David W. Piraino

Prospective study of osseous, articular, and meniscal lesions in recent anterior cruciate ligament tears by magnetic resonance imaging and arthroscopy

Fifty-four patients with anterior cruciate ligament tears that were arthroscopically reconstructed within 3 months of initial injury were prospectively evaluated. Patients with grade 3 medial collateral ligament, lateral collateral ligament, or posterior cruciate ligament tears were excluded. Eighty percent of our patients had a bone bruise present on the magnetic resonance image, with 68% in the lateral femoral condyle. Two of the latter findings—an abnormal articular cartilage signal (P = 0.02) and a thin and impacted subchondral bone (P = 0.03)—had a significant relationship with injury to the overlying articular cartilage. Meniscal tears were found in 56% of the lateral menisci and 37% of the medial menisci. A significant association was present between bone bruising on the lateral femoral condyle and the lateral tibial plateau (P = 0.02). Results of our study support the concept that the common mechanism of injury to the anterior cruciate ligament involves severe anterior subluxation with im paction of the posterior tibia on the anterior femur. Determination of the significance of bone bruising, ar ticular cartilage injury, or meniscal tears will require a long-term followup that includes evaluation for arthritis, stability, and function. These 54 patients represent the first cohort evaluated in this ongoing prospective clinical study.

The influence of the resolution and contrast on measuring the articular cartilage volume in magnetic resonance images

The progression of OA in patients may be followed by measuring the volume of articular cartilage from MR images. We attempted to determine the reproducibility of volume measurements of articular cartilage made from magnetic resonance images of the knees and the dependence of the reproducibility on image resolution and contrast-to-noise. A fat-suppressed 3D technique was used to generate four image sets with different image resolution. Each patient was imaged twice to obtain image pairs at each resolution. To assess the dependence of reproducibility on noise we generated six image sets for each patient by adding noise to the original images and repeating the comparison. On each image set, the femoral, tibial, and patellar cartilage were outlined by a combination of computer and manual methods, and the images were used to calculate the volume of each cartilage plate. Comparing the coefficient of variance between the volume measurements made from the two visits, the volume measurements made from images with the highest resolution (0.275 x 0.275 x 1.0 mm) had the highest reproducibility. The high resolution images of the tibia and femur had the least partial-volume averaging and, as a result, better defined the boundaries between cartilage and adjacent tissues. A different trend was evident for the patella. For studies of osteoarthritis therapies, we recommend using MR images with the highest possible in-plane spatial resolution to provide the most reproducible volume measurements of knee cartilage.

Application of an Artificial Neural Network in Radiographic Diagnosis

The description of 44 cases of bone tumors was used by an artificial neural network to rank the likelihood of 55 possible pathologic diagnoses. The performance of the artificial neural network was compared with the performance of experienced (3 or more years of radiology training) residents and inexperienced (less than 1 year of radiology training) residents. The artificial neural network was trained using descriptions of 110 radiographs of bone tumors with known diagnoses. The descriptions of a separate set of 44 cases were used to test the neural network. The neural network ranked 55 possible pathologic diagnoses on a scale from 1 to 55. Experienced and inexperienced residents also ranked the possible diagnoses in the same 44 cases. Inexperienced residents had a significantly lower mean proportion of diagnoses ranked first or second than did the neural network. Experienced residents had a significantly higher proportion of correct diagnoses ranked first than did the network. Otherwise, a significant difference between the performance of the network and experienced or inexperienced residents was not identified. These results demonstrate that artificial neural networks can be trained to classify bone tumors. Whether neural network performance in classification of bone tumors can be made accurate enough to assist radiologists in clinical practice remains an open question. These preliminary results indicate that further investigation of this technology for interpretation assistance is warranted.

Impact of digital radiography on clinical workflow and patient satisfaction.

Compared to traditional film radiography, digital radiography is believed to improve workflow and patient throughput. Digital radiography permits the technologist to immediately view the quality of the film directly at the modality. Additional workflow improvements, therefore, should be achieved with the integration of the radiology information system (RIS). To learn more about this proposed efficacy, a study was performed at The Cleveland Clinic Foundation (Cleveland, OH) comparing timings in three groups: traditional film radiography; digital radiography; and digital radiography with RIS integration. Our data validated a timesaving of digital radiography over traditional or standard films and an even greater timesaving in a digital radiography/RIS environment. *** DIRECT SUPPORT *** A00RM031 00013

Implementation of an electronic teaching file using web technology

The implementation of an electronic teaching file using web technology is discussed in this article. A web client server model is used for a standard web browser capable of displaying Joint Photographic Experts Group (JPEG) compression images. Like other web-based teaching files, this teaching file in a similar way uses a database containing information. This database section of the teaching file allows flexible database querying and viewing of pages generated by hypertext markup language (HTML). Because the browser client is so flexible, images types such as video and 3D representations with virtual reality markup language (VRML) can be displayed.

