Research map / Detection and segmentation / Open-set and few-shot detection
ElixirNet: Relation-Aware Network Architecture Adaptation for Medical Lesion Detection
Chenhan Jiang, Shaoju Wang, Xiaodan Liang, Hang Xu, Nong Xiao
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 |
|---|---|---|---|
| Use ElixirNet with FPN instead of FPN | FPN · DeepLesion test, IoU, 3 FPs/image | sensitivity (%): 81.51 -> 86.63 | Improved |
| Use ElixirNet with FPN instead of FPN | FPN · DeepLesion test | mAP (%): 31.5 -> 35.2 | Improved |
| Use ElixirNet with Deformv2 instead of Deformv2 | Deformv2 · DeepLesion test, IoU, 3 FPs/image | sensitivity (%): 84.47 -> 86.92 | Improved |
| Use ElixirNet with Deformv2 instead of Deformv2 | Deformv2 · DeepLesion test | mAP (%): 34.3 -> 36.3 | Improved |
| Use ElixirNet with Deformv2 instead of Deformv2 | Deformv2 · Kits19 test | mAP (%): 32.9 -> 33.6 | Improved |
| Add RTM to ElixirNet without RTM (ablation) | ElixirNet multi-type detector · DeepLesion multi-type test, bone | sensitivity (%): 56.52 -> 57.38 | Improved |
| Add RTM to ElixirNet without RTM (ablation) | ElixirNet multi-type detector · DeepLesion multi-type test, abdomen | sensitivity (%): 84.14 -> 85.41 | Improved |
| Add RTM to ElixirNet without RTM (ablation) | ElixirNet multi-type detector · DeepLesion multi-type test, mediastinum | sensitivity (%): 83.41 -> 84.62 | Improved |
| Add RTM to ElixirNet without RTM (ablation) | ElixirNet multi-type detector · DeepLesion multi-type test, kidney | sensitivity (%): 60.70 -> 65.51 | Improved |
| Add RTM to ElixirNet without RTM (ablation) | ElixirNet multi-type detector · DeepLesion multi-type test, pelvis | sensitivity (%): 80.64 -> 83.07 | Improved |
| Use the proposed medical-oriented ALB search space instead of the classification-NAS search space (ablation) | ElixirNet · DeepLesion test, IoU, 3 FPs/image | sensitivity (%): 81.06 -> 83.88 | Improved |
| Use the proposed medical-oriented ALB search space instead of the classification-NAS search space (ablation) | ElixirNet · DeepLesion test | mAP (%): 32.1 -> 34.1 | Improved |
Closest papers by meaning
- EasyLens: A Training-Free Plug-and-Play Subtle-Lesion Representation Amplifier for Medical Vision-Language Models (NeurIPS 2026 · similarity 0.85)
- MICA: Towards Explainable Skin Lesion Diagnosis via Multi-Level Image-Concept Alignment (AAAI 2024 · similarity 0.85)
- Prompt as Knowledge Bank: Boost Vision-language model via Structural Representation for zero-shot medical detection (ICLR 2025 · similarity 0.84)
- Samba: Severity-aware Recurrent Modeling for Cross-domain Medical Image Grading (NeurIPS 2024 · similarity 0.83)
- TumorChain: Interleaved Multimodal Chain-of-Thought Reasoning for Traceable Clinical Tumor Analysis (ICLR 2026 · similarity 0.83)
- A Textbook Remedy for Domain Shifts: Knowledge Priors for Medical Image Analysis (NeurIPS 2024 · similarity 0.83)
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.
