RENEX: an expert system for the interpretation of 99mTc-MAG3 scans to detect renal obstruction.

A renal expert system (RENEX) has been developed to assist physicians detect renal obstruction in patients undergoing pre- and postfurosemide 99mTc-mercaptoacetyltriglycine (99mTc-MAG3) scans. RENEX uses quantitative parameters extracted from the dynamic renal scan data and heuristic rules in the form of a knowledge base (KB) obtained from expert interpreters to conclude whether a kidney is obstructed. METHODS: Normal limits were established for 47 quantitative parameters extracted from the 99mTc-MAG3 scans of 100 potential renal donors. From these data the domain expert estimated 5 boundary conditions for each parameter: (i) definitely abnormal, (ii) probably abnormal, (iii) equivocal, (iv) probably normal, and (v) definitely normal. A sigmoid-type curve was then generated from these 5 boundary conditions, creating a parameter knowledge library used for converting the value of a prospective patient's individual quantitative parameters to a certainty factor (CF). Sixty heuristic rules were extracted from the domain expert to generate the KB for detecting obstruction. A forward-chaining inference engine was developed using the MYCIN combinatories (an approximation of Bayes theorem) to determine obstruction. A justification engine was implemented, which recorded the sequence of each rule that was fired and the current CF value of all input and output parameters at the time of instantiation to track and justify the logic of the conclusions. The entire system was fine tuned and tested using a pilot group of 32 patients (11 males, 21 females; mean age, 56.8 +/- 17.2 y; 63 kidneys) deemed by an expert panel to have 41 unobstructed kidneys, 13 obstructed kidneys,and 9 equivocal findings. RESULTS: RENEX agreed with the expert panel in 92% (12/13) of the obstructed kidneys, 93% (38/41) of the unobstructed kidneys, and 78% (7/9) of the kidneys interpreted as equivocal for obstructions. Processing time per patient was practically instantaneous using a 3.0-GHz personal computer programmed using interactive data language. CONCLUSION: We have developed a renal expert system for detecting renal obstruction using pre- and postfurosemide 99mTc-MAG3 renal scans, at a standardized expert level. These encouraging preliminary results warrant a prospective study in a large population of patients with and without renal obstruction to establish the diagnostic performance of this system.     

A software engine to justify the conclusions of an expert system for detecting renal obstruction on 99mTc-MAG3 scans.

The purposes of this study were to describe and evaluate a software engine to justify the conclusions reached by a renal expert system (RENEX) for assessing patients with suspected renal obstruction and to obtain from this evaluation new knowledge that can be incorporated into RENEX to attempt to improve diagnostic performance. METHODS: RENEX consists of 60 heuristic rules extracted from the rules used by a domain expert to generate the knowledge base and a forward-chaining inference engine to determine obstruction. The justification engine keeps track of the sequence of the rules that are instantiated to reach a conclusion. The interpreter can then request justification by clicking on the specific conclusion. The justification process then reports the English translation of all concatenated rules instantiated to reach that conclusion. The justification engine was evaluated with a prospective group of 60 patients (117 kidneys). After reviewing the standard renal mercaptoacetyltriglycine (MAG3) scans obtained before and after the administration of furosemide, a masked expert determined whether each kidney was obstructed, whether the results were equivocal, or whether the kidney was not obstructed and identified and ranked the main variables associated with each interpretation. Two parameters were then tabulated: the frequency with which the main variables associated with obstruction by the expert were also justified by RENEX and the frequency with which the justification rules provided by RENEX were deemed to be correct by the expert. Only when RENEX and the domain expert agreed on the diagnosis (87 kidneys) were the results used to test the justification. RESULTS: RENEX agreed with 91% (184/203) of the rules supplied by the expert for justifying the diagnosis. RENEX provided 103 additional rules justifying the diagnosis; the expert agreed that 102 (99%) were correct, although the rules were considered to be of secondary importance. CONCLUSION: We have described and evaluated a software engine to justify the conclusions of RENEX for detecting renal obstruction with MAG3 renal scans obtained before and after the administration of furosemide. This tool is expected to increase physician confidence in the interpretations provided by RENEX and to assist physicians and trainees in gaining a higher level of expertise.     

iRENEX: a clinically informed decision support system for the interpretation of 99mTc-MAG3 scans to detect renal obstruction

Purpose

Decision support systems for imaging analysis and interpretation are rapidly being developed and will have an increasing impact on the practice of medicine. RENEX is a renal expert system to assist physicians evaluate suspected obstruction in patients undergoing mercaptoacetyltriglycine (MAG3) renography. RENEX uses quantitative parameters extracted from the dynamic renal scan data using QuantEM?II and heuristic rules in the form of a knowledge base gleaned from experts to determine if a kidney is obstructed; however, RENEX does not have access to and could not consider the clinical information available to diagnosticians interpreting these studies. We designed and implemented a methodology to incorporate clinical information into RENEX, implemented motion detection and evaluated this new comprehensive system (iRENEX) in a pilot group of 51 renal patients.

