Cervical Optical Coherence Tomography Image Classification Based on Contrastive Self-Supervised Texture Learning

1 code implementation • 11 Aug 2021 • Kaiyi Chen, Qingbin Wang, Yutao Ma

Conclusions: The proposed contrastive-learning-based CADx method outperformed the end-to-end CNN models and provided better interpretability based on texture features, which holds great potential to be used in the clinical protocol of "see-and-treat."

Binary Classification Contrastive Learning +3