SEARCH · PubMed Health

Results for “Radiographic Image Interpretation, Computer-Assisted”

Explore indexed PubMed citations for clinical trials, systematic reviews and public health research. Read source abstracts and follow each citation to its original PubMed record.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 649 records · Page 36Linked to original sources

PubMed1994

Semiquantitative and visual analysis of FDG-PET images in pulmonary abnormalities.

UNLABELLED: FDG PET images of the thorax can be analyzed semiquantitatively using standardized uptake ratios (SUR) or activity ratios between abnormal and normal tissue, or qualitatively by visual comparison of the abnormality to normal structures. Standardized uptake ratio evaluation of FDG PET images has been shown to accurately differentiate benign from malignant focal pulmonary abnormalities. The accuracy of activity ratios and visual analysis have not been evaluated. We therefore prospectively analyzed FDG PET images in patients with pulmonary abnormalities to evaluate differences in analytic schemes. METHODS: We evaluated 107 patients with an indeterminate focal abnormality on chest radiograph or CT with FDG PET between November 1991 and March 1993. The PET studies were evaluated using SUR, activity ratios and visual analysis. Activity ratios of maximum activity/cc and average activity/cc between regions of interest (ROIs) in abnormalities and normal lung on the contralateral side were calculated. Visual interpretations were graded on a five-point scale of two observers' confidence of malignancy. FDG uptake in the abnormality was also visually graded in comparison to mediastinal activity. Receiver-operating characteristic (ROC) curve areas were generated for the SUR data, activity ratios and visual analysis. RESULTS: Of 88 patients in which a conclusive diagnosis was made, 61 (69%) patients had malignancy and 27 (31%) patients had a benign process. SUR, maximum activity ratio, average activity ratio and visual interpretation ROC curve areas were 0.96, 0.95, 0.92 and 0.96, respectively. CONCLUSIONS: SUR, activity ratios and visual evaluation are each equally accurate methods of FDG PET data analysis in differentiating malignant from benign focal pulmonary abnormalities.

Deoxyglucose↗

PubMed1994

Early diagnosis of spinal tuberculosis by MRI.

MRI was performed at three centres in Bombay on 24 patients clinically suspected of tuberculosis of the spine but with normal radiographs. There were 11 males and 13 females and their average age was 24 years (11 to 60). 99mTc bone scans were done in 16 patients before MRI. Eleven patients had the diagnosis confirmed by biopsy and the remainder all responded rapidly to specific antituberculous chemotherapy. On T1-weighted images there was a decrease in signal intensity of the involved bone and soft tissues; on T2-weighted images there was increased signal intensity. Depending on the stage of the disease, three different patterns of infection were revealed: osteitis, osteitis with an abscess, and osteitis with or without an abscess plus discitis. The anatomical pattern of involvement, particularly of the soft tissues and the discs, is specific for tuberculous disease. The ability of MRI to detect tuberculosis of the spine earlier than other techniques could reduce bone destruction and deformity and diminish the need for surgical intervention. Despite the specificity of the patterns revealed by MRI, biopsy is recommended during the stage of osteitis to confirm the diagnosis.

Abscess↗

PubMed1995

Diagnostic usefulness of chest computed radiography--film versus cathode-ray tube images.

Seventy-one plain chest images obtained by computed radiography (CR) with an imaging plate were interpreted on film and two kinds of cathode-ray tube (CRT) monitors installed separately at two facilities (1,024 x 1,536 pixels, 8 bits, and 1,024 x 1,280 pixels, 10 bits) by 20 radiologists and four chest internists. The clinical categories of these 71 cases included pulmonary nodules and interstitial abnormalities. Image reading sessions were held over a total of 4 days, ie, 2 days and then another 2 days, 3 weeks later. Twenty-four observers formed four groups with six members each. Two groups read either films or CRT images at one of the two facilities. In the second experiment, 26 of 71 images were compressed at 10:1, 19 of 71 were compressed at 20:1, and 26 were not compressed. Analyses of the areas under the receiver-operating characteristic curves showed no significant differences in detection of pulmonary abnormalities between film and CRT. In detecting interstitial pulmonary abnormalities, film was more sensitive than CRT monitor. There were no significant differences in observers' performances between the two different kinds of CRT workstation. Subjective evaluation of image quality showed that images irreversibly compressed to the ratios of 10:1 and 20:1 were inferior to original images. Although further considerations are needed with regard to spatial resolution requirements, image processing, and image compression, the utilization of CR CRT image as a substitute for CR film image will be possible.

