Improved Kidney Stone Recognition Through Attention and Multi-View Feature Fusion Strategies
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2022
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910668793315328 |
|---|---|
| author | Villalvazo-Avila, Elias Lopez-Tiro, Francisco El-Beze, Jonathan Hubert, Jacques Gonzalez-Mendoza, Miguel Ochoa-Ruiz, Gilberto Daul, Christian |
| author_facet | Villalvazo-Avila, Elias Lopez-Tiro, Francisco El-Beze, Jonathan Hubert, Jacques Gonzalez-Mendoza, Miguel Ochoa-Ruiz, Gilberto Daul, Christian |
| contents | This contribution presents a deep learning method for the extraction and fusion of information relating to kidney stone fragments acquired from different viewpoints of the endoscope. Surface and section fragment images are jointly used during the training of the classifier to improve the discrimination power of the features by adding attention layers at the end of each convolutional block. This approach is specifically designed to mimic the morpho-constitutional analysis performed in ex-vivo by biologists to visually identify kidney stones by inspecting both views. The addition of attention mechanisms to the backbone improved the results of single view extraction backbones by 4% on average. Moreover, in comparison to the state-of-the-art, the fusion of the deep features improved the overall results up to 11% in terms of kidney stone classification accuracy. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2211_02967 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | Improved Kidney Stone Recognition Through Attention and Multi-View Feature Fusion Strategies Villalvazo-Avila, Elias Lopez-Tiro, Francisco El-Beze, Jonathan Hubert, Jacques Gonzalez-Mendoza, Miguel Ochoa-Ruiz, Gilberto Daul, Christian Computer Vision and Pattern Recognition Artificial Intelligence This contribution presents a deep learning method for the extraction and fusion of information relating to kidney stone fragments acquired from different viewpoints of the endoscope. Surface and section fragment images are jointly used during the training of the classifier to improve the discrimination power of the features by adding attention layers at the end of each convolutional block. This approach is specifically designed to mimic the morpho-constitutional analysis performed in ex-vivo by biologists to visually identify kidney stones by inspecting both views. The addition of attention mechanisms to the backbone improved the results of single view extraction backbones by 4% on average. Moreover, in comparison to the state-of-the-art, the fusion of the deep features improved the overall results up to 11% in terms of kidney stone classification accuracy. |
| title | Improved Kidney Stone Recognition Through Attention and Multi-View Feature Fusion Strategies |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2211.02967 |