Landmark-based auto-contouring of clinical target volumes for radiotherapy of nasopharyngeal cancer

Abstract

Background: The delineation of clinical target volumes (CTVs) for radiotherapy for nasopharyngeal cancer is complex and varies based on the location and extent of disease.

Purpose: The current study aimed to develop an auto-contouring solution following one protocol guidelines (NRG-HN001) that can be adjusted to meet other guidelines, such as RTOG-0225 and the 2018 International guidelines.

Methods: The study used 2-channel 3-dimensional U-Net and nnU-Net framework to auto-contour 27 normal structures in the head and neck (H&N) region that are used to define CTVs in the protocol. To define the CTV-Expansion (CTV1 and CTV2) and CTV-Overall (the outer envelope of all the CTV contours), we used adjustable morphological geometric landmarks and mimicked physician interpretation of the protocol rules by partially or fully including select anatomic structures. The results were evaluated quantitatively using the dice similarity coefficient (DSC) and mean surface distance (MSD) and qualitatively by independent reviews by two H&N radiation oncologists.

Results: The auto-contouring tool showed high accuracy for nasopharyngeal CTVs. Comparison between auto-contours and clinical contours for 19 patients with cancers of various stages showed a DSC of 0.94 ± 0.02 and MSD of 0.4 ± 0.4 mm for CTV-Expansion and a DSC of 0.83 ± 0.02 and MSD of 2.4 ± 0.5 mm for CTV-Overall. Upon independent review, two H&N physicians found the auto-contours to be usable without edits in 85% and 75% of cases. In 15% of cases, minor edits were required by both physicians. Thus, one physician rated 100% of the auto-contours as usable (use as is, or after minor edits), while the other physician rated 90% as usable. The second physician required major edits in 10% of cases.

Conclusions: The study demonstrates the ability of an auto-contouring tool to reliably delineate nasopharyngeal CTVs based on protocol guidelines. The tool was found to be clinically acceptable by two H&N radiation oncology physicians in at least 90% of the cases.

Keywords: auto‐contouring; clinical target volume; nasopharynx cancer.

FIGURE 1

Flowchart of the automated contouring pipeline for nasopharyngeal cancer. The diagram illustrates the process from input data (CT images, GTVp, GTVn, and tumor stage) through various stages of CTV creation, including structure auto‐contouring, preprocessing, landmark identification, and contour refinement, to the final output of CTVs (CTV1, CTV2, CTV3, and CTV4 where applicable).

FIGURE 2

An illustration of the auto‐contouring process. (a) GTV (green) and initial segmentation of anatomical structures. (b) Identification of anatomical structures. (c) Establishment of landmarks, and generation of polygon based on landmarks. (d) Creation of contours with the polygon, and expansion (red) from GTV. (e) Final contour. (f) Comparison between clinical contour (yellow) and automatic contour (blue).

FIGURE 3

Illustration of the methodology employed for landmark identification. CT images display marked anatomical landmarks (c–e, etc.) connected by colored lines to form polygons, delineating targeted regions for radiation therapy. The lowercase letters correspond to the segments between each landmark point.

FIGURE 4

Examples of the clinical contours (yellow) versus auto‐delineated contours (blue). (a) Axial view. (b) Sagittal view. (c) Coronal view.

FIGURE 5

Box and whisker plots of dice similarity coefficient (DSC) distance between ground‐truth and automatically generated contours by our tool CT images. For this analysis, CTV3 represents the aggregate of CTV3p and CTV3n, while CTV1 is constituted by the sum of CTV1p and CTV1n. The central line represents the median value. The border of the box represents the 25th and 75th percentiles. The outliers are represented by circles markers.

FIGURE 6

Box and whisker plots of mean surface distance (MSD) distance between ground‐truth and automatically generated contours by our tool's CT images. For this analysis, CTV3 represents the aggregate of CTV3p and CTV3n, while CTV1 is constituted by the sum of CTV1p and CTV1n. The central line represents the median value. The border of the box represents the 25th and 75th percentiles. The outliers are represented by circles.

FIGURE 7

Stacked bar plots of contour scores by Physician A and Physician B. Unlike previous figures that presented aggregate data for CTV3 and CTV1, this figure provides a detailed breakdown. Here, CTV3 is dissected into CTV3p and CTV3n, and CTV1 is segmented into CTV1p and CTV1n, offering a more granular view of the contour scores for these subdivisions.