Data Display↗

PubMed1995

Diagnosis of aortic dissection: value of helical CT with multiplanar reformation and three-dimensional rendering.

OBJECTIVE: Twenty-three patients with suspected aortic dissection were evaluated in this preliminary study of helical CT to determine the usefulness of axial sections, multiplanar reformation, and three-dimensional (3D) rendering in assessing the presence of dissection and the extent of intimal flap. MATERIALS AND METHODS: Patients were referred for helical CT scanning because of chest pain or an abnormal chest radiograph. Scans were performed during bolus injection of nonionic contrast material at 2.0-2.5 ml/sec using a mean scan delay of 47 sec. Axial scans with 5-mm collimation were obtained in all patients. They extended from the great vessels to the distal thoracic aorta just above the hiatus. Delayed nonhelical sections were obtained through the upper abdomen. Multiplanar reformations and 3D models were reconstructed from the helical data in 13 patients and were compared to axial sections in 7 patients who proved to have documented dissection. The efficacy of CT was determined using surgery, angiography, or clinical outcome to establish the diagnosis. RESULTS: Of the 23 patients studied, axial sections resulted in 15 true-negative, 7 true-positive, and 1 false-positive interpretation. In three of seven patients with dissection, it was difficult to determine the extent of the intimal flap on axial sections; multiplanar reformation or 3D views clarified the relevant anatomy in all 3 cases. Among the 3D display methods, ray-sum projection views were superior to surface model or maximum-intensity-projection views. CONCLUSION: If studies of larger numbers of patients confirm our preliminary findings, multiplanar reformation and 3D rendering of helical CT scans will be a valuable addition to axial display of CT studies used to detect aortic dissection and to determine the extent of the intimal flap.

Adult↗

PubMedDate not supplied

Quantitative analysis of coronary arteriograms by microprocessor cinevideodensitometry.

A rapid microprocessor technique for measuring the cross-sectional area, diameter, and relative percentage stenosis of coronary atherosclerotic lesions by cinevideodensitometric analysis was developed and validated. Video images of projected 35-mm coronary arteriographic cine frames were analyzed from cinevideodensitometric profile curves recorded for the catheter shaft, normal artery, and stenotic segment. In radiographic phantom studies of calibrated, contrast-filled, plexiglass cylinders, cinevideodensitometric measurements correlated linearly with percentage relative stenosis (r = 0.98; SEE = 4.1%), diameter (r = 0.99; SEE = 0.12 mm), and cross-sectional area (r = 0.99; SEE = 0.32 mm2). In postmortem studies of two patients dying after coronary arteriography, cross-sectional areas of arterial segments measured by cinevideodensitometry correlated well (r = 0.99; SEE = 0.71 mm) with areas of acrylic resin casts of the coronary arteries. Intraobserver variability (r = 0.99; SEE = 2.6%) and interobserver variability (r = 0.96; SEE = 5.3%) of cinevideodensitometric measurements of coronary arteriograms were low. Additionally, percentage relative stenosis measured in the right anterior oblique projection correlated well with measurements in the left anterior oblique projection (r = 0.98; SEE = 0.11 mm2) of patients with eccentric stenotic lesions. Lastly, cinevideodensitometric measurements were significantly (p less than 0.05) more reproducible than caliper measurements. This inexpensive dedicated microprocessor system provides rapid cinevideodensitometric measurements of coronary arterial dimensions, without requiring manual tracing of arterial segments or the major expense of a main-frame computer system.

Absorptiometry, Photon↗

PubMed1990

Developments towards the slice-wise three-dimensional reconstruction of the distribution of the contrast perfusion in the myocardial muscle from biplane angiographic views.

