Computerized detection of masses in digitized mammograms using single-image segmentation and a multilayer topographic feature analysis

RATIONALE AND OBJECTIVES: We developed and evaluated a computer-aided detection (CAD) scheme for masses in digitized mammograms. METHODS: A multistep CAD scheme was developed and tested. The method uses a technique of single-image segmentation with Gaussian bandpass filtering to yield a high sensitivity for mass detection. A rule-based multilayer topographic feature analysis method is then used to classify suspected regions. A set of 260 cases, including 162 verified masses, was divided into two subsets; one set was used to set the rule-based classification and one was used to test the performance of the scheme. RESULTS: In a preliminary clinical study, the implemented detection scheme yielded 98% sensitivity with a false-positive detection rate of less than one false-positive region per image. CONCLUSION: Single-image segmentation methods seem to have high sensitivity in selecting true-positive mass regions in the first stage of a CAD scheme. A multilayer topographic image feature analysis method in the second stage of a CAD scheme has the potential to significantly reduce the false-positive detection rate.     

Artificial neural networks: current status in cardiovascular medicine

Artificial neural networks are a form of artificial computer intelligence that have been the subject of renewed research interest in the last 10 years. Although they have been used extensively for problems in engineering, they have only recently been applied to medical problems, particularly in the fields of radiology, urology, laboratory medicine and cardiology. An artificial neural network is a distributed network of computing elements that is modeled after a biologic neural system and may be implemented as a computer software program. It is capable of identifying relations in input data that are not easily apparent with current common analytic techniques. The functioning artificial neural network's knowledge is built on learning and experience from previous input data. On the basis of this prior knowledge, the artificial neural network can predict relations found in newly presented data sets. In cardiology, artificial neural networks have been successfully applied to problems in the diagnosis and treatment of coronary artery disease and myocardial infarction, in electrocardiographic interpretation and detection of arrhythmias and in image analysis in cardiac radiography and sonography. This report focuses on the current status of artificial neural network technology in cardiovascular medical research.     

Pulmonary nodules: effect of increased data sampling on detection with spiral CT and confidence in diagnosis

PURPOSE: To compare spiral computed tomography (CT) with interscan spacing of 4-5 mm versus 8-10 mm for detection rate and level of confidence in diagnosis of pulmonary nodules. MATERIALS AND METHODS: Four radiologists (two junior and two senior faculty members) retrospectively reviewed 67 spiral CT studies with one to six nodules per study. Every second image was masked, which resulted in 8-mm sections every 8 or 10 mm; then all images reconstructed every 4 or 5 mm were reviewed. Lesions were classified as definite, probable, or possible. RESULTS: Narrow interscan spacing yielded more lesions overall (583 vs 566, P < .025) and more definite lesions and fewer equivocal lesions (482 vs 431 and 101 vs 135, respectively; P < .055). The greatest effects were in the reduction of possible lesions (50 vs 88, P < .001) and in the reduction of false-positive diagnoses made by less experienced radiologists. CONCLUSION: Increased reconstruction frequency of spiral CT volume data sets improves detection of pulmonary nodules and enhances confidence in the diagnosis.     

Cardiorespiratory responses to acute hypoxemia in the chronically catheterized fetal llama at 0.7-0.9 of gestation

PURPOSE: To compare hard-copy digital chest radiographs obtained with a selenium-based system with wide-latitude asymmetric screen-film radiographs for detection of pulmonary nodules. MATERIALS AND METHODS: Fifty patients undergoing thoracic computed tomography (CT) for suspected pulmonary nodules were recruited to undergo both digital and screen-film posteroanterior (PA) and lateral chest radiography. Three chest radiologists blinded to the CT results independently reviewed each digital and screen-film radiograph, identified each nodule, and graded their confidence for its presence. RESULTS: Seventy-eight pulmonary nodules (mean diameter, 1.5 cm; range, 0.5-3.5 cm; 62 soft tissue, 16 calcified) were identified with CT in 34 patients, while 16 patients had clear lungs. The mean sensitivity for the detection of all nodules by all readers (PA and lateral) was 66% (95% Cl, 54%, 76%) for digital radiographs and 64% (95% Cl, 52%, 74%) for screen-film radiographs. Differences between the two techniques were not statistically significant (P > .05, Student t test). There was no difference in mean false-positive-true-positive ratios (PA, 0.35; lateral, 0.53) or positive predictive values (PA, 74%; lateral, 65%), and no significant difference (P > .05) was seen in mean reader confidence rating. CONCLUSION: In detecting pulmonary nodules, radiologists perform comparably with selenium-based digital and wide-latitude asymmetric screen-film radiographs.     

