.png){kind=icon}
.png){kind=icon}
Return
Report Supervision
.png){kind=icon}
PRE
AI
DOI：10.1016/j.media.2026.104257.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="d1e2195">
Radiology reports directly supervise tumor segmentation training.
</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="d1e2200">
Volume Loss and Ball Loss teach segmentation models to segment tumors matching reports in tumor count, sizes, and locations.
</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="d1e2205">
Reports scale segmentation datasets when masks are few or many.
</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="d1e2210">
R-Super gains up to +15% F1-Score and DSC over mask-only training.
</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="d1e2215">
R-Super improves tumor detection at unseen external hospitals and for small tumors.
</div></span></li>
</ul>
Keywords:
Tumor detection
Tumor segmentation
Radiology reports
Weak supervision
Computed tomography
Journal
IF:
11.8
Papers:
3.8K
Citations:
2.4W
Organization
View more organizations