Methods

To reach a conclusion as to whether a kidney is obstructed, 56 new clinical rules were added to the previously reported 60 rules used to interpret quantitative MAG3 parameters. All the clinical rules were implemented after iRENEX reached a conclusion on obstruction based on the quantitative MAG3 parameters, and the evidence of obstruction was then modified by the new clinical rules. iRENEX consisted of a library to translate parameter values to certainty factors, a knowledge base with 116 heuristic interpretation rules, a forward chaining inference engine to determine obstruction and a justification engine. A clinical database was developed containing patient histories and imaging report data obtained from the hospital information system associated with the pertinent MAG3 studies. The system was fine-tuned and tested using a pilot group of 51 patients (21 men, mean age 58.2?±?17.1?years, 100 kidneys) deemed by an expert panel to have 61 unobstructed and 39 obstructed kidneys.

Results

iRENEX, using only quantitative MAG3 data agreed with the expert panel in 87?% (34/39) of obstructed and 90?% (55/61) of unobstructed kidneys. iRENEX, using both quantitative and clinical data agreed with the expert panel in 95?% (37/39) of obstructed and 92?% (56/61) of unobstructed kidneys. The clinical information significantly (p?Conclusion Our renal expert system for detecting renal obstruction has been substantially expanded to incorporate the clinical information available to physicians as well as advanced quality control features and was shown to interpret renal studies in a pilot group at a standardized expert level. These encouraging results warrant a prospective study in a large population of patients with and without renal obstruction to establish the diagnostic performance of iRENEX.     

Diagnostic performance of an expert system for the interpretation of myocardial perfusion SPECT studies.

An expert system (PERFEX) developed for the computer-assisted interpretation of myocardial perfusion SPECT studies is now becoming widely available. To date, a systematic validation of the diagnostic performance of this expert system for the interpretation of myocardial perfusion SPECT studies has not been reported. METHODS: To validate PERFEX's ability to detect and locate coronary artery disease (CAD), we analyzed 655 stress/rest myocardial perfusion prospective SPECT studies in patients who also underwent coronary angiography. The patient population comprised CAD patients (n = 480) and healthy volunteers (n = 175) (449 men, 206 women). Data from 461 other patient studies were used to implement and refine 253 heuristic rules that best correlated the presence and location of left ventricular myocardial perfusion defects on SPECT studies with angiographically detected CAD and with human expert visual interpretations. Myocardial perfusion defects were automatically identified as segments with counts below sex-matched normal limits. PERFEX uses the certainty of the location, size, shape, and reversibility of the perfusion defects to infer the certainty of the presence and location of CAD. The visual interpretations of tomograms and polar maps, vessel stenosis from coronary angiography, and PERFEX interpretations were all accessed automatically from databases and were used to automatically generate comparisons between diagnostic approaches. RESULTS: Using the physician's reading as a gold standard, PERFEX's sensitivity and specificity levels for detection and localization of disease were, respectively, 83% and 73% for CAD, 76% and 66% for the left anterior descending artery, 90% and 70% for the left circumflex artery, and 74% and 79% for the right coronary artery. These results were extracted from a receiver operating characteristic curve using the average optimal input certainty factor. CONCLUSION: This study shows that the diagnostic performance of PERFEX for interpreting myocardial perfusion SPECT studies is comparable with that of nuclear medicine experts in detecting and locating CAD.     

Comparison of 99mTc complexes for renal imaging.

The distribution of 17 different agents for renal imaging was compared in the rabbit by organ radioassay at 1 hr. Similarly, 99mTc complexes of iron-ascorbate, glucoheptonate (GHA) and 2,3-dimercaptosuccinic acid (DMS), and 203Hg-chlormerodrin were compared in the dog. The distribution of 99mTc-GHA and DMS was assessed in the human by blood and urinary clearance, external renal measurements, and scintillation camera imaging, and compared with older renal radiopharmaceuticals. Radiation dose estimates, based chiefly on human data, were calculated. Technetium-99m-DMS reaches a high concentration in the renal cortex and its urinary excretion rate and blood clearance are slow. It is excellent for imaging the renal parenchyma without activity in pelvocalyceal collecting system. However, it readily oxidizes and must be used within 30 min of preparation. The biologic distribution of 99mTc-GHA is similar to gluconate and iron-ascorbate complex. Its renal concentration is not as great as that of DMS but its blood and urinary clearances are much faster, resulting in lower radiation doses to most organs. Early camera images with this agent usually demonstrate both the renal parenchyma and collecting system. In later images, ther is excellent demonstration of the parenchyma alone, superior to that obtained with 99mTc-Sn-DTPA. It is a very stable complex and may be used for at least 5 hr after preparation. All radioactive renal agents examined to date have a significant concentration in the liver, making an accurate quantitative comparison between the two kidneys difficult.     

