SicTTA: Single image continual test time adaptation for medical image segmentation [0.03%]
基于单张医学图像的连续测试时间自适应方法
Jianghao Wu,Xinya Liu,Guotai Wang et al.
Jianghao Wu et al.
Test Time Adaptation (TTA) enhances model robustness by adapting to unseen domains during testing. Existing methods typically rely on large batch sizes or pseudo-label generation, which are often impractical in clinical settings where data ...
An interactive and explainable AI approach to improve human-machine teaming in cancer subtyping from digital cytopathology [0.03%]
一种互动且可解释的AI方法，可通过数字细胞病理学改善癌症亚型的人机协作
Haomin Chen,Catalina Gomez,Zelia M Correa et al.
Haomin Chen et al.
Algorithmic decision support is rapidly becoming a staple of personalized medicine, particularly for high-stakes recommendations such as cancer subtyping in which access to patient-specific information can drastically alter the course of tr...
FairREAD: Re-fusing demographic attributes after disentanglement for fair medical image classification [0.03%]
基于解耦的公平医学图像分类方法
Yicheng Gao,Jinkui Hao,Bo Zhou
Yicheng Gao
Recent advancements in deep learning have shown transformative potential in medical imaging, yet concerns about fairness persist due to performance disparities across demographic subgroups. Existing methods aim to address these biases by mi...
BrachyPlan: A fine-grained efficient dose-guided inverse planning strategy for low-dose-rate brachytherapy [0.03%]
BrachyPlan: 一种用于低剂量率组织间插植治疗的细粒度、高效且基于剂量引导的逆向计划策略
Jiaxuan Liu,Haitao Li,Haochen Shi et al.
Jiaxuan Liu et al.
Brachytherapy delivers highly conformal doses for malignancies ranging from pancreatic to head-and-neck cancers, yet today's treatment-planning systems still depend on extensive manual manipulation and dose engines of uncertain accuracy. We...
3D masked autoencoder with spatiotemporal transformer for modeling of 4D fMRI data [0.03%]
具有时空变换器的3D掩码自动编码器用于4D fMRI数据分析建模
Jie Gao,Bao Ge,Ning Qiang et al.
Jie Gao et al.
Functional magnetic resonance imaging (fMRI) is a crucial tool in neuroscience for capturing dynamic brain activity across spatial and temporal dimensions. However, fMRI data are high-dimensional, spatiotemporal interdependent, and often no...
Unpaired volumetric harmonization of brain MRI with conditional latent diffusion [0.03%]
基于条件潜在扩散的未配对脑MRI体积谐调
Mengqi Wu,Minhui Yu,Shuaiming Jing et al.
Mengqi Wu et al.
Multi-site structural MRI is increasingly used in neuroimaging studies to diversify subject cohorts. However, combining MR images acquired from various sites/centers may introduce site-related non-biological variations. Retrospective image ...
Two-level semi-supervised collaborative medical image segmentation with bidirectional knowledge exchange [0.03%]
双向知识交流的两层半监督协作医学图像分割方法
Zhongda Zhao,Haiyan Wang,Tao Lei et al.
Zhongda Zhao et al.
Traditional co-training methods fail to leverage ensemble learning effectively, resulting in resource waste. To address this, we propose a two-level co-training structure. The first-level models follow a classical co-training approach, whil...
BUFNet: Boundary-aware and uncertainty-driven multi-modal fusion network for MR brain tumor segmentation [0.03%]
基于边界感知和不确定性驱动的多模态融合网络用于磁共振脑肿瘤图像分割
Tongxue Zhou,Su Ruan,Baiying Lei
Tongxue Zhou
Brain tumor segmentation plays a critical role in the diagnosis and treatment planning of brain tumors. However, achieving accurate segmentation is challenging due to the complex boundaries between different tumor sub-regions. Additionally,...
AdverIN: Monotonic adversarial intensity attack for domain generalization in medical image segmentation [0.03%]
用于医学图像分割的领域泛化单调对抗强度攻击
Zheyuan Zhang,Bin Wang,Lanhong Yao et al.
Zheyuan Zhang et al.
Domain generalization (DG) has emerged as a promising research direction because it can potentially enable deep learning models to handle data from previously unseen domains. DG methods try to achieve this by learning domain-invariant featu...
CIMB-MVQA: Causal intervention on modality-specific biases for medical visual question answering [0.03%]
基于模态特异偏差的因果干预的医学视觉问答研究
Bing Liu,Lijun Liu,Jiaman Ding et al.
Bing Liu et al.
Medical Visual Question Answering (Med-VQA) systems frequently rely on spurious visual and language cues produced by dataset biases and structural con-founders, which undermines robustness and real-world generalization. To alleviate spuriou...