Conversion of teaching file cases from film to digital format: a comparison between use of a diagnostic-quality digitizer and use of a flatbed scanner with transparency adapter

RATIONALE AND OBJECTIVES: The authors' institution had decided to convert its radiology teaching files from film to digital media. This study was performed to determine the simplest method for converting the analog film images to digital images without a subsequent loss in diagnostic accuracy. MATERIALS AND METHODS: Twenty chest radiographs that demonstrated interstitial lung disease were randomly selected from the departmental teaching files and matched with 20 control radiographs from healthy adults. Analog film images were converted with both a diagnostic-quality film image digitizer (digitized) and a flatbed scanner equipped with a transparency adapter (scanned). Three radiology faculty members reviewed a mixed set of corresponding analog film, digitized, and scanned images. Reviewers judged whether each image depicted interstitial lung disease, indicated their level of confidence in the diagnosis, and rated each image for quality. Image quality was assessed by each reviewer subjectively at the time of viewing the individual image, without regard to other images. A one-way analysis of variance was performed to determine whether there was a statistically significant difference in diagnostic accuracy between the three image formats. Agreement in diagnosis between corresponding images in the three different formats was evaluated for each reviewer with the McNemar test. RESULTS: There was no statistically significant difference in diagnostic accuracy between analog film and scanned images, but there was such a difference between these two groups and digitized images. Accuracy was 97% for analog film, 94% for scanned, and 89% for digitized images. Results of the McNemar test showed no statistically significant difference in agreement between the analog film images and the scanned images for any of the reviewers (P > .05). CONCLUSION: A high-end flatbed scanner with transparency adapter provided accurate, simple, and inexpensive conversion of analog film teaching files to digital format, with no loss of the ability to detect or diagnose subtle abnormalities such as interstitial lung disease.     

Tutor versus computer: a prospective comparison of interactive tutorial and computer-assisted instruction in radiology education

RATIONALE AND OBJECTIVES: This study compared the educational effectiveness of an interactive tutorial with that of interactive computer-assisted instruction (CAI) and determined the effects of personal preference, learning style, and level of training. MATERIALS AND METHODS: Fifty-four medical students and four radiology residents were prospectively, randomly assigned to receive instruction from different sections of an interactive tutorial and an interactive CAI module. Participants took tests of factual knowledge at the beginning and end of the instruction and a test of visual diagnosis at the end. They completed questionnaires to evaluate their preferred learning styles objectively and to elicit their subjective attitudes toward the two formats. Mean test scores of the tutorial and CAI groups were compared by means of analysis of covariance and two-tailed repeated-measures F test. RESULTS: Both the tutorial and CAI groups demonstrated significant improvement in posttest scores (P < .01 and P < .01, respectively) with the tutorial group's mean posttest score marginally but significantly higher (32.84 vs 28.13, P < .001). There were no significant interaction effects with participants' year of training (P = .845), objectively evaluated preferred learning style (P = .312), subjectively elicited attitude toward learning with CAI (P = .703), or visual diagnosis score (tutorial, 7.61; CD-ROM, 7.75; P = .79). CONCLUSION: Interactive tutorial and optimal CAI are both effective instructional formats. The tutorial was marginally but significantly more effective at teaching factual knowledge, an effect unrelated to students' year of training, learning style, or stated enjoyment of CAI. The superiority of the tutorial is expected to increase when it is compared with commercially expedient CAI modules.     

Incorporating electronic media into medical student education: a survey of AMSER members on computer and web use in radiology courses. Alliance of Medical Student Educators in Radiology

RATIONALE AND OBJECTIVES: The purpose of this study was to define the current use of information technology in radiology tutorials for medical students. MATERIALS AND METHODS: The authors conducted a Web-based survey of directors of medical school courses in radiology. The survey dealt with the details of the courses and the use of computers and the Web during the courses. RESULTS: There were 48 responses. Most radiology courses were elective (73%) and were offered monthly. Most institutions (79%) had picture archiving and communication systems (PACS) available or were completely filmless. The teaching case presentations, however, often included film images displayed on a view box or by an overhead projector. Computers dedicated to student use were uncommon (28%). The Web was used infrequently as a teaching resource, and a Web site was not available in most courses. Computer technical support was variable and usually provided by the course director. Course directors at institutions with PACS were more likely to use digital technology for case presentations and more likely to use the Web for teaching purposes. CONCLUSION: Despite the widespread use of digital technology and PACS in the field of radiology, digital technology is underused in radiology courses. However, departments with PACS tend to use digital technology more frequently in education than do departments without PACS.     

