Table 2 Quantitative comparisons of WSFS+ with the state-of-the-art methods including U-Net, ADGC-UNet, Yolov8x-seg, DiscoBox, and SAM-Med2D on USOVA3D dataset.

From: A weakly-supervised follicle segmentation method in ultrasound images

Method

mAP50

IOU

Dice Score

FLOPs(G)

Params(M)

U-Net*

0.656

0.612

0.76

21.0

31.3

ADGC-UNet*

–

0.612

0.76

11.2

6.3

Yolov8x-seg*

0.920

0.789

0.88

344.1

71.8

DiscoBox

0.747

0.346

0.51

71.1

44.8

SAM-Med2D

0.716

0.373

0.54

33.8

271.2

WSFS+

0.957

0.714

0.83

10.5

71.8

  1. The best and second-best results in each category are highlighted in bold and italic formats, respectively. * represents fully supervised method.
Back to article page