Research map / Detection and segmentation / Open-set and few-shot detection
Co-Heterogeneous and Adaptive Segmentation from Multi-Source and Multi-Phase CT Imaging Data: A Study on Pathological Liver and Lesion Segmentation
Ashwin Raju, Chi-Tung Cheng, Yuankai Huo, Jinzheng Cai, Junzhou Huang, Jing Xiao, Le Lu, ChienHung Liao, Adam P. Harrison
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 co-training over contrast phases (ablation) | PHNN baseline · CGMH PACS (all phases) | DSC: 91.4 -> 94.0 | Improved |
| add hetero-modality fusion to co-training (co-heterogeneous training) (ablation) | co-training · CGMH PACS (all phases) | DSC: 94.0 -> 94.7 | Improved |
| add adversarial domain adaptation on the consensus prediction (ablation) | Co-hetero · CGMH PACS (all phases) | DSC: 94.7 -> 95.0 | Improved |
| add hole-based pseudo-labelling (ablation) | Co-hetero w ADA · CGMH PACS (all phases) | DSC: 95.0 -> 95.4 | Improved |
| add hole-based pseudo-labelling (ablation) | Baseline · CGMH PACS (NC phase) | DSC: 84.6 -> 89.4 | Improved |
| add ADA to the baseline (ablation) | Baseline · CGMH PACS (NC phase) | DSC: 84.6 -> 90.9 | Improved |
| add CHASe semi-supervised learning on unlabelled multi-phase data | PHNN baseline · CGMH PACS (NC phase) | DSC: 84.6 -> 94.0 | Improved |
| add CHASe semi-supervised learning | PHNN baseline · CGMH PACS (V phase) | DSC: 90.7 -> 94.9 | Improved |
| add CHASe semi-supervised learning | PHNN baseline · CGMH PACS (all phases) | ASSD: 1.21 -> 0.63 | Improved |
| add hole-based pseudo-labelling (ablation) | Co-hetero w ADA · Public labelled test set (lesion) | DSC: 61.0 -> 60.3 | Hurt |
| add CHASe components | PHNN baseline · Public labelled test set (lesion) | DSC: 47.5 -> 60.3 | Improved |
| add CHASe components | PHNN baseline · Public labelled test set (liver) | DSC: 96.3 -> 96.8 | No clear effect |
Closest papers by meaning
- AMOS: A Large-Scale Abdominal Multi-Organ Benchmark for Versatile Medical Image Segmentation (NeurIPS 2022 · similarity 0.86)
- Continual Segment: Towards a Single, Unified and Non-forgetting Continual Segmentation Model of 143 Whole-body Organs in CT Scans (ICCV 2023 · similarity 0.86)
- Training Like a Medical Resident: Context-Prior Learning Toward Universal Medical Image Segmentation (CVPR 2024 · similarity 0.85)
- Touchstone Benchmark: Are We on the Right Way for Evaluating AI Algorithms for Medical Segmentation? (NeurIPS 2024 · similarity 0.85)
- CAT: Coordinating Anatomical-Textual Prompts for Multi-Organ and Tumor Segmentation (NeurIPS 2024 · similarity 0.85)
- Interactive Medical Image Segmentation: A Benchmark Dataset and Baseline (CVPR 2025 · similarity 0.85)
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.