In theory, radiographic myocardial perfusion imaging allows a quantitative assessment of the functional significance of a coronary stenosis. However, in the conventional two-dimensional projection images there does not exist a one-two-one relationship between a selected myocardial region of interest (ROI) and one particular coronary segment perfusing that area due to over-projection of myocardial regions in front of and behind the selected ROI perfused by other arterial segments, which may result in measurements which are difficult to interpret or even unreliable. To overcome these problems, we have developed two algorithms to determine the spatial distribution of perfusion levels in slices of the heart, selected approximately perpendicular to the left ventricular long axis, from two orthogonal angiographic views: the Segmental Reconstruction Technique (SRT) and the Network Programming Reconstruction Technique (NPRT). Both techniques require a priori geometric information about the myocardium, which can be obtained from the epicardial coronary tree (epicardial boundaries) and the left ventricular lumen (endocardial boundaries). Using the SRT approach, pie-shaped segments are defined for each slice within the myocardial geometric constraints such that superimposition of these segments when projected in orthogonal biplane views is minimal. The reconstruction process uses a model with identical myocardial geometry and definition of segments. Each segment of the model is assigned a relative perfusion level with unit one if no other a priori information is available. In this case, the model contains geometric information only. In case a priori information about expected segmental perfusion levels is available, a level between zero and one is assigned to each segment. The a priori information on the myocardial perfusion levels can be extracted from either anatomic information about the location and severity of existing coronary arterial obstructions, or from a slice adjacent to the one under reconstruction. Using the NPRT approach perfusion levels are computed for each volume picture element of a slice within the reconstructed myocardial geometry, thus resulting in a much higher spatial resolution than the SRT approach. A priori information of perfusion levels must be included in this approach, again based upon anatomical information, or upon the slice adjacent to the one under reconstruction. The very first slice of a myocardial study will be reconstructed by the SRT approach. Extensive computer simulations for the SRT have proved that the mean difference between the actual and reconstructed segmental perfusion levels, on a scale from 0 to 1, is smaller than 0.45 (SEE = 0.0033, REE = 1.80) for various coronary artery disease states without the use of a priori information on expected perfusion levels. This error becomes smaller than 0.36 (SEE = 0.0026, REE = 1.42), if a priori information in the reconstruction technique is included. Similar computer simulations for the NPRT have proved that these mean differences in geometric segments equal to those defined for the SRT, are smaller than 2.94 (SEE = 0.0308, REE = 0.77) on a scale from 0 to 16, without the use of a priori information on expected perfusion levels, and smaller than 1.72 (SEE = 0.0304, REE = 1.10) on the same scale when a priori information is included. Therefore, it may be concluded that slice-wise three-dimensional reconstruction of perfusion levels is feasible from biplane computer-simulated data, and that a similarity exists for mean perfusion levels in corresponding regions in the simulated and reconstructed slices, for various states of single coronary artery disease.

Algorithms↗

PubMed1990

Teleradiology image transmission system: diagnostic accuracy at three matrix sizes for various types of images.

The interpretability of transmitted digitized radiographic images is an important factor in the operation and use of teleradiology systems. Matrix size may influence diagnostic accuracy of the interpretation. Commercially available equipment has certain built-in image enhancement controls that may increase the interpretability of the image received. Evaluation of the effect of varying the matrix size and other factors on diagnostic accuracy are described.

Computer Communication Networks↗

PubMed1995

Three-dimensional display of cardiac structures using reconstructed magnetic resonance imaging.

It is sometimes difficult to understand the three-dimensional (3D) relationship of cardiac and mediastinal structures despite advances in magnetic resonance (MR) imaging techniques. We present a low-cost system for 3D reconstruction of the major mediastinal structures by processing the MR imaging data on a NeXT workstation. MR images of multisection, multiphase, spin-echo techniques stored in a picture archiving and communication system (PACS) data base were used for the reconstruction. The computer program obtained the contours of the multiple components of the mediastinal structures by the combination of automatic and manual procedure. The bundled software of a 3D kit was used for surface rendering of hidden surface removal, shading of the visible parts of the surfaces, perspective transformation, and motion parallax by rotation of the surfaces. 3D reconstruction was performed in 15 patients with cardiac diseases, and the 3D-reconstructed images were compared with the plain chest x rays of the patients. The 3D presentation clearly showed the complex anatomy of cardiovascular diseases and helped elucidate the misconceptions in the interpretation of the plain chest x rays. Our 3D images are used for education and should be viewed by medical students and beginners in radiology at an individual pace with plain chest radiographs, MR images, and legends. Although applied to the heart and the great vessels in this report, this system is also applicable to other structures.

Computer Graphics↗

PubMed1995

Detection of lung nodules in digital chest radiographs using artificial neural networks: a pilot study.