COMPARE radiology: creating an interactive Web-based training program for radiology with multimedia authoring software

RATIONALE AND OBJECTIVES: Computer-based training has two primary benefits: Content can be presented interactively, and students can choose the time, place, and pace of learning. As a subject of medical education, radiology lends itself particularly well to computer-based training because of its highly visual content. To improve the efficiency of radiology training at their institution, the authors decided to create an interactive Web-based training site. MATERIALS AND METHODS: Working with a group of medical students knowledgeable in multimedia authoring, the authors used authoring software to create "COMPARE Radiology," an interactive training program that follows the modality-based structure of the undergraduate curriculum for radiology at the University of Erlangen-Nuremberg, Erlangen, Germany, and at medical schools worldwide. RESULTS: The Web-based program offers cases and exercises in radiographic anatomy at different selectable levels of difficulty, allowing users to test and build their knowledge of radiology. Pathologic images are initially presented without any further information. Additional information (patient history, laboratory results, reports from other imaging studies, and normal images for comparison) can be retrieved selectively and successively. Further information regarding the diagnosis and pathologic findings can be found by following links to external Web sites. The COMPARE Radiology program content is extended and updated regularly. The program is subject to internal peer review and can be evaluated by the user online. CONCLUSION: The authors' experience shows that a highly interactive Web-based training program for radiology, tailored to the requirements of the target group, can be developed economically by a team of medical students using an advanced storing system, with the guidance of a radiologist and without the help of professionally trained computer experts.     

Evaluating medical students on radiology clerkships in a filmless environment: use of an electronic test prepared from PACS and digital teaching collection images

RATIONALE AND OBJECTIVES: The competency of medical students in radiology clerkships is traditionally evaluated with film images, projected slides of photographed films, or printed reproductions of films. As radiology departments switch to filmless imaging, it seemed appropriate to determine the feasibility of an electronic evaluation prepared directly from digital images. MATERIALS AND METHODS: The image-based portion of a multiple-choice final examination was prepared as a PowerPoint presentation that included images downloaded from the departmental picture archiving and communication system (PACS) or digital teaching collections. The images were downloaded as bitmap files, imported to Adobe Photoshop for image editing, converted to tagged image file format, and finally imported to PowerPoint, where they were combined with text to create 50 questions. A liquid crystal diode projector displayed the questions, with a timer set to advance them automatically. RESULTS: The examination was easy and inexpensive to prepare (no photography costs). In an initial survey of 25 students, 17 (71%) of 24 students rated the resolution of images as excellent and five (21%) as good. No student gave an image a poor rating. Students preferred that images cover at least 40%-50% of the slides, and most approved of a blue background. An original allowance of 30 seconds per slide was reported to be too fast; the interval was increased to 45 seconds. CONCLUSION: An electronic final examination for medical students, prepared with images downloaded from PACS or digital teaching collections, is feasible, easy to prepare, and cost-effective, and it provides an excellent display of test images.     

Improved Method for Automatic Identification of Lung Regions on Chest Radiographs

RATIONALE AND OBJECTIVES: The authors performed this study to evaluate an algorithm developed to help identify lungs on chest radiographs. MATERIALS AND METHODS: Forty clinical posteroanterior chest radiographs obtained in adult patients were digitized to 12-bit gray-scale resolution. In the proposed algorithm, the authors simplified the current approach of edge detection with derivatives by using only the first derivative of the horizontal and/or vertical image profiles. In addition to the derivative method, pattern classification and image feature analysis were used to determine the region of interest and lung boundaries. Instead of using the traditional curve-fitting method to delineate the lung, the authors applied an iterative contour-smoothing algorithm to each of the four detected boundary segments (costal, mediastinal, lung apex, and hemidiaphragm edges) to form a smooth lung boundary. RESULTS: The algorithm had an average accuracy of 96.0% for the right lung and 95.2% for the left lung and was especially useful in the delineation of hemidiaphragm edges. In addition, it took about 0.775 second per image to identify the lung boundaries, which is much faster than that of other algorithms noted in the literature. CONCLUSION: The computer-generated segmentation results can be used directly in the detection and compensation of rib structures and in lung nodule detection.     