Depot medroxyprogesterone acetate or oral contraception in postpartum adolescents

The purpose of the study was the evaluation of low-dose spiral CT in the detection and assessment of contours of pulmonary nodules. In a prospective investigation 71 consecutive chest CT examinations were acquired both at 30 and 200 mA. Films were interpreted independently by two radiologists. According to the size, nodules were divided into four categories: 10 mm; nodule shape was registered. With both protocols, 240 nodules were detected. The correlation coefficient for both methods was 0.89. Discrepancies were found most frequently in nodules near to pulmonary vessels. Nodule size estimation did not differ more than one size category. Eight spiculated nodules were identified by both techniques. Low-dose spiral CT of the chest has a high sensitivity in the detection of pulmonary nodules. If clinical circumstances require dose minimization, low-dose spiral CT may be advocated as an alternative screening method to conventional dose spiral CT.     

Improved parameters for unsharp mask filtering of digital chest radiographs

Observer performance with four unsharp mask filtering algorithms for storage phosphor chest radiographs was compared with that with conventional screen-film radiographs in the detection of three types of simulated lung disease: nodules, fine lines, and micronodule clusters. Previously studied parameter sets (small [1.4-mm] and medium [5-mm] filter masks) and two new parameter sets (large [2.5-cm] and ultralarge [7-cm] masks) were compared by means of receiver operating characteristic analysis. With medium and small masks, nodule detection was inferior to that achieved with other modes. Use of ultralarge masks decreased the detection of lines compared with detection with conventional screen-film radiographs. Although detection of micronodule clusters was worse with digital images than with conventional screen-film radiographs, results with large and ultralarge masks were better than with small masks. Overall, filtering with large masks was best suited for simultaneously matching linear, nodular, and micronodular structures. These results suggest that lesion-specific processing of digital chest images is not necessary.     

Symptoms versus a diagnosis of depression: Differences in psychosocial functioning.

In studies of clinical depression, individuals who demonstrate elevated levels of symptoms but do not meet interview-based diagnostic criteria are typically labeled as false positive and eliminated from further consideration. However, the implicit assumption that false-positive participants differ in important ways from true-positive (i.e., diagnosed) participants has not been tested systematically. This study compared the functioning of true-positive, false-positive, and true-negative adolescents on clinical and psychosocial functioning. Although the false-positive participants manifested higher levels of current and future psychopathology than did the true-negative participants, they did not differ significantly from the true-positive participants on most of the measures of psychosocial dysfunction. "False positive," therefore, is not a benign condition. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Real-time automated detection and quantitative analysis of seizures and short-term prediction of clinical onset

PURPOSE: We describe an algorithm for rapid real-time detection, quantitation, localization of seizures, and prediction of their clinical onset. METHODS: Advanced digital signal processing techniques used in time-frequency localization, image processing, and identification of time-varying stochastic systems were used to develop the algorithm, which operates in generic or adaptable "modes." The "generic mode" was tested on (a) 125 partial seizures (each contained in a 10-min segment) involving the mesial temporal regions and recorded using depth electrodes from 16 subjects, and (b) 205 ten-minute segments of randomly selected interictal (nonseizure) data. The performance of the algorithm was compared with expert visual analysis, the current "gold standard." RESULTS: The generic algorithm achieved perfect sensitivity and specificity (no false-positive and no false-negative detections) over the entire data set. Seizure intensity, a novel measure that seems clinically relevant, ranged between 35.7 and 6129. Detection was sufficiently rapid to allow prediction of clinical onset in 92% of seizures by a mean of 15.5 s. CONCLUSIONS: This algorithm, which was implemented with a personal computer, represents a definitive step toward rapid and accurate detection and prediction of seizures. It may also enable development of intelligent devices for automated seizure warning and treatment and stimulate new study of the dynamics of seizures and of the epileptic brain.     