Quantitation of renal function with technetium-99m MAG3

The technetium-labeled hippuran analog [99mTc]MAG3 was compared with [131I]hippuran in 50 patients using a quantitative renal function protocol that includes: (a) estimation of effective renal plasma flow by a single-injection, single-sample plasma clearance method, (b) determination of relative function of right and left kidney from the initial count rate over each kidney, and (c) comparison of recovered urine activity with plasma disappearance. This protocol is suitable for routine clinical use, and, in fact, has been used heavily at our clinic for a number of years. By slight modification of the formulas, the results obtained with [99mTc]MAG3 agreed well with those using [131I]hippuran. We conclude that [99mTc]MAG3 can be substituted for [131I]hippuran in the quantitative protocol, with the better image quality and lower radiation dose (in abnormals) of a technetium-labeled agent.     

Technetium-99m MAG3 renal scintigraphy with demonstration of aortic dissection

Demonstration of type B aortic dissection is rare during renal scintigraphy. The discordant radionuclide pattern of asymmetric renal flow with equivalent renal function and excretion has been previously reported in aortic dissection. However, delayed scintigraphic features of the false lumen have not been described. The author presents such a case with persistent technetium-99m MAG3 accumulation in the posterior mediastinum on postvoid planar imaging.     

Comparison of Tc-99m MAG3 and Tc-99m DTPA in renal transplant patients with impaired renal function

Tc-99m mercaptoacetyltriglycine (MAG3) is a new Tc-99m renal agent that compares favorably to I-131 Hippuran in animal models, normal volunteers, and patients. Based on the fact that Tc-99m MAG3 has a much more rapid clearance than Tc-99m DTPA and a smaller volume of distribution, it was postulated that the image quality of Tc-99m MAG3 studies should be superior to scans obtained using Tc-99m DTPA, particularly in patients with impaired renal function. To test this hypothesis, Tc-99m DTPA and MAG3 images were obtained in three transplant patients during periods of stable but impaired renal function. In one study, the Tc-99m DTPA study was potentially misleading, whereas the Tc-99m MAG3 examination assessed the clinical situation correctly. In all three cases, the Tc-99m MAG3 images were superior.     

Comparison of technetium-99m MAG3 kit with HPLC-purified technetium-99m MAG3 and OIH in rats

Technetium-99m (99mTc) mercaptoacetylglycylglycylyglycine (MAG3) in high (greater than or equal to 95%) radiochemical purity is prepared from lyophilized kits containing benzoylMAG3, sodium tartrate, lactose, and stannous chloride by adding sodium [99mTC]pertechnetate and heating the contents briefly. Constant-infusion renal whole-blood clearance obtained with [99mTc] MAG3 kits was compared with that obtained with high performance liquid chromatography (HPLC) pure [99mTc]MAG3 and with co-infused iodine-131 (131I) iodohippurate (OIH) in anesthetized rats. Average renal whole-blood clearance of [99mTc]MAG3 from kits was 3.9 +/- 0.4 ml/min/100 g body weight (mean +/- s.e.m. n = 5) and that for HPLC-pure [99mTc]MAG3 was 4.6 +/- 0.3 (n = 3). Renal whole-blood clearance ratios for [99mTc]MAG3 to co-infused iodine-131 (131I) OIH were greater than unity for both kit formulation (1.7 +/- 0.1) and HPLC-pure [99mTc]MAG3 (1.9 +/- 0.2). Differences in these two measures were not significant. Plasma binding (determined from blood drawn at the end of the infusion) of [99mTc]MAG3 prepared from both kits (75 +/- 2%, n = 4) and HPLC-separation (76 +/- 4%) were greater than that of [131I]OIH in corresponding plasma samples (31 +/- 1% and 32 +/- 2%) respectively). Renograms performed in anesthetized rats revealed no statistically significant differences between kit-prepared [99mTc]MAG3 and [131I]OIH in terms of time-to-peak renal activity (5.0 +/- 1.7 min, n = 6; and 2.2 +/- 0.2 min, n = 3, mean +/- s.e.m. for [99mTc]MAG3 and [131I]OIH, respectively), in terms of time to fall to half-maximal activity (15.3 +/- 2.4 min and 9.6 +/- 2.1 min, respectively), or in terms of fraction of peak radioactivity in right kidney (0.53 +/- 0.01 for both substances). To assess possible interference from hepatobiliary uptake and excretion in renal failure, radioactivity in liver regions of interest was followed by gamma camera scintigraphy for 30 min after intravenous injection of [131I]OIH and kit and HPLC-purified [99mTc]MAG3 in anesthetized rats rendered anephric by ligating renal peduncles. Liver activity was 25% of total for both preparations of [99mTc]MAG3 and was 22% of total for [131I]OIH. There were no significant differences among the substances.     