A fast and accurate method for registration of MR images of the head

This paper proposes a new fully automated technique that can be used for the registration of medical images of the head. The method uses Chebyshev polynomials in order to approximate and then minimize a novel multiresolutional, signal intensity independent disparity function, which can generally be defined as the mean squared value of the mean weighted ratio of two images. This function is explicitly computed for n Chebyshev points in a geometric transformation parameter interval [-A, +A] transformation units and is approximated using the Chebyshev polynomials for all other points in the interval. For 3D T2-T1 weighted MR registration, 120 experiments with studies from ten patients were performed and showed that n = 4 Chebyshev points for A = 18 transformation units give mean rotational error 0.36 degrees and a mean translational error 0.36 mm. The different noise conditions did not affect the performance of the method. We conclude that the method is suitable for routine clinical applications and that it has significant potential for future development and improvement.

Emergent Diagnoses from a Collective of Radiologists: Algorithmic versus Social Consensus Strategies

Twelve radiologists independently diagnosed 74 medical images. We use two approaches to combine their diagnoses: a collective algorithmic strategy and a social consensus strategy using swarm techniques. The algorithmic strategy uses weighted averages and a geometric approach to automatically produce an aggregate diagnosis. The social consensus strategy used visual cues to quickly impart the essence of the diagnoses to the radiologists as they produced an emergent diagnosis. Both strategies provide access to additional useful information from the original diagnoses. The mean number of correct diagnoses from the radiologists was 50 and the best was 60. The algorithmic strategy produced 63 correct diagnoses and the social consensus produced 67. The algorithm’s accuracy in distinguishing normal vs. abnormal patients (0.919) was significantly higher than the radiologists’ mean accuracy (0.861; p = 0.047). The social consensus’ accuracy (0.951; p = 0.007) showed further improvement.

Transcatheter Aortic Valve Repair, Imaging, and Electronic Imaging Health Record

Degenerative aortic stenosis (AS) is a common valvular pathology in developed nations. Secondary to advanced age and often multiple co-morbidities, a significant percentage of patients are not considered surgical candidates. For these high-risk patients, transcatheter aortic valve replacement (TAVR) is a rapidly emerging less-invasive treatment alternative. Because of the lack of direct exposure and visualization of the operative field, pre-procedural planning and intra-procedural guidance relies on imaging. Large 3-dimensional data files are acquired, which are reconstructed on advanced workstations during review and interpretation. Optimally, the imaging data is organized into a comprehensive digital file as an integral part of the electronic health record (EHR) following the patient. This manuscript will discuss the role of image data management in the context of TAVR.

Transforming the radiological interpretation process: the SCAR TRIP initiative

The Society for Computer Applications in Radiology (SCAR) Transforming the Radiological Interpretation Process (TRIP) Initiative aims to spearhead research, education, and discovery of innovative solutions to address the problem of information and image data overload. The initiative will foster inter-disciplinary research on technological, environmental and human factors to better manage and exploit the massive amounts of data. TRIP will focus on the following basic objectives: improving the efficiency of interpretation of large data sets, improving the timeliness and effectiveness of communication, and decreasing medical errors. The ultimate goal of the initiative is to improve the quality and safety of patient care. Interdisciplinary research into several broad areas will be necessary to make progress in managing the ever-increasing volume of data. The six concepts involved include: human perception, image processing and computer-aided detection (CAD), visualization, navigation and usability, databases and integration, and evaluation and validation of methods and performance. The result of this transformation will affect several key processes in radiology, including image interpretation; communication of imaging results; workflow and efficiency within the health care enterprise; diagnostic accuracy and a reduction in medical errors; and, ultimately, the overall quality of care.

Radiology Image Interpretation System: Modified observer performance study of an image interpretation expert system

Application of computer-based expert systems to diagnostic medical problems has been described in many areas including clinical diagnosis and radiology. Expert systems are computer programs that contain encoded expert knowledge to provide expert advice. A modified observer-performance study was done comparing the efficacy of the Radiology Image Interpretation System (RIIS), an expert system that diagnoses focal bone abnormalities, and radiology residents on a known set of 44 abnormal and 10 normal cases. Modified receiver operating characteristic curves for four inexperienced residents, five experienced residents, and RIIS were generated using the set of known radiographs. The true-positive rates of RIIS and the residents at false-positive rates of 0.05, 0.15, and 0.20 were estimated using the modified receiver operating characteristics curve and were compared using a pairedt test. On the average, the RIIS system was less accurate when compared with experienced and inexperienced residents but the difference was only significant for experienced residents at a false-positive rate of 0.05. RIIS performed better than inexperienced residents when RIIS was used by experienced residents but this difference was not significant.