Research map / Detection and segmentation / CNN features
Effective Lymph Nodes Detection in CT Scans Using Location Debiased Query Selection and Contrastive Query Representation in Transformer
Qinji Yu, Yirui Wang, Ke Yan, Haoshen Li, Dazhou Guo, Li Zhang, Na Shen, Qifeng Wang, Xiaowei Ding, Le Lu, Xianghua Ye, Dakai Jin
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add multi-scale 2.5D feature fusion to Mask DINO (ablation) | Mask DINO · LN detection internal test | average recall (%): 51.32 -> 52.40 | Improved |
| add query contrastive learning on top of 2.5D fusion (ablation) | LN-DETR · LN detection internal test | average recall (%): 52.40 -> 53.44 | Improved |
| add location debiased query selection on top of 2.5D fusion (ablation) | LN-DETR · LN detection internal test | average recall (%): 52.40 -> 54.51 | Improved |
| combine debiased query selection and contrastive learning (ablation) | LN-DETR · LN detection internal test | average recall (%): 52.40 -> 56.27 | Improved |
| use LN-DETR instead of Mask DINO on external test | Mask DINO · LN detection external test | average recall (%): 46.89 -> 52.04 | Improved |
| apply detection transformer (Mask DINO) directly without LN-specific changes versus CNN-based MULAN | Mask DINO · LN detection external test | average recall (%): 48.03 -> 46.89 | Hurt |
| detect by instance segmentation (Mask2Former/MP-Former) instead of direct detection | LN detection · LN detection internal test | average recall (%): 45.11 and 47.69 vs 51.32 (Mask DINO) | Hurt |
| use LN-DETR on enlarged LNs (>=10mm) | Mask DINO · LN size >= 10mm | average recall (%): 72.01 -> 77.15 | Improved |
| apply LN-DETR to universal lesion detection on DeepLesion | LN-DETR · NIH DeepLesion test | average recall (%): 88.46 vs P3D* 88.55 | Mixed |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- Mask DINO — Mask DINO: Towards a Unified Transformer-Based Framework for Object Detection and Segmentation (CVPR 2023) · better on 3 of 3 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- CancerUniT: Towards a Single Unified Model for Effective Detection, Segmentation, and Diagnosis of Eight Major Cancers Using a Large Collection of CT Scans (ICCV 2023 · similarity 0.84)
- CT-Lesion: A Multi-Region CT Dataset for Co-existing Lesion Segmentation and Detection (NeurIPS 2026 · similarity 0.83)
- TumorChain: Interleaved Multimodal Chain-of-Thought Reasoning for Traceable Clinical Tumor Analysis (ICLR 2026 · similarity 0.83)
- Dual-Level Hypergraph Generation for Addressing Feature Scarcity in Whole-Slide Image Classification (CVPR 2026 · similarity 0.83)
- Large-scale and Fine-grained Vision-language Pre-training for Enhanced CT Image Understanding (ICLR 2025 · similarity 0.82)
- Patient-Level Anatomy Meets Scanning-Level Physics: Personalized Federated Low-Dose CT Denoising Empowered by Large Language Model (CVPR 2025 · similarity 0.81)
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.
