Table 1.

Metrics (mean ± std) and corresponding inter-observer variation (IOV) for all ROIs for the in-house and external model, compared to the manual delineations and each other. Significant difference of metrics between the two models, when compared to manual delineations, is indicated with an asterisk. Inter-observer variations are acquired from 1: Almberg et al. [14], 2: Chung et al. [17], 3: Francolini et al. [18], 4: Leonardi et al. [19].

		DSC score [-]					95%HD [mm]
		In-house vs manual	External vs manual		In-house vs external	IOV (mean)	In-house vs manual	External vs manual		In-house vs external	IOV (mean)
CTVp	mean ± std	0.94 ± 0.02	0.92 ± 0.02	*	0.93 ± 0.02	0.941, 0.852, 0.943	9.38 ± 9.04	8.80 ± 4.64		8.01 ± 8.94	5.711, 8.942
	median (range)	0.95 (0.89, 0.97)	0.92 (0.87, 0.94)		0.93 (0.86, 0.95)		7.81 (2.45, 55.2)	7.77 (2.40, 28.2)		6.47 (3.16, 54.8)
CTVn1	mean ± std	0.79 ± 0.05	0.76 ± 0.08	*	0.79 ± 0.07	0.741, 0.692, 0.723	11.3 ± 4.65	13.3 ± 7.26		10.1 ± 3.61	14.601, 13.582
	median (range)	0.79 (0.64, 0.88)	0.78 (0.52, 0.87)		0.80 (0.52, 0.84)		10.1 (4.47, 21.9)	11.4 (5.00, 33.3)		9.33 (5.48, 20.6)
CTVn2	mean ± std	0.71 ± 0.07	0.69 ± 0.07		0.67 ± 0.09	0.621, 0.472, 0.773, 0.554	9.42 ± 4.33	10.1 ± 3.61		11.3 ± 4.13	16.211, 18.742
	median (range)	0.74 (0.53, 0.82)	0.69 (0.53, 0.83)		0.68 (0.46, 0.86)		8.48 (2.24, 22.2)	9.95 (4.58, 21.3)		10.1 (6.08, 23.1)
CTVn3	mean ± std	0.74 ± 0.06	0.67 ± 0.10		0.72 ± 0.09	0.671, 0.562, 0.793, 0.584	7.01 ± 2.72	8.71 ± 3.07	*	7.67 ± 3.33	9.391, 9.872
	median (range)	0.74 (0.58, 0.82)	0.69 (0.4, 0.82)		0.74 (0.47, 0.86)		6.44 (3.61, 14.9)	8.25 (3.00, 16.9)		6.74 (3.74, 18.8)
CTVn4	mean ± std	0.57 ± 0.13	0.33 ± 0.11	*	0.30 ± 0.08	0.721, 0.452, 0.753, 0.694	6.45 ± 3.08	16.4 ± 3.88	*	16.5 ± 2.57	6.131, 11.822
	median (range)	0.57 (0.22, 0.79)	0.33 (0.01, 0.54)		0.29 (0.18, 0.35)		5.46 (2.83, 18.0)	15.7 (9.43, 23.2)		16.6 (10.5, 21.8)
Heart	mean ± std	0.94 ± 0.02	0.93 ± 0.02	*	0.93 ± 0.02	0.951, 0.912	7.46 ± 3.79	9.48 ± 4.67	*	11.1 ± 3.74	6.691, 13.002
	median (range)	0.94 (0.90, 0.96)	0.93 (0.88, 0.96)		0.94 (0.88, 0.96)		7.00 (3.00, 23.0)	8.00 (3.00, 19.1)		10.0 (6.00, 19.0)
Lung (left)	mean ± std	0.98 ± 0.01	0.96 ± 0.02	*	0.96 ± 0.02	0.982	2.56 ± 2.37	4.63 ± 3.55	*	4.65 ± 3.21	2.192
	median (range)	0.98 (0.95, 0.99)	0.97 (0.91, 0.99)		0.97 (0.90, 0.98)		1.87 (1.00, 13.4)	2.91 (1.00, 10.8)		3.61 (1.00, 12.7)
Lung (right)	mean ± std	0.98 ± 0.01	0.96 ± 0.03	*	0.97 ± 0.03	0.992	2.14 ± 1.29	5.37 ± 5.54	*	5.32 ± 5.04	2.332
	median (range)	0.99 (0.96, 0.99)	0.98 (0.88, 0.99)		0.98 (0.90, 0.99)		2.00 (1.00, 6.16)	1.83 (1.00, 20.8)		5.05 (2.83, 9.27)
Thyroid	mean ± std	0.63 ± 0.17	0.71 ± 0.17	*	0.68 ± 0.09	0.811, 0.722	8.23 ± 7.19	7.05 ± 7.31	*	5.36 ± 1.91	3.911, 5.372
	median (range)	0.67 (0.00, 0.82)	0.75 (0.00, 0.87)		0.69 (0.47, 0.81)		5.66 (2.83, 41.4)	4.18 (2.00, 39.1)		5.05 (2.83, 9.27)
Esophagus	mean ± std	0.70 ± 0.10	0.32 ± 0.07	*	0.27 ± 0.04	0.831, 0.782	9.58 ± 6.98	161 ± 22.4	*	161 ± 18.0	2.961, 7.082
	median (range)	0.71 (0.45, 0.88)	0.32 (0.18, 0.45)		0.27 (0.18, 0.35)		7.77 (1.73, 36.8)	160 (116, 226)		160 (133, 201)
Esophagus (overlap)	mean ± std	0.77 ± 0.08	0.85 ± 0.05	*	0.77 ± 0.07	0.831, 0.782	3.81 ± 2.38	2.29 ± 1.44	*	4.44 ± 2.22	2.961, 7.082
	median (range)	0.78 (0.55, 0.89)	0.86 (0.71, 0.92)		0.78 (0.53, 0.87)		3.24 (1.41, 12.57)	1.87 (1.00, 7.21)		3.80 (1.41, 11.4)
Humeral head	mean ± std	0.85 ± 0.06	0.85 ± 0.09		0.83 ± 0.13	–	8.18 ± 3.76	8.26 ± 4.81		9.88 ± 3.68	–
	median (range)	0.86 (0.68, 0.95)	0.86 (0.52, 0.96)		0.83 (0.70, 0.94)		7.45 (1.00, 19.7)	7.50 (1.00, 21.0)		10.0 (3.00, 18.57)