Research map / Label-efficient and robust learning / Recognition and long-tail
Holistic and Comprehensive Annotation of Clinically Significant Findings on Diverse CT Images: Learning From Radiology Reports and Label Ontology
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 LesaNet instead of the multiscale multilabel CNN baseline | Multilabel lesion annotation · Text-mined and hand-labeled test sets | F1: 0.2823 -> 0.3423; 0.3894 -> 0.4344 | Helped |
| Add score propagation layer (ablation) | LesaNet · Text-mined and hand-labeled test sets | Recall: 0.4733 -> 0.5327; 0.4965 -> 0.5274 | Helped |
| Add relational hard example mining (RHEM) (ablation) | LesaNet · Text-mined and hand-labeled test sets | Precision: 0.2983 -> 0.3593; 0.4341 -> 0.4737 | Helped |
| Add hierarchical label expansion (ablation) | LesaNet · Text-mined and hand-labeled test sets | AUC: 0.9148 -> 0.9344; 0.9236 -> 0.9398 | Helped |
| Use the text-mining module to filter irrelevant labels (ablation) | LesaNet training labels · Text-mined test set | F1: 0.3324 -> 0.3423 | Helped |
| Add multilabel triplet loss (ablation) | LesaNet · Text-mined test set | F1: 0.3274 -> 0.3423 | Helped |
| Select hard negatives only from exclusive labels known to be reliable (ablation) | RHEM in LesaNet · Lesion annotation | Recall: +4% | Helped |
| Train with relevant and uncertain labels rather than relevant labels only (ablation) | LesaNet training labels · Lesion annotation | Accuracy | Helped |
| Jointly learn more labels rather than restricting training to a label subset (ablation) | LesaNet · Label subsets on the test set | F1 | No clear effect |
Closest papers by meaning
- Large-scale and Fine-grained Vision-language Pre-training for Enhanced CT Image Understanding (ICLR 2025 · similarity 0.86)
- Bootstrapping Chest CT Image Understanding by Distilling Knowledge from X-ray Expert Models (CVPR 2024 · similarity 0.84)
- MICA: Towards Explainable Skin Lesion Diagnosis via Multi-Level Image-Concept Alignment (AAAI 2024 · similarity 0.84)
- TumorChain: Interleaved Multimodal Chain-of-Thought Reasoning for Traceable Clinical Tumor Analysis (ICLR 2026 · similarity 0.83)
- A Trusted Lesion-assessment Network for Interpretable Diagnosis of Coronary Artery Disease in Coronary CT Angiography (AAAI 2025 · similarity 0.83)
- MEPNet: Medical Entity-Balanced Prompting Network for Brain CT Report Generation (AAAI 2025 · similarity 0.82)
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.