FAMNet: Frequency-aware Matching Network for Cross-domain Few-shot Medical Image Segmentation
Authors: Yuntian Bo, Yazhou Zhu, Lunbo Li, Haofeng Zhang
AAAI 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Combining these two modules, our FAMNet surpasses existing FSMIS models and Cross-domain Few-shot Semantic Segmentation models on three cross-domain datasets, achieving state-of-the-art performance in the CD-FSMIS task. Extended version https://arxiv.org/abs/2412.09319 On three cross-domain datasets, our proposed method achieves state-of-the-art performance. The effectiveness and superiority of our method are further verified through various ablation studies and visualization. |
| Researcher Affiliation | Academia | Yuntian Bo, Yazhou Zhu, Lunbo Li, Haofeng Zhang* School of Computer Science and Engineering, Nanjing University of Science and Technology, China EMAIL |
| Pseudocode | No | The paper describes the methodology in detail using mathematical formulations and textual descriptions, but it does not include any explicitly labeled pseudocode blocks or algorithms in a structured, code-like format. |
| Open Source Code | Yes | Code https://github.com/primebo1/FAMNet |
| Open Datasets | Yes | The Cross-Modality dataset comprises two abdominal datasets. The first is Abdominal MRI obtained from (Kavur et al. 2021)... The second is Abdominal CT, which comprises 20 3D abdominal CT scans from (Landman et al. 2015). The Cross-Sequence dataset is a cardiac dataset from (Zhuang et al. 2022) The Cross-Institution dataset consists of 321 3D prostate T2-weighted MRI scans collected by the University College London hospitals (UCLH) and 82 3D prostate MRI scans from the National Cancer Institute (NCI), Bethesda, Maryland, USA. The data from UCLH are collected from 4 studies: INDEX (Dickinson et al. 2013), the Smart Target Biopsy Trial (Hamid et al. 2019), PICTURE (Simmons et al. 2014), Promise12 (Simmons et al. 2014), and organized by (Li et al. 2023). The data from NCI are provided in (Choyke et al. 2016). |
| Dataset Splits | No | The paper mentions that "the model is optimized using a single source domain dataset Ds encompassing the base categories Cbase" and "subsequently, the model s performance is assessed on a target domain dataset Dt". It also states, "for each meta-learning task, we randomly divide the data into multiple episodes." However, it does not provide specific percentages or sample counts for how the overall datasets (Ds and Dt from the cited sources) are split into training, validation, or test sets. |
| Hardware Specification | Yes | Our method is implemented on an NVIDIA GeForce RTX 4080S GPU. |
| Software Dependencies | No | The paper mentions using a "ResNet-50 (He et al. 2016) feature encoder Eθ( ) pre-trained on MS-COCO (Lin et al. 2014)" but does not specify any software libraries, frameworks, or operating system versions with specific version numbers. |
| Experiment Setup | Yes | For all datasets, we train the model for 39K iterations, comprising 3000 iterations per epoch with the batch size set to 1. To comprehensively test the performance of our proposed model, we conduct bidirectional evaluations within each dataset. N for the adaptive average pooling in FAM is set to 302. In the multi-spectral decoupling of foreground features, we divide the frequency band into low, mid, and high frequencies with a ratio of 3:4:3. We chose the SGD optimizer with an initial learning rate of 0.001, a momentum of 0.9 and a decay factor of 0.95 every 1K iterations. |