zllhhhh commited on
Commit
997d1f2
·
verified ·
1 Parent(s): 156f515

Model card: arXiv paper link and citation

Browse files
Files changed (1) hide show
  1. README.md +13 -2
README.md CHANGED
@@ -16,8 +16,7 @@ datasets:
16
 
17
  A 3D CT image–text encoder that scores any sentence against a CT volume and follows the image evidence for each
18
  finding: its score drops when the finding's organ is erased, stays when another organ is erased, and prefers the
19
- sentence that names the correct side. Paper: *ORGANIC-3D: Grounding 3D CT Vision Language Models in Organ-Level
20
- Image–Text Coupling*.
21
 
22
  · Code: https://github.com/lzl199704/organic3d
23
 
@@ -71,3 +70,15 @@ zero-shot tumour detection 75.0 and lesion-erasure hit rate 70.7 (AbdomenAtlas 3
71
  Trained on chest CT from one centre (CT-RATE) and abdominal CT from one centre (Merlin) with report-derived labels;
72
  performance elsewhere is unknown. Laterality is far from perfect (Side 76.9 / 63.8). Licence terms of COLIPRI, CT-RATE
73
  and Merlin apply.
 
 
 
 
 
 
 
 
 
 
 
 
 
16
 
17
  A 3D CT image–text encoder that scores any sentence against a CT volume and follows the image evidence for each
18
  finding: its score drops when the finding's organ is erased, stays when another organ is erased, and prefers the
19
+ sentence that names the correct side. Paper: [*ORGANIC-3D: Grounding 3D CT Vision Language Models in Organ-Level Image–Text Coupling*](https://arxiv.org/abs/2611.23529).
 
20
 
21
  · Code: https://github.com/lzl199704/organic3d
22
 
 
70
  Trained on chest CT from one centre (CT-RATE) and abdominal CT from one centre (Merlin) with report-derived labels;
71
  performance elsewhere is unknown. Laterality is far from perfect (Side 76.9 / 63.8). Licence terms of COLIPRI, CT-RATE
72
  and Merlin apply.
73
+
74
+ ## Citation
75
+
76
+ ```bibtex
77
+ @article{liu2026organic3d,
78
+ title = {ORGANIC3D: Grounding 3D CT Vision Language Models in Organ Level Image Text Coupling},
79
+ author = {Liu, Zelong and Ahmed, Hamza and Lee, Wynn Wingyi and Torjman, Mickael and Dimitrakakis, Alexander and
80
+ Lu, Jiahua and Deyer, Timothy and Taouli, Bachir and Fayad, Zahi A. and Mei, Xueyan},
81
+ journal = {arXiv preprint arXiv:2611.23529},
82
+ year = {2026}
83
+ }
84
+ ```