MAG3Renography

Introduction: The majority of the estimated 590,000 radionuclide renal scans performed annually in the United States are conducted at sites that perform fewer than 3 studies per week. Due to the relative infrequency of renal studies, some trainees may fail to acquire the expertise needed for a competent interpretation, a problem shared by radiologists whose nuclear medicine training was limited to 3-4 months. Limited training and experience may lead to incorrect scan interpretation, discourage use of the procedure, and negatively impact patient care. To address this problem, we developed software (RENEX) to assist in the interpretation of Tc-99m MAG3 diuretic renal scans [1-3]. RENEX is a heuristic or rule based decision support system that uses quantitative data derived from the renogram to determine the status of a potentially obstructed kidney (obstructed, indeterminate, or not obstructed). RENEX provides the justification (rules) for its interpretation and specifies a level of confidence [1,4]. RENEX has a diagnostic accuracy comprable to that of experts and greater diagnostic accuracy than that of nuclear medicine residents with one year of training; the diagnostic accuracy of these experienced residents improved when they reinterpreted the cases with access to RENEX [5]. RENEX also outperformed a second set of experienced nuclear medicine residents and diagnostic accuracy again improved with access to RENEX [6]. Following exposure to RENEX, these residents interpreted a new set of cases and had better agreement with experts than that obtained on the initial set [6]. Methods: We designed a website to supplement resident and physician exposure to Tc-99m MAG3 diuretic studies and make the teaching components of RENEX more broadly available. Results: The website is organized into a Home Page, Introduction Pages, a Case Review Page, RENEX and Expert Interpretation Pages. The Introduction Pages provide a sample study accompanied by an explanation of relevant renogram parameters, links to references and a description of RENEX. The user scores each kidney on the Case Review Page as obstructed, indeterminate, or not obstructed using a numerical scoring system. The RENEX Interpretation (score) and justification becomes available to the user after the kidneys in the assigned cases have been scored. After reviewing the scores and justification by RENEX, users are asked to re- score each kidney. They may re-enter their original scores or modify their initial scores based on input from RENEX. Once the cases re-scored, the user is given access to the scores and comments of 3 experienced readers Conclusions: This interactive web based format allows users to gain additional experience and supplement their diagnostic acumen by comparing their interpretations with the interpretations and rationale provided by RENEX and experts.

The goal of artificial intelligence, expert systems, decision support systems and computer assisted diagnosis (CAD) in imaging is the development and implementation of software to assist in the detection and evaluation of abnormalities, to alert physicians to cognitive biases, to reduce intra and inter-observer variability and to facilitate the interpretation of studies at a faster rate and with a higher level of accuracy. These developments are needed to meet the challenges resulting from a rapid increase in the volume of diagnostic imaging studies coupled with a concurrent increase in the number and complexity of images in each patient data. The convergence of an expanding knowledge base and escalating time constraints increases the likelihood of physician errors. Errors are even more likely when physicians interpret low volume studies such as 99mTc-MAG3 diuretic scans where imagers may have had limited training or experience. Decision support systems include neural networks, case-based reasoning, expert systems and statistical systems. iRENEX (renal expert) is an expert system for diuretic renography that uses a set of rules obtained from human experts to analyze a knowledge base of both clinical parameters and quantitative parameters derived from the renogram. Initial studies have shown that the interpretations provided by iRENEX are comparable to the interpretations of a panel of experts. iRENEX provides immediate patient specific feedback at the time of scan interpretation, can be queried to provide the reasons for its conclusions and can be used as an educational tool to teach trainees to better interpret renal scans. iRENEX also has the capacity to populate a structured reporting module and generate a clear and concise impression based on the elements contained in the report; adherence to the procedural and data entry components of the structured reporting module assures and documents procedural competency. Finally, although the focus is CAD applied to diuretic renography, this review offers a window into the rationale, methodology and broader applications of computer assisted diagnosis in medical imaging.