Fused Multilayer Layer-CAM Fine-Grained Spatial Feature Supervision for Surgical Phase Classification Using CNNs
Abstract
In this paper, we propose a novel spatial context aware combined loss function to be used along with an end to end Encoder-Decoder training methodology for the task of surgical phase classification on laparoscopic cholecystectomy surgical videos. Proposed spatial context aware combined loss function leverages on the fine-grained class activation maps obtained from fused multilayer Layer-CAM for supervising the learning of surgical phase classifier. We report peak surgical phase classification accuracy of 91.95%, precision of 86.19% and recall of 83.75% on publicly available Cholec80 dataset consisting of 7 surgical phases. Our proposed method utilizes just 77% of the total number of parameters in comparison with state of the art methodology and achieves 3.4% improvement in terms of accuracy, 4.6% improvement in terms of precision and comparable recall.
Cite
Text
Pradeep and Sinha. "Fused Multilayer Layer-CAM Fine-Grained Spatial Feature Supervision for Surgical Phase Classification Using CNNs." European Conference on Computer Vision Workshops, 2022. doi:10.1007/978-3-031-25075-0_48Markdown
[Pradeep and Sinha. "Fused Multilayer Layer-CAM Fine-Grained Spatial Feature Supervision for Surgical Phase Classification Using CNNs." European Conference on Computer Vision Workshops, 2022.](https://mlanthology.org/eccvw/2022/pradeep2022eccvw-fused/) doi:10.1007/978-3-031-25075-0_48BibTeX
@inproceedings{pradeep2022eccvw-fused,
title = {{Fused Multilayer Layer-CAM Fine-Grained Spatial Feature Supervision for Surgical Phase Classification Using CNNs}},
author = {Pradeep, Chakka Sai and Sinha, Neelam},
booktitle = {European Conference on Computer Vision Workshops},
year = {2022},
pages = {712-726},
doi = {10.1007/978-3-031-25075-0_48},
url = {https://mlanthology.org/eccvw/2022/pradeep2022eccvw-fused/}
}