SOTA Results
Datasets:
- BUSI - three types normal, benign, malignant + masks
- BUSIS - 563 images with masks
- UDIAT - 163 images aka Dataset B
- OASBUD - small dataset in Matlab format with masks BUV - breast ultrasound videos
Classification Results
Acc | AUC | Sens. | Spec. | Prec. | F1 | Arch. | Data. | Year | Ref |
---|---|---|---|---|---|---|---|---|---|
.891 | 0.962 | 0.923 | 0.831 | 0.918 | Resnet50 | private | 2022 | Guo et al. (2022) | |
0.867 | 0.95 | ViTb32 | UDIAT + BUSI | 2022 | Gheflati and Rivaz (2022) | ||||
0.85 | 0.94 | Resnet50 | UDIAT + BUSI | 2022 | Gheflati and Rivaz (2022) | ||||
0.93 | 0.96 | 0.90 | 0.92 | 0.94 | Attention - VGG16 | UDIAT + Private | 2021 | (Kalafi et al., n.d.) |
References
Gheflati, Behnaz, and Hassan Rivaz. 2022. “Vision Transformers for Classification of Breast Ultrasound Images.” In 2022 44th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), 480–83. https://doi.org/10.1109/EMBC48229.2022.9871809.
Guo, Yuanfan, Canqian Yang, Tiancheng Lin, Chunxiao Li, Rui Zhang, Rong Wu, and Yi Xu. 2022. “Self Supervised Lesion Recognition for Breast Ultrasound Diagnosis.” In 2022 IEEE 19th International Symposium on Biomedical Imaging (ISBI), 1–4. https://doi.org/10.1109/ISBI52829.2022.9761701.
Kalafi, Elham Yousef, Ata Jodeiri, Seyed Kamaledin Setarehdan, Ng Wei Lin, Binti Rahman, Nur Aishah Taib, and Sarinder Kaur Dhillon. n.d. “Classification of Breast Cancer Lesions in Ultrasound Images by Using Attention Layer and Loss Ensembles in Deep Convolutional Neural Networks.”