Evidential Uncertainty-Guided Mitochondria Segmentation for 3D EM Images
Authors: Ruohua Shi, Lingyu Duan, Tiejun Huang, Tingting Jiang
AAAI 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experiments conducted on four challenging benchmarks demonstrate the superiority of our proposed method over existing approaches. Our experimental results demonstrate the effectiveness of incorporating evidential uncertainty estimation to enhance 3D mitochondria segmentation, as EUMS-3D outperforms existing methods on four benchmark datasets |
| Researcher Affiliation | Collaboration | 1National Engineering Research Center of Visual Technology, National Key Laboratory for Multimedia Information Processing, School of Computer Science, Peking University 2Peng Cheng Laboratory 3Beijing Academy of Artificial Intelligence 4National Biomedical Imaging Center, Peking University |
| Pseudocode | No | The paper provides architectural diagrams and loss function equations, but no pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not contain any statement or link indicating that the source code for the methodology is openly available. |
| Open Datasets | Yes | We evaluate our method on four datasets: Mito EM-R (Wei et al. 2020), Mito EM-H (Wei et al. 2020), Kasthuri++ dataset (Casser et al. 2020) and Lucchi++ (Casser et al. 2020). Mito EM is a dense mitochondria instance segmentation dataset from ISBI 2021 challenge... |
| Dataset Splits | No | The paper specifies training and testing splits for the datasets (e.g., "400 for training and 100 for testing" for Mito EM), but does not explicitly mention a separate validation dataset or split. |
| Hardware Specification | No | The paper mentions using a "High-Performance Computing Platform of Peking University for providing computational resources" but does not specify any exact GPU models, CPU models, or other hardware details. |
| Software Dependencies | No | The paper does not list any specific software dependencies with version numbers (e.g., Python, PyTorch, CUDA versions). |
| Experiment Setup | Yes | The λ1 and λ2 in the loss function are set to be 1 and 0.5 following (Zou et al. 2022). To explore the influence of τ, we train the model using various threshold values τ = 0, 0.25, 0.5, 0.75, 1 on Mito EM-R dataset, respectively. |