Ultrasound-based deep learning radiomics model for differentiating benign, borderline, and malignant ovarian tumours: a multi-class classification exploratory study

Table 2 The expert assessment the ultrasound images

		Histopathological diagnosis			Sum
		Benign tumour (n, Ac%)	BOT (n, Ac%)	Malignant tumour (n, Ac%)	Sum
US expert examiners	Benign tumour (n, Ac%)	505 (95.80%)	10	12	527
	BOTs (n, Ac%)	24	19 (34.50%)	12	55
	Malignant tumour (n, Ac%)	20	26	221 (82.80%)	267
Sum		549	55	245	849

ISSN: 1471-2342