.png){kind=icon}
.png){kind=icon}
Return
MFF-Diff: A multi-level feature fusion conditional diffusion model for PET/CT tumor segmentation
.png){kind=icon}
PRE
AI
DOI：10.1016/j.asoc.2026.116260.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
<ul class="list">
<li class="react-xocs-list-item"><span class="list-label">•</span><span class="list-content">
<div class="u-margin-s-bottom" id="p0025">
A conditional diffusion framework is proposed for PET/CT tumor segmentation.
</div></span></li>
<li class="react-xocs-list-item"><span class="list-label">•</span><span class="list-content">
<div class="u-margin-s-bottom" id="p0030">
Modality-specific feature encoders enhance metabolic and anatomical feature learning.
</div></span></li>
<li class="react-xocs-list-item"><span class="list-label">•</span><span class="list-content">
<div class="u-margin-s-bottom" id="p0035">
A task-aware two-stage fusion strategy adapts PET/CT interaction during diffusion.
</div></span></li>
<li class="react-xocs-list-item"><span class="list-label">•</span><span class="list-content">
<div class="u-margin-s-bottom" id="p0040">
Global-structure modeling improves long-range dependency and structural consistency.
</div></span></li>
<li class="react-xocs-list-item"><span class="list-label">•</span><span class="list-content">
<div class="u-margin-s-bottom" id="p0045">
MFF-Diff improves Dice by 2.57 and 3.34 percentage points over the best competitor on HeadNeck and STS.
</div></span></li>
</ul>
Journal
IF:
6.6
Papers:
1.4W
Citations:
4.8W