Outcome analysis of patients with acute pancreatitis by using an artificial neural network

RATIONALE AND OBJECTIVES: The authors performed this study to evaluate the ability of an artificial neural network (ANN) that uses radiologic and laboratory data to predict the outcome in patients with acute pancreatitis. MATERIALS AND METHODS: An ANN was constructed with data from 92 patients with acute pancreatitis who underwent computed tomography (CT). Input nodes included clinical, laboratory, and CT data. The ANN was trained and tested by using a round-robin technique, and the performance of the ANN was compared with that of linear discriminant analysis and Ranson and Balthazar grading systems by using receiver operating characteristic analysis. The length of hospital stay was used as an outcome measure. RESULTS: Hospital stay ranged from 0 to 45 days, with a mean of 8.4 days. The hospital stay was shorter than the mean for 62 patients and longer than the mean for 30. The 23 input features were reduced by using stepwise linear discriminant analysis, and an ANN was developed with the six most statistically significant parameters (blood pressure, extent of inflammation, fluid aspiration, serum creatinine level, serum calcium level, and the presence of concurrent severe illness). With these features, the ANN successfully predicted whether the patient would exceed the mean length of stay (Az = 0.83 +/- 0.05). Although the Az performance of the ANN was statistically significantly better than that of the Ranson (Az = 0.68 +/- 0.06, P < .02) and Balthazar (Az = 0.62 +/- 0.06, P < .003) grades, it was not significantly better than that of linear discriminant analysis (Az = 0.82 +/- 0.05, P = .53). CONCLUSION: An ANN may be useful for predicting outcome in patients with acute pancreatitis.     

Evaluation of the quality of self-education mammography material available for patients on the Internet

RATIONALE AND OBJECTIVES: The Internet offers many advantages for educating patients but has no standards for publication. This limitation could negatively affect patient care. The purpose of this study was to evaluate the quality of information on mammography that a patient could find on the Internet. MATERIALS AND METHODS: Three search utilities were used to research the term "mammography." For each utility, the first 50 addresses for Web pages were evaluated (or all the addresses, if fewer than 50 were returned). Web sites selected contained information that could guide an asymptomatic woman in deciding whether to undergo screening mammography. These sites were then evaluated for whether they indicated their sponsorship, authorship, the currency of information, and references. Sites were also noted if they advised women older than 50 years to undergo screening mammography at intervals of longer than 1 year or otherwise severely diminished the role of mammography. RESULTS: Thirty-eight Web sites were identified. Ten indicated authorship, 29 indicated the currency of the information, and 27 provided references. All of the Web sites indicated sponsorship. Three sites recommended screening mammography at intervals of longer than 1 year for women 50 years of age or older. Two sites suggested that mammography is not substantially more sensitive than physical examination. CONCLUSION: Many Web sites do not meet the standards for disseminating information required in professional peer-reviewed journals. Some Web sites contain statements that might lead asymptomatic women over age 50 years to delay screening mammography or to undergo screening at intervals of longer than 1 year.     

Self-test software for PowerPoint: a tool for self-learning

RATIONALE AND OBJECTIVES: We developed self-test software to improve self-learning efficiency using Microsoft PowerPoint data files. CONCLUSION: This tool can be run on IBM-compatible computer under Microsoft Windows. It is a new useful and interactive tool for self-learning. This tool allows users to do view the cases in the PowerPoint data files by random or sequentially. Goal-oriented effective self-learning is possible from methods that conjecture the possible differential diagnosis without promptly seeing correct diagnosis. Thus effective and interactive self-learning is possible.     

Reproducibility of Computer-Aided Detection Marks in Digital Mammography

Objective

To evaluate the performance and reproducibility of a computer-aided detection (CAD) system in mediolateral oblique (MLO) digital mammograms taken serially, without release of breast compression.

Materials and Methods

A CAD system was applied preoperatively to the full-field digital mammograms of two MLO views taken without release of breast compression in 82 patients (age range: 33 - 83 years; mean age: 49 years) with previously diagnosed breast cancers. The total number of visible lesion components in 82 patients was 101: 66 masses and 35 microcalcifications. We analyzed the sensitivity and reproducibility of the CAD marks.

