vault backup: 2024-11-06 12:02:21

201 Metadata/My Library.bib

@@ -13324,6 +13324,23 @@ Subject\_term: Careers, Politics, Policy},
   file = {/home/danesabo/Zotero/storage/LQP8SU73/Zhou and Kimura - 1994 - Simultaneous identification of nominal model, parametric uncertainty and unstructured uncertainty fo.pdf;/home/danesabo/Zotero/storage/G83Q8RYC/0005109894901171.html}
 }
 
+@inproceedings{zhouUNetNestedUNet2018,
+  title = {{{UNet}}++: {{A Nested U-Net Architecture}} for {{Medical Image Segmentation}}},
+  shorttitle = {{{UNet}}++},
+  booktitle = {Deep {{Learning}} in {{Medical Image Analysis}} and {{Multimodal Learning}} for {{Clinical Decision Support}}},
+  author = {Zhou, Zongwei and Rahman Siddiquee, Md Mahfuzur and Tajbakhsh, Nima and Liang, Jianming},
+  editor = {Stoyanov, Danail and Taylor, Zeike and Carneiro, Gustavo and Syeda-Mahmood, Tanveer and Martel, Anne and Maier-Hein, Lena and Tavares, João Manuel R.S. and Bradley, Andrew and Papa, João Paulo and Belagiannis, Vasileios and Nascimento, Jacinto C. and Lu, Zhi and Conjeti, Sailesh and Moradi, Mehdi and Greenspan, Hayit and Madabhushi, Anant},
+  date = {2018},
+  pages = {3--11},
+  publisher = {Springer International Publishing},
+  location = {Cham},
+  doi = {10.1007/978-3-030-00889-5_1},
+  abstract = {In this paper, we present UNet++, a new, more powerful architecture for medical image segmentation. Our architecture is essentially a deeply-supervised encoder-decoder network where the encoder and decoder sub-networks are connected through a series of nested, dense skip pathways. The re-designed skip pathways aim at reducing the semantic gap between the feature maps of the encoder and decoder sub-networks. We argue that the optimizer would deal with an easier learning task when the feature maps from the decoder and encoder networks are semantically similar. We have evaluated UNet++ in comparison with U-Net and wide U-Net architectures across multiple medical image segmentation tasks: nodule segmentation in the low-dose CT scans of chest, nuclei segmentation in the microscopy images, liver segmentation in abdominal CT scans, and polyp segmentation in colonoscopy videos. Our experiments demonstrate that UNet++ with deep supervision achieves an average IoU gain of 3.9 and 3.4 points over U-Net and wide U-Net, respectively.},
+  isbn = {978-3-030-00889-5},
+  langid = {english},
+  file = {/home/danesabo/Zotero/storage/6I8URLWJ/Zhou et al. - 2018 - UNet++ A Nested U-Net Architecture for Medical Image Segmentation.pdf}
+}
+
 @inproceedings{zimmermanMakingFormalMethods2000,
   title = {Making Formal Methods Practical},
   booktitle = {19th {{DASC}}. 19th {{Digital Avionics Systems Conference}}. {{Proceedings}} ({{Cat}}. {{No}}.{{00CH37126}})},