SPGNet: A Shape-prior Guided Network for Medical Image Segmentation
Authors: Zhengxuan Song, Xun Liu, Wenhao Zhang, Yongyi Gong, Tianyong Hao, Kun Zeng
IJCAI 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We demonstrate superior performance on chest X-ray and breast ultrasound benchmarks. We evaluate SPGNet on a chest X-ray dataset with prominent shape regularities and a breast ultrasound dataset with potential regularities. Results demonstrate superior accuracy over baselines and existing state-of-the-art methods, particularly in edge smoothness. |
| Researcher Affiliation | Academia | 1Sun Yat-sen University 2The Third Affiliated Hospital of Sun Yat-sen University 3University of the West of England 4Guangdong University of Foreign Studies 5South China Normal University |
| Pseudocode | No | The paper describes the model architecture and processes using text and diagrams (Figure 2, 4, 5, 6), but it does not include a dedicated pseudocode block or algorithm section. |
| Open Source Code | Yes | Corresponding author Code will be available at https://github.com/Chris97s/spgnet |
| Open Datasets | Yes | In our comprehensive evaluation, we utilized two publicly available datasets: chest X-rays and breast ultrasound image data. JSRT Dataset. The JSRT database [Shiraishi et al., 2000] consists of 247 high-resolution X-ray images... Breast Ultrasound Dataset (BUS). The Breast Ultrasound Dataset (BUS) [Al-Dhabyani et al., 2020] includes 780 breast ultrasound images... |
| Dataset Splits | Yes | For a fair quantitative comparison, all methods for dense pixel-level classification underwent evaluation using the same 5-fold cross-validation scheme, maintaining a standardized input resolution of 256 256. To validate each module, various coefficients in the mixed loss function were adjusted to reflect the combined effects. It was observed that three factors primarily contributed to the improvement: (i) DCM (Dual-path Collaboration Module): Coefficients λ1 and λ2 for Lseg were set during training to highlight the impact of DCM. Utilizing DCM, which enables collaborative learning of input image features by dual-path encoders, yielded enhancements of 1.65% for BUS and 0.03% for the right lung, emphasizing the effectiveness of our dual-path collaborative network structure. (ii) Supervision on Shape: Building upon the first factor (DCM), coefficients λ3 and λ4 for Lc and Lshape were introduced. This supervises the shape weights and guides the ASM Transformation output shape, leading to a significant 2.87% improvement for BUS and 0.12% for the right lung. This underscores the effectiveness of our offline-modeled, multi-class shape priors in guiding the segmentation network, demonstrating that deep learning segmentation networks, guided by diverse shape prior information, can significantly compensate for deficiencies in shape perception. (iii) Multi-stage Shape Refinement: Building upon the second factor (DCM+Tasm), coefficients λ5, λ6, and λ7 were sequentially introduced for each stage of shape refinement. With the introduction of each refinement stage, there has been a relative improvement of 0.3%, 0.81% and 1.07% for BUS, and 0.02%, 0.05% and 0.07% for the right |
| Hardware Specification | Yes | We implemented all evaluation methods on a server equipped with an NVIDIA Ge Force RTX 4090 GPU. |
| Software Dependencies | No | The paper mentions using the 'Adam optimizer' and implies the use of deep learning frameworks but does not specify any software names with version numbers (e.g., Python, PyTorch, TensorFlow versions). |
| Experiment Setup | Yes | The batch size was set to 16, utilizing the Adam optimizer. The initial learning rate was 0.0001, with weight decay at 0.0005, and a learning rate decay of 90% every 15 epochs. We performed 150 epochs of training on the JSRT dataset and 300 epochs on the Breast Ultrasound Dataset (BUS) while keeping the remaining training hyperparameters consistent. |