Radiologists can fail to detect up to 30% of pulmonary nodules in chest radiographs. A back-propagation neural network was used to detect lung nodules in digital chest radiographs to assist radiologists in the diagnosis of lung cancer. Regions of interest (ROIs) that contained nodules and normal tissues in the lung were selected from digitized chest radiographs by a previously developed computer-aided diagnosis (CAD) scheme. Different preprocessing techniques were used to produce input data to the neural network. The performance of the neural network was evaluated by receiver operating characteristic (ROC) analysis. We found that subsampling of original 64- x 64-pixel ROIs to smaller 8- x 8-pixel ROIs provides the optimal preprocessing for the neural network to distinguish ROIs containing nodules from false-positive ROIs containing normal regions. The neural network was able to detect obvious nodules very well with an Az value (area under ROC curve) of 0.93, but was unable to detect subtle nodules. However, with a training method that uses different orientations of the original ROIs, we were able to improve the performance of the neural network to detect subtle nodules. Artificial neural networks have the potential to serve as a useful classifier to help to eliminate the false-positive detections of the CAD scheme.

False Positive Reactions↗

PubMed1994

Computed tomography interpretations with a low-cost workstation: a timing study.

An ergonomically simple prototype workstation with two 900 x 1,100-pixel monitors capable of displaying eight full-resolution computed tomography (CT) images in 0.2 seconds, was compared with film for interpretation of computed tomographic images of the chest and abdomen. The hardware platform for this workstation cost less than $11,500 in 1993. A repeated-measures experiment was used to generate average interpretation times of 6.17 minutes for the workstation and 6.03 minutes for the film, including loading and unloading films, with three of the four subjects averaging about a minute longer for each workstation interpretation. All dictated reports were of clinically acceptable accuracy. All radiologists stated that workstations based on this design would be an acceptable clinical tool. However, observation suggested human working-memory strain among infrequent CT readers that could indicate the need for additional training. These data suggest that low-cost workstations can have practical application in interpretation of digital medical images such as CT, with the possibility of small increases in interpretation time.

Adult↗

PubMedDate not supplied

A review on biomedical image processing and future trends.

The last two decades have witnessed a revolutionary development in the field of biomedical and diagnostic imaging. Imaging procedures and modalities which were only in the experimental research phase in the early part of the last two decades, have now become universally accepted clinical procedures. They include computerized tomography (CT), magnetic resonance imaging, ultrasound imaging, nuclear medicine imaging, computerized hematological cell analysis, etc. In the past, the conventional and relatively simple image processing techniques such as image enhancement, gray-level mapping, spectral analysis, region extraction, etc. have been modified for biomedical images and successfully applied for processing and analysis. The role of image enhancement, gray-level mapping, and image reconstruction from projections algorithms in CT and other radiological imaging modalities is well evident. Recently, many advances in biomedical image processing, analysis, and understanding algorithms have shown a great potential for enhancing and interpreting useful diagnostic information from these images more accurately. This paper presents a review on the current state-of-the-art techniques in biomedical image processing and comments on future trends.

Algorithms↗

PubMed1991

Carpal orientation from computed reference axes.

Carpal instability is usually diagnosed by abnormal two-plane radiographic angles. These angles are often unreliable. A method that eliminates interpretation of overlapping shadows and uses all of the carpal geometry should improve clinical diagnoses. The digital data from computed tomography scans can be manipulated to describe the carpal orientation in the normal wrist. The digital data from the computed tomography scans of twenty-two normal wrists were used to compute distances with and without directions between the volumetric centroids of the carpal bones. An expansion technique also extracted from the computed tomography data an orthogonal set of vectors, the principal axes. The first principal axis describes the longest dimension of each bone. The average angle produced by the first principal axes of the scaphoid and lunate was 23.6 degrees, scaphoid and capitate was 73.2 degrees, and the capitate and the lunate was 93.5 degrees. These computations represent new carpal axes and intercarpal angles that are not related to the commonly measured two-plane radiographic angles. They should prove helpful in the study of kinematics and pathomechanics in the wrist joint.

Carpal Bones↗

PubMed1994

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.

Breast Neoplasms↗

PubMedDate not supplied

Clubfoot analysis with three-dimensional computer modeling.

