요약
Abstract
1. 서론
2. 데이터셋
2.1 MIMIC-CXR
2.2 IU-Xray
3. 의료 영상 판독 소견서 자동 생성 연구동향
3.1 Dynamic Graph Enhanced Contrastive Learning for Chest X-ray Report Generation (DCL)
3.2 Interactive and Explainable Region-Guided Radiology Report Generation(RGRG)
3.3 Complex Organ Mask Guided Radiology Report Generation (COMG)
3.4 Improving Medical Report Generation with Adapter Tuning and Knowledge Enhancement in Vision-Language Foundation Model (MAKEN)
3.5 Knowledge-injected U-Transformer for Radiology Report Generation(KiUT)
3.6 Radiology Report Generation by Transformer with Multiple Learnable Expert Tokens (METransformer)
4. 평가 지표
4.1 Bilingual Evaluation Understudy(BLEU)
4.2 Metric for Evaluation of Translation with Explicit ORdering (METEOR)
4.3 Recall-Oriented Understudy for Gisting Evaluation (ROGUE)
4.4 Consensus-based Image Description Evaluation (CIDer)
5. 성능 비교
6. 결론
Acknowledgement
참고문헌