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].
Uncertainty-Guided Pixel Contrastive Learning for Semi-Supervised Medical Image Segmentation
Authors: Tao Wang, Jianglin Lu, Zhihui Lai, Jiajun Wen, Heng Kong
IJCAI 2022 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experiments conducted on popular medical image benchmarks demonstrate that the proposed method achieves better segmentation performance than the state-of-the-art methods. |
| Researcher Affiliation | Academia | 1College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China 2Shenzhen Institute of Artificial Intelligence and Robotics for Society, Shenzhen, China 3Shenzhen University General Hospital, Shenzhen, China |
| Pseudocode | No | The paper does not include any explicit pseudocode or algorithm blocks. |
| Open Source Code | No | The paper refers to 'SSL4MIS' with a GitHub link (https://github.com/Hi Lab-git/SSL4MIS), which is a benchmark for semi-supervised medical image segmentation, not explicitly the open-source code for the method proposed in this paper. |
| Open Datasets | Yes | We validate the proposed method on two public datasets: ACDC dataset [Bernard et al., 2018]... ISIC dataset [Codella et al., 2018]... |
| Dataset Splits | Yes | We divide the dataset in a ratio of 7:3 to obtain the training set and verification set. In training set, 5% (91) and 10% (181) images are labeled for different semi-supervised experiment settings. |
| Hardware Specification | Yes | We implement the methods using Py Torch library and train them on a NVIDIA RTX 2080Ti GPU. |
| Software Dependencies | No | The paper mentions 'Py Torch library' but does not specify its version or any other software dependencies with version numbers. |
| Experiment Setup | Yes | We use Res Net-50 to replace the encoder part of UNet and initialize its parameters with the weights pre-trained on Image Net. We adopt SGD as an optimizer with a weight decay of 0.0005 and a momentum of 0.9. The initial learning rate is set to 0.01, which will reduce to 0.001 by polynomial scheduler strategy during training. We implement the methods using Py Torch library and train them on a NVIDIA RTX 2080Ti GPU. The batch size is set to 16, where 8 images are labeled. All methods perform 6000 iterations during training. In this paper, we set λ1 = λ2 = 0.1 and λt is a temperature parameter that increases from 0 to 0.01. |