AI Paper Atlas

Research map / Detection and segmentation / CNN features

OmniCT: Towards a Unified Slice-Volume LVLM for Comprehensive CT Analysis

Tianwei Lin, Zhongwei Qiu, Wenqiao Zhang, Jiang Liu, Yihan Xie, Mingjian Gao, Zhenxuan Fan, Zhaocheng Li, Sijing Li, Zhongle Xie, Peng LU, Yueting Zhuang and 3 more

ICLR 2026 · Detection and segmentation › CNN features · approach: Domain-specific segmentation and detection · 4 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Add Spatial Consistency Enhancement (SCE) (ablation)OmniCT · public 2D benchmarksaverage accuracy: 78.68 -> 80.14Improved
Add SCE (ablation)OmniCT · public 3D benchmarksaverage score: 62.17 -> 63.68Improved
Add Organ-level Semantic Enhancement (OSE) (ablation)OmniCT · public 3D benchmarksaverage score: 62.17 -> 65.37Improved
Add OSE (ablation)OmniCT · public 2D benchmarksaverage accuracy: 78.68 -> 80.74Improved
Add OSE on top of SCE (ablation)OmniCT · MedEval-CT-Benchaverage score: 78.06 -> 79.62Improved
Add SCE on top of OSE (ablation)OmniCT · MedEval-CT-Benchaverage score: 78.62 -> 79.62Improved
Add SCE and OSE together (ablation)OmniCT · public 3D benchmarksaverage score: 62.17 -> 66.15Improved
Use 2D SigLIP encoder instead of 3D M3D-CLIP (ablation)OmniCT · MedEval-CT-Bench native 3Daverage accuracy: 80.4 -> 82.9Improved
Use SigLIP instead of VideoMAEv2 3D encoder (ablation)OmniCT · MedEval-CT-Bench native 3Daverage accuracy: 76.2 -> 82.9Improved
Use DINOv3 (0.61x tokens) instead of SigLIP (ablation)OmniCT · MedEval-CT-Bench native 3Daverage accuracy: 82.9 -> 81.9Mixed
Use Phi-4-mini instead of Qwen2.5-3B as LLM backbone (ablation)OmniCT · MedEval-CT-Benchaverage score: 75.9 -> 76.2No clear effect
Scale OmniCT from 3B to 7BOmniCT · 2D CT benchmarksaverage accuracy: 77.71 -> 81.45Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy