Semi-supervised TEE Segmentation via Interacting with SAM Equipped with Noise-Resilient Prompting
Authors: Sen Deng, Yidan Feng, Haoneng Lin, Yiting Fan, Alex Pui-Wai Lee, Xiaowei Hu, Jing Qin
AAAI 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We conduct extensive experiments on an in-house TEE dataset; experimental results demonstrate that our method achieves better performance than state-of-the-art SSL models. |
| Researcher Affiliation | Collaboration | 1 Centre for Smart Health, School of Nursing, The Hong Kong Polytechnic University 2 Department of cardiology, Shanghai Chest Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, 200030, China 3 Division of Cardiology, Department of Medicine and Therapeutics, The Chinese University of Hong Kong 4 Shanghai Artificial Intelligence Laboratory |
| Pseudocode | Yes | Algorithm 1: Pseudo code of our training strategy |
| Open Source Code | No | The paper does not provide an explicit statement or link indicating that the source code for the described methodology is publicly available. |
| Open Datasets | No | The dataset consists of TEE data from 100 patients. We randomly divided the patients into three sets, with 70/30 for training and testing. |
| Dataset Splits | No | The paper states "We randomly divided the patients into three sets, with 70/30 for training and testing," but does not specify a separate validation set split or percentages for a three-way split (train/validation/test). |
| Hardware Specification | Yes | All the experiments are conducted on 4 NVIDIA 3090 GPUs. |
| Software Dependencies | No | The paper mentions that the network is optimized using Adam W, but does not specify version numbers for any software dependencies, libraries, or programming languages used. |
| Experiment Setup | Yes | The network is optimized using Adam W with a mini-batch size of 8 and trained for a total of 300 epochs. The learning rate is initialized as 0.004, which is divided by 2 every 60 epochs. The proportion of p in the SPFA algorithm and the selected points number k is set as 0.7 and 6 in our experiment. |