Cancer Pathological Segmentation Network Based on Depth Feature Fusion

Algorithm	DICE /%	MA/%	Sen/%	Pre/%	IOU/%
U-Net	70.06	86.04	68.57	77.93	58.74
FCN-VGG16	68.01	85.05	66.72	73.67	56.91
SegNet	72.05	85.86	70.81	75.56	60.30
DeepLabv3+	76.52	87.87	75.98	78.81	65.34
TransUnet	75.02	87.49	78.40	75.14	65.09
CA-Net	74.33	83.47	77.53	72.12	62.00
HU-Net	77.99	88.52	79.22	78.78	67.01

Table 2. The results of different models on the BOT dataset
View table
View in Article
Table 2. The results of different models on the BOT dataset
Algorithm DICE/% MA/% Sen/% Pre/% IOU/%
EU-Net 75.26 87.00 77.59 74.59 63.73
FU-Net 77.45 88.52 77.46 78.78 66.53
AU-Net 76.98 87.64 76.78 78.36 65.56
HU-Net 77.99 88.65 79.22 78.95 67.01

Table 3. The result of different algorithms on the SEED dataset

View table

View in Article

Table 3. The result of different algorithms on the SEED dataset

Algorithm	Dice/%	MA/%	Sen/%	Pre/%	IOU/%
U-Net	66.36	78.90	65.61	70.15	53.65
FCN-VGG16	71.47	75.37	78.52	71.36	56.87
SegNet	75.01	80.23	78.82	73.75	61.55
DeepLabv3+	81.86	86.24	82.59	80.66	69.63
TransUnet	80.25	85.16	82.95	79.79	68.94
CA-Net	76.74	81.13	80.68	74.35	63.70
HU-Net	82.94	87.42	84.01	82.56	72.08

Table 4. The results of different models on the SEED dataset
View table
View in Article
Table 4. The results of different models on the SEED dataset
Algorithm Dice/% MA/% Sen/% Pre/% IOU/%
EU-Net 78.95 83.42 80.85 77.56 66.10
AU-Net 79.76 85.02 80.26 79.87 67.74
FU-Net 81.76 86.84 82.23 81.92 70.48
HU-Net 82.94 87.42 84.0 82.56 72.08

Tools

Get Citation

Copy Citation Text

Hong HUANG, Tao WANG, Yuan LI, Fanlin ZHOU, Yu LI. Cancer Pathological Segmentation Network Based on Depth Feature Fusion[J]. Acta Photonica Sinica, 2022, 51(3): 0310001

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites