Cholec80

doi:doi:10.57702/g9q07m7i

Cholec80

The proposed network is implemented in PyTorch using a single Tesla V100-DGXS-32GB GPU of an NVIDIA DGX station. For the ResNet-50 part, PyTorch default ImageNet pretrained parameters are loaded for transfer learning and fine-tuned for 100 epochs on Cholec80 and Sacrocolpopexy respectively.

BibTex:

@dataset{Jiale_Zhang_and_Wenfeng_Huang_and_Xiangyun_Liao_and_Qiong_Wang_2024,
    abstract = {The proposed network is implemented in PyTorch using a single Tesla V100-DGXS-32GB GPU of an NVIDIA DGX station. For the ResNet-50 part, PyTorch default ImageNet pretrained parameters are loaded for transfer learning and fine-tuned for 100 epochs on Cholec80 and Sacrocolpopexy respectively.},
    author = {Jiale Zhang and Wenfeng Huang and Xiangyun Liao and Qiong Wang},
    doi = {10.57702/g9q07m7i},
    institution = {No Organization},
    keyword = {'Anomaly Detection', 'Cholecystectomy', 'Deep learning', 'Endoscopic Surgery', 'Laparoscopic Surgery', 'Laparoscopic Videos', 'Laparoscopic cholecystectomy', 'Laparoscopic image desmoking', 'Medical image analysis', 'Medical imaging', 'Multi-Agent Reinforcement Learning', 'Phase Recognition', 'Reinforcement Learning', 'Smoke removal', 'Surgical Tool Localization', 'Surgical Tool Tracking', 'Surgical Videos', 'Surgical Workﬂow Segmentation', 'Surgical data', 'Surgical phases', 'Tool presence', 'Video Analysis', 'Weakly-Supervised Learning', 'laparoscopic cholecystectomy', 'phase recognition', 'surgical phase recognition', 'surgical videos', 'surgical workﬂow', 'video analysis'},
    month = {dec},
    publisher = {TIB},
    title = {Cholec80},
    url = {https://service.tib.eu/ldmservice/dataset/cholec80},
    year = {2024}
}