Application Values of 2D and 3D Radiomics Models Based on CT Plain Scan in Differentiating Benign from Malignant Ovarian Tumors

Table 1

Case distribution in the training set and validation set.

	Training group ()			Validation group ()			value
	Benign	Malignant	value	Benign	Malignant	value
Quantity	45	54		19	22
Age (year)			0.0164			0.0015	0.3032
<18	4 (8.9%)	1 (1.9%)		1 (5.3%)	0 (0.0%)
>18, ≤30	7 (15.6%)	2 (3.7%)		8 (42.1%)	0 (0.0%)
>30, ≤50	20 (44.4%)	20 (37.0%)		6 (31.6%)	7 (31.8%)
>50	14 (31.1%)	31 (57.4%)		4 (21.1%)	15 (68.2%)
CA125 (U/mL)			<0.0001			0.0009	0.8859
<35	22 (48.9%)	4 (7.4%)		9 (47.4%)	4 (18.2%)
>35, ≤200	20 (44.4%)	16 (29.6%)		10 (52.6%)	5 (22.7%)
>200, ≤500	2 (4.4%)	11 (20.4%)		0 (0.0%)	4 (18.2%)
>500	1 (2.2%)	23 (42.6%)		0 (0.0%)	9 (40.9%)
Ascites			<0.0001			0.0004	0.4627
None	26 (57.8%)	10 (18.5%)		15 (78.9%)	4 (18.2%)
Small	17 (37.8%)	12 (22.2%)		3 (15.8%)	4 (18.2%)
Moderate	0 (0.0%)	13 (24.1%)		1 (5.3%)	4 (18.2%)
Large	2 (4.4%)	19 (35.2%)		0 (0.0%)	10 (45.5%)
Cystic-solid tumor			<0.0001			0.0044	0.6431
Cystic	17 (37.8%)	2 (3.7%)		7 (36.8%)	0 (0.0%)
Cystic-solid	26 (57.8%)	45 (83.3%)		12 (63.2%)	20 (90.9%)
Solid	2 (4.4%)	7 (13%)		0 (0.0%)	2 (9.1%)
Boundary			<0.0001			0.4082	0.3399
Clear	41 (91.1%)	24 (44.4%)		16 (84.2%)	15 (68.2%)
Blur	4 (8.9%)	30 (55.6%)		3 (15.8%)	7 (31.8%)
Radscore median [iqr]	-0.6 [-1.1, 0.6]	0.8 [0.6, 1.1]	<0.0001	-0.6 [-1.0, -0.1]	0.8 [0.4, 1.0]	0.0005	0.7503