Impact of slice thickness, pixel size, and CT dose on the performance of automatic contouring algorithms

Abstract

Purpose: To investigate the impact of computed tomography (CT) image acquisition and reconstruction parameters, including slice thickness, pixel size, and dose, on automatic contouring algorithms.

Methods: Eleven scans from patients with head-and-neck cancer were reconstructed with varying slice thicknesses and pixel sizes. CT dose was varied by adding noise using low-dose simulation software. The impact of these imaging parameters on two in-house auto-contouring algorithms, one convolutional neural network (CNN)-based and one multiatlas-based system (MACS) was investigated for 183 reconstructed scans. For each algorithm, auto-contours for organs-at-risk were compared with auto-contours from scans with 3 mm slice thickness, 0.977 mm pixel size, and 100% CT dose using Dice similarity coefficient (DSC), Hausdorff distance (HD), and mean surface distance (MSD).

Results: Increasing the slice thickness from baseline value of 3 mm gave a progressive reduction in DSC and an increase in HD and MSD on average for all structures. Reducing the CT dose only had a relatively minimal effect on DSC and HD. The rate of change with respect to dose for both auto-contouring methods is approximately 0. Changes in pixel size had a small effect on DSC and HD for CNN-based auto-contouring with differences in DSC being within 0.07. Small structures had larger deviations from the baseline values than large structures for DSC. The relative differences in HD and MSD between the large and small structures were small.

Conclusions: Auto-contours can deviate substantially with changes in CT acquisition and reconstruction parameters, especially slice thickness and pixel size. The CNN was less sensitive to changes in pixel size, and dose levels than the MACS. The results contraindicated more restrictive values for the parameters should be used than a typical imaging protocol for head-and-neck.

Keywords: CT parameters; atlas-based segmentation; auto-contouring; convolutional neural network.

Fig. 1

Comparison of DSC, MSD, and HD for the auto‐contours produced for varying slice thickness and those from a control of slice thickness of 3 mm. Figure parts (a) and (d) show the average values of all patients and structures. Figure parts (b) and (e) show the average values of all patients and large structures. Figure parts (c) and (f) show the average values of all patients and small structures. Large structures included the brain, brainstem, spinal cord, left and right eyes, mandible, and left and right parotid glands, and small structures included the left and right cochlea, esophagus, optic chiasm, left and right lenses, left and right optic nerves.

Fig. 2

Comparison of DSC, MSD, and HD for the auto‐contours produced for varying pixel thickness and those from a control of pixel thickness 0.977 mm. Figure parts (a) and (d) show the average values of all patients and structures. Figure parts (b) and (e) show the average values of all patients and large structures. Figure parts (c) and (f) show the average values of all patients and small structures. Large structures included the brain, brainstem, spinal cord, left and right eyes, mandible, and left and right parotid glands, and small structures included the left and right cochlea, esophagus, optic chiasm, left and right lenses, left and right optic nerves.

Fig. 3

Comparison of DSC, MSD, and HD for the auto‐contours produced for varying dose and those from a control of 100% of original dose. Figure parts (a) and (d) show the average values of all patients and structures. Figure parts (b) and (e) show the average values of all patients and large structures. Figure parts (c) and (f) show the average values of all patients and small structures. Large structures included the brain, brainstem, spinal cord, left and right eyes, mandible, and left and right parotid glands, and small structures included the left and right cochlea, esophagus, optic chiasm, left and right lenses, left and right optic nerves.