Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in [1].
SGTC: Semantic-Guided Triplet Co-training for Sparsely Annotated Semi-Supervised Medical Image Segmentation
Authors: Ke Yan, Qing Cai, Fan Zhang, Ziyan Cao, Zhi Liu
AAAI 2025 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experiments on three public medical datasets demonstrate that our method outperforms most state-of-the-art semi-supervised counterparts under sparse annotation settings. The source code is available at https://github.com/xmeimeimei/SGTC. |
| Researcher Affiliation | Academia | 1Faculty of Computer Science and Technology, Ocean University of China 2School of Automation, Northwestern Polytechnical University 3School of Information Science and Engineering, Shandong University EMAIL, EMAIL, EMAIL, EMAIL |
| Pseudocode | No | The paper describes the proposed Semantic-Guided Triplet Co-Training (SGTC) framework and its components using natural language descriptions, mathematical equations, and an architectural diagram (Figure 2). However, it does not include any explicitly labeled pseudocode or algorithm blocks. |
| Open Source Code | Yes | Extensive experiments on three public medical datasets demonstrate that our method outperforms most state-of-the-art semi-supervised counterparts under sparse annotation settings. The source code is available at https://github.com/xmeimeimei/SGTC. |
| Open Datasets | Yes | LA2018 Dataset (Xiong et al. 2021) contains 100 gadolinium enhanced MR imaging scans with labels. Ki TS19 Dataset (Heller et al. 2019) is provided by the Medical Centre of Minnesota University and consists of 300 abdominal CT scans. Li TS Dataset (Bilic et al. 2023) is a CT dataset focused on liver and liver tumour segmentation. |
| Dataset Splits | Yes | LA2018 Dataset...we utilize 80 training samples and 20 testing samples for fair comparison with other methods. Ki TS19 Dataset...The dataset is divided into 190 training samples and 20 testing samples. Li TS Dataset...where 100 scans are used for training, and the remaining 31 scans for test. |
| Hardware Specification | No | The paper mentions training is conducted in the PyTorch framework but does not provide any specific details about the hardware used (e.g., GPU model, CPU, memory). |
| Software Dependencies | No | The paper states, "The entire training is conducted in the Py Torch framework." However, it does not specify a version number for PyTorch or any other software libraries used. |
| Experiment Setup | Yes | The entire training is conducted in the Py Torch framework. We set the batch size to 4, with each batch containing two volumes with labels and two volumes without labels. We train for 6000 iterations using the Stochastic Gradient Descent (SGD) optimizer. The initial learning rate is set to 0.01 and gradually decays to 0.0001. The value of parameter α is initialized to 0.1 and is increased every 150 iterations. |