Technology transfer in digital mammography. Report of the Joint National Cancer Institute-National Aeronautics and Space Administration workshop of May 19-20, 1993

Digital mammography is one of the most promising novel technologies for further improvement of early detection of breast cancer, offering important potential advantages: 1) improved image quality; 2) digital image processing for improved lesion contrast; 3) computer-aided diagnosis for enhanced radiologic interpretation; and 4) teleradiology for facilitated radiologic consultation. The Diagnostic Imaging Research Branch of the National Cancer Institute (NCI) recently funded an international, multidisciplinary, multi-institutional Digital Mammography Development Group for collaborations between NCI, the academic community, and industry to facilitate the integrated development and implementation of digital mammographic systems. Currently, however, digital mammography faces a number of fundamental technological roadblocks: 1) cost-effective digital detectors and displays for imaging systems; 2) the need for novel algorithms for image processing and computer-aided diagnosis; and 3) high performance, low cost digital networks to provide an "information superhighway" for teleradiology. To solve some of these technological problems, the Diagnostic Imaging Research Branch of NCI joined efforts with the Technology Transfer Division of the National Aeronautics and Space Administration to pursue a federal technology transfer program in digital mammography. The authors discuss the findings and recommendations of the workshop entitled "Technology Transfer in Digital Mammography," which was organized and held jointly by the NCI and the National Aeronautics and Space Administration in May, 1993. Numerous innovative technologies of varying degree of promise for digital mammography were presented at the conference. In this article, specific technologies presented at the workshop by the federal and federally-supported laboratories are described, and critiques of these technologies by the leaders of the medical imaging community are presented.     

Resection of residual retroperitoneal masses in testicular cancer: evaluation and improvement of selection criteria. The ReHiT study group. Re-analysis of histology in testicular cancer

Residual retroperitoneal masses may remain after chemotherapy for metastatic non-seminomatous testicular cancer, which harbour residual tumour or totally benign tissue (necrosis/fibrosis). These residual masses may be effectively removed by a surgical resection. We evaluated current selection criteria and tried to develop alternative criteria in a data set of 544 patients, who had retroperitoneal lymph node dissection of residual masses. Six resection policies were identified from the literature. Two alternative policies were developed with logistic regression analysis. Evaluation of the policies focused on the true-positive rate (resection in case of tumour), and the false-positive rate (resection in case of necrosis). It appeared that most current policies use the size of the residual mass (> or = 10 mm or > or = 20 mm) as the predominant selection criterion. This resulted in high true-positive rates (most > 90%), but false-positive rates between 37% and 87%. The alternative policies included five well-known predictors of necrosis in addition to residual mass size (primary tumour histology, prechemotherapy levels of the three tumour markers alphafetoprotein (AFP), human chorionic gonadotropin (HCG) and lactate dehydrogenase (LDH) and mass shrinkage during chemotherapy). This strategy resulted in improved true- and false-positive rates, even when categories of the predictors were simplified for practical application. We conclude that a simple statistical model, based on a limited number of patient characteristics, provides better guidelines for patient selection than those currently used in clinical practice.     

Circulating lymphocyte phenotypic surface markers in anxiety disorder patients and normal volunteers

Assessment of clinical utility involves a series of steps based primarily on published peer-reviewed medical literature. Relevant publications usually use the scientific method, appropriate control groups, blinded reading, prospective design, and other study elements. Assessments are more credible when conducted by those who do not have a conflict of interest in the technique. A detailed assessment of digital and quantitative EEG was conducted recently by the American Academy of Neurology. The American Clinical Neurophysiology Society was a joint sponsor. This assessment concluded that digital EEG is an excellent substitute for paper EEG. It also found quantitative techniques helpful in epilepsy monitoring, seizure detections, and in operating room/intensive care unit trend monitors. Several other applications were considered promising, whereas some applications were considered not ready for clinical use. Substantial problems still plague the field, predisposing to false-positive results.