Results

The sensitivity of the CAD system for first MLO views was 71% (47/66) for masses and 80% (28/35) for microcalcifications. The sensitivity of the CAD system for second MLO views was 68% (45/66) for masses and 17% (6/35) for microcalcifications. In 84 ipsilateral serial MLO image sets (two patients had bilateral cancers), identical images, regardless of the existence of CAD marks, were obtained for 35% (29/84) and identical images with CAD marks were obtained for 29% (23/78). Identical images, regardless of the existence of CAD marks, for contralateral MLO images were 65% (52/80) and identical images with CAD marks were obtained for 28% (11/39). The reproducibility of CAD marks for the true positive masses in serial MLO views was 84% (42/50) and that for the true positive microcalcifications was 0% (0/34).

Conclusion

The CAD system in digital mammograms showed a high sensitivity for detecting masses and microcalcifications. However, reproducibility of microcalcification marks was very low in MLO views taken serially without release of breast compression. Minute positional change and patient movement can alter the images and result in a significant effect on the algorithm utilized by the CAD for detecting microcalcifications.     

Pulmonary CT image classification with evolutionary programming

RATIONALE AND OBJECTIVES: It is often difficult to classify information in medical images from derived features. The purpose of this research was to investigate the use of evolutionary programming as a tool for selecting important features and generating algorithms to classify computed tomographic (CT) images of the lung. MATERIALS AND METHODS: Training and test sets consisting of 11 features derived from multiple lung CT images were generated, along with an indicator of the target area from which features originated. The images included five parameters based on histogram analysis, 11 parameters based on run length and co-occurrence matrix measures, and the fractal dimension. Two classification experiments were performed. In the first, the classification task was to distinguish between the subtle but known differences between anterior and posterior portions of transverse lung CT sections. The second classification task was to distinguish normal lung CT images from emphysematous images. The performance of the evolutionary programming approach was compared with that of three statistical classifiers that used the same training and test sets. RESULTS: Evolutionary programming produced solutions that compared favorably with those of the statistical classifiers. In separating the anterior from the posterior lung sections, the evolutionary programming results were better than two of the three statistical approaches. The evolutionary programming approach correctly identified all the normal and abnormal lung images and accomplished this by using less features than the best statistical method. CONCLUSION: The results of this study demonstrate the utility of evolutionary programming as a tool for developing classification algorithms.     

Solitary pulmonary nodule on helical dynamic CT scans: analysis of the enhancement patterns using a computer-aided diagnosis (CAD) system

OBJECTIVE: We wanted to investigate the usefulness of a computer-aided diagnosis (CAD) system in assisting radiologists to diagnosis malignant solitary pulmonary nodules (SPNs), as compared with diagnosing SPNs with using direct personal drawing. MATERIALS AND METHODS: Forty patients with SPNs were analyzed. After the pre-contrast scan was performed, an additional ten series of post-contrast images were obtained at 20-second intervals. Two investigators measured the attenuation values of the SPNs: a radiologist who drew the regions of interest (ROIs), and a technician who used a CAD system. The Bland and Altman plots were used to compare the net enhancement between a CAD system and direct personal drawing. The diagnostic characteristics of the malignant SPNs were calculated by considering the CAD and direct personal drawing and with using Fisher's exact test. RESULTS: On the Bland and Altman plot, the net enhancement difference between the CAD system and direct personal drawing was not significant (within +/- 2 standard deriation). The sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV) and accuracy of diagnosing malignant SPNs using CAD was 92%, 85%, 75%, 96% and 88%, respectively. The sensitivity, specificity, PPV, NPV and accuracy of diagnosing malignant SPNs using direct drawing was 92%, 89%, 79%, 92% and 88%, respectively. CONCLUSION: The CAD system was a useful tool for diagnosing malignant SPNs.     

Multifeature analysis of Gd-enhanced MR images of breast lesions

The objective of this study was to determine whether linear discriminant analysis of different independent features of MR images of breast lesions can increase the sensitivity and specificity of this technique. For MR images of 23 benign and 20 malignant breast lesions, three independent classes of features, including characteristics of Gd-DTPA-uptake curve, boundary, and texture were evaluated. The three classes included five, four and eight features each, respectively. Discriminant analysis was applied both within and across the three classes, to find the best combination of features yielding the highest classification accuracy. The highest specificity and sensitivity of the different classes considered independently were as follows: Gd-up-take curves, 83% and 70%; boundary features, 86% and 70%; and texture, 70% and 75%, respectively. A combination of one feature each from the first two classes and age yielded a specificity of 79% and sensitivity of 90%, whereas highest figures of 93% and 95%, respectively, were obtained when a total of 10 features were combined across different classes. Statistical analysis of different independent classes of features in MR images of breast lesions can improve the classification accuracy of this technique significantly.