Use of auto-segmentation in the delineation of target volumes and organs at risk in head and neck

Figures & data

Table 1. Study summary table.

Study title	Year	AS used	Number of physicist involved	Disease-related factor	Number of cases	Contouring structures	Time savings assessed?	Delineation accuracy assessed?	AS strategy assessed?	Physicists influence assessed?	Patient staging assessed?	Observer variability assessed?	Study quality
Clinical validation of ABAS of multiple target volumes and normal tissue (swallowing/mastication) structures in the head and neck. Teguh et al. [14]	2011	Multi- &Single-ABAS	5 experienced observers + expert panel (4 staff members)	HNC	12	TV Neck levels I–IV & 20 OARs	Yes	Yes	Yes	No	No	No	Poor (0)
ABAS of head and neck OARs and nodal target volumes: a clinical validation. Daisne et al. [6]	2013	ABAS	1 radiation oncologist	Un-operated HNC	20	OARs & CTV	Yes	Yes	Yes	No	No	Yes	Good (4)
AS of low-risk CTV for head and neck radiation therapy. Yang et al. [3]	2014	Multi- & Single-ABAS	8 radiation oncologists	HNC (Unilateral tonsil cancer)	16	Low-risk CTV	No	Yes	Yes	Yes	Yes	Yes	Poor (0)
AS of normal and target structures in head and neck CT images: A feature-driven model-based approach. Qazi et al. [2]	2011	Hybrid approach	1 observer	HNC	10	OAR & TV (lymph nodes level I–IV)	No	Yes	Yes	No	No	No	Poor (1)
Evaluation of automatic atlas-based lymph node segmentation for HNC. Stapleford et al. [1]	2010	Multi- & Single-ABAS	5 radiation oncologists	HNC (Oropharyn x and nasopharyn x)	5	TV of lymph node regions	Yes	Yes	No	No	No	Yes	Poor-Fair (2)
Does ABAS of neck levels require subsequent manual contour editing to avoid risk of severe target under-dosage? A dosimetric analysis. Voet et al. [5]	2011	Single-ABAS	2 radiation oncologists	HNC	9	OARs & TV	No	Yes	No	No	No	No	Poor-Fair (2)
Dosimetric evaluation of AS for adaptive IMRT for HNC. Tsuji et al. [11]	2010	Unknown	1 planner and 1 radiation oncologist	HNC	16	CTV	No	Yes	No	No	No	No	Poor (1)
Prospective randomized double-blind study of atlas-based OAR AS-assisted radiation planning in HNC. Walker et al. [23]	2014	Unknown	15 radiation oncologists with 1–4 years of experience	HNC	40	16 OARs	Yes	Yes	No	Yes	No	No	Good (4)
Systematic evaluation of three difference commercial software solutions for AS for adaptive therapy in head and neck prostate and pleural cancer. La Macchia et al. [25]	2012	Single-ABAS	3 radiation oncologists	– HNC – Prostate – Pleura	5 from each site Total: 15	All volumes of interests	Yes	No	No	No	No	No	Poor (0)
Evaluation of an AS algorithm for definition of head and neck OARs. Thomson et al. [24]	2014	SPICE	5 radiation oncologists	HNC	10	5 OARs	Yes	Yes	No	No	No	No	Poor (0)

ABAS: atlas-based automatic segmentation; AS: automatic segmentation; CT: computed tomography; CTV: clinical target volume; HNC: head and neck cancer; IMRT: intensity-modulated radiation therapy; OAR: organ at risk; SPICE: smart probabilistic image contouring engine; TV: target volume.

Table 2. Summary of inclusion and exclusion criteria.

Inclusion

Exclusion

All studies published after 2005 Adult (≥18 years) populations of patients with a histologically proven head and neck cancer regardless of staging and treatment intent English language publications Publications investigating auto-segmentation delineation in targets and/or OARs for head and neck patients planned for IMRT treatment Studies investigating at least one of the following outcomes: time savings and delineation accuracy

Studies published before 2005 Studies investigating patients <18 years of age with other cancers beside head and neck cancers Studies describing the technical development of auto-segmentation software Studies discussing about auto-segmentation delineation solely for prostate, breast, lung or other cancers and not head and neck cancers (due to difference in information requirements) Studies assessing physician or healthcare opinion Studies assessing patients who were planned for conventional two-dimensional radiotherapy, three-dimensional conformal radiotherapy as well as pediatric head and neck cancer patients were excluded

Table 3. Quality of study assessment using Jadad et al. [26] (Assessing the quality of reports of randomized clinical trials: is blinding necessary?).