Comparison of iodine-131 OIH and technetium-99m MAG3 renal imaging in volunteers

Animal studies have suggested that the nonisomeric N3S triamide mercaptide ligand, 99mTc mercaptoacetyltriglycine (MAG3), may provide a satisfactory 99mTc-labeled replacement for 131I hippurate (OIH). Sequential 30-min [99mTc]MAG3 (5-10 mCi) and [131I]OIH (300 microCi) imaging studies were performed in ten normal volunteers in order to compare the image quality, renal excretion, blood clearance, and time to peak height of the renogram curve. In addition, [99mTc] MAG3 (5 mCi) and [131I]OIH (150 microCi) were administered simultaneously in eight volunteers for comparison of 180-min blood and plasma clearances and urine excretion. In the sequential imaging studies, the blood clearance of [99mTc]MAG3 was more rapid than [131I]OIH with a mean clearance of 1.30 l/min compared with 0.88 l/min for [131I]OIH (p less than 0.05). Seventy-three percent of the injected dose of the MAG3 was excreted by 30 min compared with 66.8% for [131I]OIH. Whole kidney and cortical renogram curves showed no significant difference in the time to peak height for MAG3 and [131I]OIH. In all subjects, the quality of the [99mTc]MAG3 images were clearly superior to [131I]OIH. Following simultaneous injection, blood and plasma clearances for [131I]OIH were more rapid than MAG3 when determined for multiple time intervals from 0-30 to 0-180 min (p less than or equal to 0.05). The 0-30-min clearances of MAG3 and [131I]OIH were only slightly greater than the 0-180-min clearances and can be used to obtain valid comparisons of the two agents. As in the sequential study, 30-min urine excretion was greater for MAG3 than [131I]OIH (73.1 compared with 69.6%) but the difference was not statistically significant. Although the differences in the MAG3 clearances following sequential and simultaneous administration are not satisfactorily explained, the fact that both clearances were rapid, the MAG3 and OIH renogram curves were quite similar, and 30-min urine excretions of MAG3 and OIH were essentially identical suggests that MAG3 may become a 99mTc replacement for [13I]OIH and further clinical evaluation is warranted.     

Dynamic SPECT evaluation of renal plasma flow using technetium-99m MAG3 in kidney transplant patients.

OBJECTIVE: The purpose of this study was to evaluate Patlak's graphic analysis method to determine renal plasma flow (RPF) in kidney transplants. METHODS: Dynamic SPECT was performed with 99mTc MAG3 in 12 patients. RPF was determined by both Patlak's graphic analysis method and Russell's method. Ventral, central and dorsal tomographic images of the transplanted kidney were reconstructed to estimate intrarenal distribution of renal plasma flow. RESULTS: The renal influx constant (Ku) calculated by Patlak's graphic analysis method was reproducible and correlated with both serum creatinine (r = -0.88, P < 0.001) and blood urea nitorogen levels (r = -0.82, P < 0.002). However, a significant difference was noted between the RPF values derived from Patlak's graphic analysis method and Russell's method. Ku was corrected by a factor calculated from raw and reconstructed data, and the resulting values were in fair agreement with those determined by Russell's method. CONCLUSION: These methods are useful in evaluating the function of transplanted kidneys.     

81mKr ventilation and 99mTc perfusion scans in chest disease: comparison with standard radiographs.

In 75 patients with various pulmonary disorders, ventilation and perfusion scans were obtained in multiple views with the 81mKr/99mTc technique and compared with an evaluation of regional ventilation and perfusion derived from the standard chest radiograph. In emphysema, the chest film correlated poorly with ventilation-perfusion scans, showing a trend to underestimate the functional impairment. In chronic bronchitis and asthma, large segmental defects observed on both ventilation and perfusion scans were associated with a normal chest radiograph. Typical findings in pulmonary embolism were segmental defects on perfusion scan with normal ventilation scan and clear lung fields on the chest film. In chronic left heart disease, plain films were inaccurate in predicting alteration of the base-to-apex perfusion gradient observed on the scan.