Table 2 Performance comparison on the IVUS-CAD-Rad dataset

From: PlaqueCap: lesion-centered captioning of atherosclerotic plaques in intravascular ultrasound using vision-language models and prompt injection

Model

BLEU-4

CIDEr

METEOR

ROUGE-L

BLIP-2

24.8

71.3

20.1

45.2

GIT

23.2

67.9

19.3

43.7

LLaVA

20.8

60.3

18.0

40.9

MiniGPT-4

19.5

58.2

17.4

39.7

BioViL-T

25.9

73.6

21.2

45.8

MedCLIP

22.4

66.0

19.1

42.7

Caption-MedIC

26.4

72.4

21.6

46.5

PMC-VQA

21.7

63.1

18.5

41.5

PathoCap

25.2

70.8

20.5

45.1

GPT-4V

27.1

74.0

21.3

46.2

PlaqueCap (Ours)

30.9

79.7

23.2

49.3

  1. All values are percentages. Best results are bold.
Back to article page