Study	Year	Was the study described as randomized? (1 = yes; 0 = no)	Was the method of randomization well described and adequate? (0 = not described; 1 = described and adequate; −1 = described, but inadequate)	Was the study described as double-blind? (1 = yes; 0 = no)	Was the method of double blinding well described and adequate? (0 = not described; 1 = describe and adequate; −1 = described, but not adequate)	Was there a description of Yes, withdrawals and dropouts sufficient to determine the number of patients in each treatment group entering and completing the trial? (1 = yes; 0 = no)	Final score / quality of study (0 = Bad, 1 = Poor, 2 = Fairly Poor, 3 = Fair, 4 = Good, 5 = Very good)
Teguh et al. [14]	2011	0	0	0	0	0	0
Daisne et al. [6]	2013	1	1	1	1	0	4
Yang et al. [3]	2014	1	0	0	0	0	0
Qazi et al. [2]	2011	0	0	0	0	1	1
Stapleford et al. [1]	2010	0	0	1	1	0	2
Voet et al. [5]	2011	1	1	0	0	0	2
Tsuji et al. [11]	2010	0	0	0	0	1	1
Walker et al. [23]	2014	1	1	1	1	0	4
La Macchia et al. [25]	2012	0	0	0	0	0	0
Thomson et al. [24]	2014	0	0	0	0	0	0

Teguh DN, Levendag PC, Voet PW, et al. Clinical validation of atlas-based auto-segmentation of multiple target volumes and normal tissue (swallowing/mastication) structures in the head and neck. Int J Radiat Oncol Biol Phys 2011;81:950–7.

 PubMed Web of Science ®Google Scholar

Daisne JF, Blumhofer A. Atlas-based automatic segmentation of head and neck organs at risk and nodal target volumes: a clinical validation. Radiat Oncol 2013;8:154.

 PubMed Web of Science ®Google Scholar

Yang J, Beadle BM, Garden AS, et al. Auto-segmentation of low-risk clinical target volume for head and neck radiation therapy. Prac Radiat Oncol 2014;4:e31–7.

 Google Scholar

Qazi AA, Pekar V, Kim J, et al. Auto-segmentation of normal and target structures in head and neck CT images: a feature-driven model-based approach. Med Phys 2011;38:6160–70.

 PubMed Web of Science ®Google Scholar

Stapleford LJ, Lawson JD, Perkins C, et al. Evaluation of automatic atlas-based lymph node segmentation for head-and-neck cancer. Int J Radiat Oncol Biol Phys 2010;77:959–66.

 PubMed Web of Science ®Google Scholar

Voet PW, Dirkx ML, Teguh DN, et al. Does atlas-based autosegmentation of neck levels require subsequent manual contour editing to avoid risk of severe target underdosage? A dosimetric analysis. Radiother Oncol 2011;98:373–7.

 PubMed Web of Science ®Google Scholar

Tsuji SY, Hwang A, Weinberg V, et al. Dosimetric evaluation of automatic segmentation for adaptive IMRT for head-and-neck cancer. Int J Radiat Oncol Biol Phys 2010;77:707–14.

 PubMed Web of Science ®Google Scholar

Walker GV, Awan M, Tao R, et al. Prospective randomized double-blind study of atlas-based organ-at-risk autosegmentation-assisted radiation planning in head and neck cancer. Radiother Oncol 2014;112:321–5.

 PubMed Web of Science ®Google Scholar

La Macchia M, Fellin F, Amichetti M, et al. Systematic evaluation of three different commercial software solutions for automatic segmentation for adaptive therapy in head-and-neck, prostate and pleural cancer. Radiat Oncol 2012;7:160.

 PubMed Web of Science ®Google Scholar

Thomson D, Boylan C, Liptrot T, et al. Evaluation of an automatic segmentation algorithm for definition of head and neck organs at risk. Radiat Oncol 2014;9:173.

 PubMed Web of Science ®Google Scholar

Jadad AR, Moore RA, Carroll D, et al. Assessing the quality of reports of randomized clinical trials: is blinding necessary? Control Clin Trials 1996;17:1–12.

 PubMedGoogle Scholar