Artificial Intelligence-Based Prediction of Contrast Medium Doses for Computed Tomography Angiography Using Optimized Clinical Parameter Sets.

OBJECTIVES: In this paper, an artificial intelligence-based algorithm for predicting the optimal contrast medium dose for computed tomography (CT) angiography of the aorta is presented and evaluated in a clinical study. The prediction of the contrast dose reduction is modelled as a classification problem using the image contrast as the main feature. METHODS: This classification is performed by random decision forests (RDF) and k-nearest-neighbor methods (KNN). For the selection of optimal parameter subsets all possible combinations of the 22 clinical parameters (age, blood pressure, etc.) are considered using the classification accuracy and precision of the KNN classifier and RDF as quality criteria. Subsequently, the results of the evaluation were optimized by means of feature transformation using regression neural networks (RNN). These were used for a direct classification based on regressed Hounsfield units as well as preprocessing for a subsequent KNN classification. RESULTS: For feature selection, an RDF model achieved the highest accuracy of 84.42% and a KNN model achieved the best precision of 86.21%. The most important parameters include age, height, and hemoglobin. The feature transformation using an RNN considerably exceeded these values with an accuracy of 90.00% and a precision of 97.62% using all 22 parameters as input. However, also the feasibility of the parameter sets in routine clinical practice has to be considered, because some of the 22 parameters are not measured in routine clinical practice and additional measurement time of 15 to 20 minutes per patient is needed. Using the standard feature set available in clinical routine the best accuracy of 86.67% and precision of 93.18% was achieved by the RNN. CONCLUSION: We developed a reliable hybrid system that helps radiologists determine the optimal contrast dose for CT angiography based on patient-specific parameters.

Random Forest and Gradient Boosted Trees for Patient Individualized Contrast Agent Dose Reduction in CT Angiography.

This work aims to recognize the patient individual possibility of contrast dose reduction in CT angiography. This system should help to identify whether the dose of contrast agent in CT angiography can be reduced to avoid side effects. In a clinical study, 263 CT angiographies were performed and, in addition, 21 clinical parameters were recorded for each patient before contrast agent administration. The resulting images were labeled according to their contrast quality. It is assumed that the contrast dose could be reduced for CT angiography images with excessive contrast. These data was used to develop a model for predicting excessive contrast based on the clinical parameters using logistic regression, random forest, and gradient boosted trees. In addition, the minimization of clinical parameters required was investigated to reduce the overall effort. Therefore, models were tested with all subsets of clinical parameters and each parameter's importance was examined. In predicting excessive contrast in CT angiography images covering the aortic region, a maximum accuracy of 0.84 was achieved by a random forest with 11 clinical parameters; for the leg-pelvis region data, an accuracy of 0.87 was achieved by a random forest with 7 parameters; and for the entire data set, an accuracy of 0.74 was achieved by gradient boosted trees with 9 parameters.

Automatic quality measurement of aortic contrast-enhanced CT angiographies for patient-specific dose optimization.

PURPOSE: Iodine-containing contrast agent (CA) used in contrast-enhanced CT angiography (CTA) can pose a health risk for patients. A system that adjusts the frequently used standard CA dose for individual patients based on their clinical parameters can be useful. As basis the quality of the image contrast in CTA volumes has to be determined, especially to recognize excessive contrast induced by CA overdosing. However, a manual assessment with a ROI-based image contrast classification is a time-consuming step in everyday clinical practice. METHODS: We propose a method to automate the contrast measurement of aortic CTA volumes. The proposed algorithm is based on the mean HU values in selected ROIs that were automatically positioned in the CTA volume. First, an automatic localization algorithm determines the CTA image slices for certain ROIs followed by the localization of these ROIs. A rule-based classification using the mean HU values in the ROIs categorizes images with insufficient, optimal and excessive contrast. RESULTS: In 95.89% (70 out of 73 CTAs obtained with the ulrich medical CT motion contrast media injector) the algorithm chose the same image contrast class as the radiological expert. The critical case of missing an overdose did not occur with a positive predicative value of 100%. CONCLUSION: The resulting system works well within our range of considered scan protocols detecting enhanced areas in CTA volumes. Our work automized an assessment for classifying CA-induced image contrast which reduces the time needed for medical practitioners to perform such an assessment manually.

Computer-Assisted Quality Assessment of Aortic CT Angiographies for Patient-Individual Dose Adjustment.

Iodine-containing contrast agents (CA) are important for enhanced image contrast in CT imaging especially in CT angiography (CTA). CA however poses a risk to the patient since it can e.g. harm the kidneys. In clinical routine often a standard dose is applied that does not take differences between individual patients into account. We propose a method that as a preliminary stage determines excessive image contrast and CA overdosing by assessing the image contrast in CTA images obtained with the ulrich medical CT motion contrast media injector with RIS/PACS interface. A resulting CA dose recommendation is linked to a set of clinical parameters collected for each assessed patient. We used the established data set to implement an automatic classification for individual CA dose adjustment. The classification determines similar cases of new patients to take on the associated CA dose adjustment recommendation. The computation of similar patient data is based on the previously collected patient-individual parameters. The study shows that as basis for a recommendations the largest proportion of patients receive too much CA. A first evaluation of the automatic classification showed an overall error rate of 22% to recognize the correct class for CA dose adjustments using a k-NN-Classifier and a leave-one-out method. The classification's positive predictive value for correctly assigning a CA overdosing was 85.71%.