Automated Billing Code Retrieval from MRI Scanner Log Data.

Although the level of digitalization and automation steadily increases in radiology, billing coding for magnetic resonance imaging (MRI) exams in the radiology department is still based on manual input from the technologist. After the exam completion, the technologist enters the corresponding exam codes that are associated with billing codes in the radiology information system. Moreover, additional billing codes are added or removed, depending on the performed procedure. This workflow is time-consuming and we showed that billing codes reported by the technologists contain errors. The coding workflow can benefit from an automated system, and thus a prediction model for automated assignment of billing codes for MRI exams based on MRI log data is developed in this work. To the best of our knowledge, it is the first attempt to focus on the prediction of billing codes from modality log data. MRI log data provide a variety of information, including the set of executed MR sequences, MR scanner table movements, and given a contrast medium. MR sequence names are standardized using a heuristic approach and incorporated into the features for the prediction. The prediction model is trained on 9754 MRI exams and tested on 1 month of log data (423 MRI exams) from two MRI scanners of the radiology site for the Swiss medical tariffication system Tarmed. The developed model, an ensemble of classifier chains with multilayer perceptron as a base classifier, predicts medical billing codes for MRI exams with a micro-averaged F1-score of 97.8% (recall 98.1%, precision 97.5%). Manual coding reaches a micro-averaged F1-score of 98.1% (recall 97.4%, precision 98.8%). Thus, the performance of automated coding is close to human performance. Integrated into the clinical environment, this work has the potential to free the technologist from a non-value adding an administrative task, therefore enhance the MRI workflow, and prevent coding errors.

Age and gender dependence of human cardiac phosphorus metabolites determined by SLOOP 31P MR spectroscopy.

The aim of this study was to apply (31)P magnetic resonance spectroscopy (MRS) using spatial localization with optimal point spread function (SLOOP) to investigate possible age and gender dependencies of the energy metabolite concentrations in the human heart. Thirty healthy volunteers (18 males and 12 females, 21-67 years old, mean = 40.7 years) were examined with the use of (31)P-MRS on a 1.5 T scanner. Intra- and interobserver variability measures (determined in eight of the volunteers) were both 3.8% for phosphocreatine (PCr), and 4.7% and 8.3%, respectively, for adenosine triphosphate (ATP). High-energy phosphate (HEP) concentrations in mmol/kg wet weight were 9.7 +/- 2.4 (age < 40 years, N = 16) and 7.7 +/- 2.5 (age >or= 40 years, N = 14) for PCr, and 5.1 +/- 1.0 (age < 40 years) and 4.1 +/- 0.8 (age >or= 40 years) for ATP, respectively. Separated by gender, PCr concentrations of 9.2 +/- 2.4 (men, N = 18) and 8.0 +/- 2.8 (women, N = 12) and ATP concentrations of 4.9 +/- 1.0 (men) and 4.2 +/- 0.9 (women) were measured. A significant decrease of PCr and ATP was found for volunteers older than 40 years (P < 0.05), but the differences in metabolic concentrations between both sexes were not significant. In conclusion, age has a minor but still significant impact on cardiac energy metabolism, and no significant gender differences were detected.

Auto-SENSE perfusion imaging of the whole human heart.

PURPOSE: To show the application of auto-sensitivity encoding (SENSE)-a self-calibrating parallel imaging technique-to first pass perfusion imaging of the whole human heart. MATERIALS AND METHODS: The self-calibrating parallel imaging method auto-SENSE was implemented for a saturation recovery turbo-fast low-angle shot (FLASH) sequence on a 1.5-T scanner using a standard four-element body phased array coil. By reducing the acquisition time per slice by a factor of two compared to conventional turbo FLASH imaging, the number of imaged slices could be doubled to six to ten with an unchanged temporal resolution of one image per heartbeat. This technique has been tested in eight healthy volunteers for contrast-enhanced heart perfusion imaging. RESULTS: Auto-SENSE heart perfusion imaging with improved coverage of the human heart could be performed successfully in all volunteers. A first quantitative comparison of perfusion values between the auto-SENSE and the non-SENSE techniques shows good agreement. CONCLUSION: Auto-SENSE allows perfusion imaging of the whole human heart without gaps.

Absolute concentrations of high-energy phosphate metabolites in normal, hypertrophied, and failing human myocardium measured noninvasively with (31)P-SLOOP magnetic resonance spectroscopy.

OBJECTIVE: The purpose of the present study was to measure absolute concentrations of phosphocreatine (PCr) and adenosine triphosphate (ATP) in normal, hypertrophied, and failing human heart. BACKGROUND: Conflicting evidence exists on the extent of changes of high-energy phosphate metabolites in hypertrophied and failing human heart. Previous reports using phosphorus-31 magnetic resonance spectroscopy ((31)P-MRS) have quantified metabolites in relative terms only. However, this analysis cannot detect simultaneous reductions. METHODS: Four groups of subjects (n = 10 each), were studied: volunteers and patients with hypertensive heart disease (HHD), aortic stenosis, and dilated cardiomyopathy (DCM). Left ventricular (LV) function and mass were measured by cine magnetic resonance imaging. Absolute and relative concentrations of PCr and ATP were determined by (31)P-MRS with spatial localization with optimum point spread function. RESULTS: Left ventricular ejection fraction remained normal in HHD and aortic stenosis, but was severely reduced to 18% in DCM; LV mass was increased by 55%, 79%, and 68% respectively. In volunteers, PCr and ATP concentrations were 8.82 +/- 1.30 mmol/kg wet weight and 5.69 +/- 1.02 mmol/kg wet weight, and the PCr/ATP ratio was 1.59 +/- 0.33. High-energy phosphate levels were unaltered in HHD. In aortic stenosis, PCr was decreased by 28%, whereas ATP remained constant. In DCM, PCr was reduced by 51%, ATP by 35%, and reduction of the PCr/ATP ratio by 25% was of borderline significance (p = 0.06). Significant correlations were observed among energetic and functional variables, with the closest relations for PCr. CONCLUSIONS: In human heart failure due to DCM, both PCr and ATP are significantly reduced. Ratios of PCr to ATP underestimate changes of high-energy phosphate levels.