Visual Computing for Industry, Biomedicine, and Art

Table 3 Results of performing ablation study of our proposed method trained and tested on the BUSI [21] dataset

From: Multi-task approach based on combined CNN-transformer for efficient segmentation and classification of breast tumors in ultrasound images

Fold	Accuracy (%)	DC (%)	IoU (%)	Precision (%)	Recall (%)
Baseline	93.860 ± 0.010	81.940 ± 0.004	69.700 ± 0.010	76.820 ± 0.020	87.900 ± 0.010
Baseline + CAF	94.040 ± 0.010	83.420 ± 0.007	72.560 ± 0.010	80.100 ± 0.010	88.100 ± 0.008

Back to article page