More Like this

1. Long-Term Geochemical and Geodynamic Segmentation of the Paleo-Pacific Margin of Gondwana: Insight From the Antarctic and Adjacent Sectors: Segmentation of the Gondwana margin

   https://doi.org/10.1002/2017TC004611  

   Nelson, D. A. ; Cottle, J. M. ( December 2017 , Tectonics)
2. Fusing RGBD Tracking and Segmentation Tree Sampling for Multi-Hypothesis Volumetric Segmentation

   https://doi.org/10.1109/ICRA48506.2021.9561136  

   Price, Andrew ; Huang, Kun ; Berenson, Dmitry ( January 2021 , 2021 IEEE International Conference on Robotics and Automation (ICRA))
3. Multiple surface segmentation using convolution neural nets: application to retinal layer segmentation in OCT images

   https://doi.org/10.1364/BOE.9.004509  

   Shah, Abhay ; Zhou, Leixin ; Abrámoff, Michael D. ; Wu, Xiaodong ( January 2018 , Biomedical Optics Express)

   null (Ed.)
4. Contextual Guided Segmentation Framework for Semi-supervised Video Instance Segmentation

   https://doi.org/10.1007/s00138-022-01278-x  

   Le, Trung-Nghia ; Nguyen, Tam V. ; Tran, Minh-Triet ( March 2022 , Machine Vision and Applications)
5. 3D Domain Adaptive Instance Segmentation Via Cyclic Segmentation GANs

   https://doi.org/10.1109/JBHI.2023.3281332  

   Lauenburg, Leander ; Lin, Zudi ; Zhang, Ruihan ; Santos, Márcia dos ; Huang, Siyu ; Arganda-Carreras, Ignacio ; Boyden, Edward S. ; Pfister, Hanspeter ; Wei, Donglai ( January 2023 , IEEE Journal of Biomedical and Health Informatics)

   3D instance segmentation for unlabeled imaging modalities is a challenging but essential task as collecting expert annotation can be expensive and time-consuming. Existing works segment a new modality by either deploying pre-trained models optimized on diverse training data or sequentially conducting image translation and segmentation with two relatively independent networks. In this work, we propose a novel Cyclic Segmentation Generative Adversarial Network (CySGAN) that conducts image translation and instance segmentation simultaneously using a unified network with weight sharing. Since the image translation layer can be removed at inference time, our proposed model does not introduce additional computational cost upon a standard segmentation model. For optimizing CySGAN, besides the CycleGAN losses for image translation and supervised losses for the annotated source domain, we also utilize self-supervised and segmentation-based adversarial objectives to enhance the model performance by leveraging unlabeled target domain images. We benchmark our approach on the task of 3D neuronal nuclei segmentation with annotated electron microscopy (EM) images and unlabeled expansion microscopy (ExM) data. The proposed CySGAN outperforms pre-trained generalist models, feature-level domain adaptation models, and the baselines that conduct image translation and segmentation sequentially. Our implementation and the newly collected, densely annotated ExM zebrafish brain nuclei dataset, named NucExM, are publicly available at https://connectomics-bazaar.github.io/proj/CySGAN/index.html. 

   more » « less