Which way are the bones rotated in a clubfoot? This question has long been debated by clubfoot surgeons. Opinions have been based on observations from surgery, radiographs, and autopsies. These methods all have pitfalls and are subject to misinterpretation. We used three-dimensional computer modeling to analyze histologic sections of a newborn clubfoot and a newborn normal foot. Relative to the bimalleolar axis in the axial plane, the normal talus demonstrated 5 degrees of internal rotation of its body and 25 degrees internal rotation of its neck. The clubfoot talus showed 14 degrees of external rotation of its body and 45 degrees of internal rotation of its neck. The calcaneus was externally rotated 5 degrees in the normal foot and internally rotated 22 degrees in the clubfoot.

Calcaneus↗

PubMed1991

Computer-aided interpretation and quantification of angular periodontal bone defects on dental radiographs.

Capabilities of human observers to detect and describe small bone defects objectively are limited. Digital image processing can provide a useful contribution to the diagnostic process. This paper describes the evaluation of a computer-aided procedure for the interpretation and quantification of angular periodontal bone defects on dental radiographs. The computer-aided procedure was able to rank series of artificial periodontal bone lesions as accurate as experienced clinicians. Comparison of data from clinical inspection of lesions during surgery and quantitative results of the digitized procedure shows that the latter produced reliable information on the lesions size. Reproducibility is satisfactory. It was concluded that computer-aided detection and description of periodontal bone defects decreases the interobserver variability in general and the time-dependent variability in repeated assessments of a single observer.

Alveolar Bone Loss↗

PubMed1990

Receiver operating characteristic analysis of chest image interpretation with conventional, laser-printed, and high-resolution workstation images.

The differences among radiologists in interpreting conventional and digitized images obtained with different radiologic procedures is an important research issue in these times of implementation and growth of the digital modalities. The authors performed a multiobserver study to determine the performance of radiologists reading posteroanterior conventional radiographs, digitized radiographs laser printed onto film, and images displayed on a high-resolution workstation (video monitor). A total of 300 images were evaluated by seven radiologists who recorded their ordinal confidence rating of the presence or absence of one or more of the following abnormalities: interstitial disease, nodule, and pneumothorax. Receiver operating characteristic analysis showed statistically significant differences for the detection of different abnormalities by individual readers. The group as a whole showed a significant reduction in observer performance for the detection of interstitial disease and pneumothorax when the laser-printed radiographs or the workstation was used rather than conventional radiographs.

Computer Systems↗

PubMed1992

Subperiosteal resorption: effect of full-frame image compression of hand radiographs on diagnostic accuracy.

Image compression is essential to handle a large volume of digital images, including computed tomographic, magnetic resonance, computed radiographic, and digitized images in a digital radiology operation. Developed during the past few years, full-frame bit allocation performed with the cosine transform technique has been proved to be an excellent irreversible image compression method. This article describes the effect, on the accuracy of diagnosis of subperiosteal resorption, of using the hardware compression module to produce hand radiographs. Receiver operating characteristic analysis of the interpretation of 71 radiographs by five observers demonstrated that there is no statistically significant difference in diagnostic accuracy between the original radiographs and compressed and reconstructed images obtained with a compression ratio as high as 20:1.

Bone Resorption↗

PubMed1991

Trends in future urodynamics: computer support-data base-digitized imaging.

The use of computers in urodynamics must be based preferably on the structure of the urodynamic investigation itself. This enables implementation of computerized systems in the urodynamic laboratory in the most natural way and provides transparency of urodynamic software for the investigators. Additionally, the algorithms of the urodynamic software then can provide for a urodynamic investigation following a logical path based on the patient's history and clinical data and (automatically interpreted) results from earlier steps in the urodynamics. As an extension of this structured logical reasoning, the computer use in urodynamics can be extended to include validation and decision rules, comprising measurement data and rules for interpretation and combination of history, clinical and measurement data. Conclusions will be presented then in the form of a preliminary differential diagnosis, including the odds for each of the possible diagnoses. These kinds of computerized interpretation systems will be validated by comparison with the classical clinical diagnoses and are generally known as expert systems. These systems rely on logical branching-as opposed to systems that are statistical in nature and use large data bases to classify individual data into known groups. Data bases will remain for the purpose of documentation, based on individual patients and comprising all patient data-comparable to the existing patient files in the hospital's archives. The computer files have to include also the original data from functional studies like urodynamics-and not just the abstracted conclusions-and from imaging techniques. Intelligent compression of data prevents the data bases from exploding. Digital imaging techniques combined with computerized urodynamic investigations open possibilities for dynamic analysis of morphologic data and combination thereof with urodynamic measurement data.

Databases, Factual↗