EURASIP Journal on Advances in Signal Processing

Table 5 Experiment results on abdominal scans under setting 2

From: A dynamic few-shot learning framework for medical image stream mining based on self-training

Method	Dataset-abdomen—MRI					Dataset-abdomen—CT
	Lower		Upper		Mean	Lower		Upper		Mean
	Left kidney	Right kidney	Spleen	Liver	Mean	Left kidney	Right kidney	Spleen	Liver	Mean
SE-Net [37]	60.19	59.98	50.12	26.43	49.18	33.05	15.43	0.24	0.30	12.26
Vanilla PANet [38]	54.33	37.61	49.81	44.15	46.48	32.86	17.23	29.98	39.17	29.81
ALPNet-init	18.25	13.31	23.77	36.63	22.99	13.77	10.85	16.49	41.52	82.63
ALPNet [39]	54.08	58.74	51.81	36.22	50.12	35.12	30.41	28.25	47.81	35.39
DARCNN [13]	44.72	44.83	58.27	64.75	53.14	37.64	35.89	44.78	61.10	44.85
MRNet [42]	52.21	56.55	57.45	69.27	58.87	38.67	35.71	50.03	46.22	42.65
Ours	74.57	78.74	68.01	73.84	73.79	64.59	55.57	61.11	74.56	63.95

Back to article page