Machine Learning Techniques Applied to Dose Prediction in Computed Tomography Tests

Abstract

Increasingly more patients exposed to radiation from computed axial tomography (CT) will have a greater risk of developing tumors or cancer that are caused by cell mutation in the future. A minor dose level would decrease the number of these possible cases. However, this framework can result in medical specialists (radiologists) not being able to detect anomalies or lesions. This work explores a way of addressing these concerns, achieving the reduction of unnecessary radiation without compromising the diagnosis. We contribute with a novel methodology in the CT area to predict the precise radiation that a patient should be given to accomplish this goal. Specifically, from a real dataset composed of the dose data of over fifty thousand patients that have been classified into standardized protocols (skull, abdomen, thorax, pelvis, etc.), we eliminate atypical information (outliers), to later generate regression curves employing diverse well-known Machine Learning techniques. As a result, we have chosen the best analytical technique per protocol; a selection that was thoroughly carried out according to traditional dosimetry parameters to accurately quantify the dose level that the radiologist should apply in each CT test.

Keywords: computed axial tomography; dose; machine learning; patients.

Figure 1

Methodology to predict future doses in patients radiated by CT.

Figure 2

Boxplot.

Figure 3

Density-based spatial clustering of applications with noise technique (DBSCAN) detection.

Figure 4

Cross Validation method.

Figure 5

Radiation delivered by the scanner (CTDI_VOL) prediction according to BMI including European DRLs for men’s/women’s skull protocol (left), together with error histograms (right), employing the Neural Networks technique: men (a,b), and women (c,d).

Figure 6

CTDI_VOL prediction according to BMI including European DRLs for men’s/women’s thorax, abdomen & pelvis protocol (left), together with error histograms (right), employing the Gaussian Process Regression (GPR) technique for men; (a,b), and the Neural Networks for women; (c,d).

Figure 6

CTDI_VOL prediction according to BMI including European DRLs for men’s/women’s thorax, abdomen & pelvis protocol (left), together with error histograms (right), employing the Gaussian Process Regression (GPR) technique for men; (a,b), and the Neural Networks for women; (c,d).

Figure 7

CTDI_VOL prediction according to BMI including European DRLs for men’s/women’s abdomen & pelvis protocol (left), together with error histograms (right), employing the ‘bagged’ regression trees (a,b) for men and the Neural Networks (c,d) for women.

Figure 8

CTDI_VOL prediction according to BMI including European DRLs for men’s/women’s thorax protocol (left), together with error histograms (right), employing the Neural Networks (a,b) for men and the GPR (c,d) for women.

Figure 9

CTDI_VOL prediction according to BMI including European DRLs for men’s/women’s abdomen protocol (left), together with error histograms (right), employing the Neural Networks (a,b) for men and the GPR (c,d) for women.

Figure 10

Size-Specific Dose Estimate (SSDE) prediction according to CTDI_VOL for skull protocol (left), together with error histograms (right), employing the ‘bagged’ regression trees technique (a,b).

Figure 11

SSDE prediction according to CTDI_VOL for Thorax, Abdomen, & Pelvis protocol (left), together with error histograms (right), employing the Neural Networks technique (a,b).

Figure 12

SSDE prediction according to CTDIvol for Abdomen & Pelvis protocol (left), together with error histograms (right), employing the GPR technique (a,b).

Figure 13

SSDE prediction according to CTDI_VOL for Thorax protocol (left), together with error histograms (right), employing the Neural Networks technique (a,b).

Figure 14

SSDE prediction according to CTDI_VOL for Abdomen protocol (left), together with error histograms (right), the ‘bagged’ regression trees technique (a,b).