notesum.ai
Published at November 22ReXrank: A Public Leaderboard for AI-Powered Radiology Report Generation
cs.CV
cs.AI
cs.CL
Released Date: November 22, 2024
Authors: Xiaoman Zhang1, Hong-Yu Zhou1, Xiaoli Yang1, Oishi Banerjee1, Julián N. Acosta1, Josh Miller2, Ouwen Huang2, Pranav Rajpurkar1
Aff.: 1Department of Biomedical Informatics, Harvard Medical School, Boston, MA, USA; 2Gradient Health, Durham, NC, USA

| Model | 1/RadCliQ-v1 | BLEU-2 | BertScore | SembScore | RadGraph | RaTEScore | GREEN | 1/FineRadScore |
| Findings + Impression | ||||||||
| MedVersa | 0.92 ± 0.02 | 0.19 ± 0.00 | 0.43 ± 0.01 | 0.32 ± 0.01 | 0.27 ± 0.01 | 0.55 ± 0.01 | 0.42 ± 0.01 | 0.36 ± 0.03 |
| CheXpertPlus_CheX_MIMIC | 0.83 ± 0.02 | 0.17 ± 0.00 | 0.36 ± 0.00 | 0.39 ± 0.01 | 0.20 ± 0.00 | 0.52 ± 0.00 | 0.37 ± 0.01 | 0.36 ± 0.03 |
| CheXpertPlus_MIMIC | 0.80 ± 0.02 | 0.17 ± 0.00 | 0.35 ± 0.00 | 0.38 ± 0.01 | 0.19 ± 0.00 | 0.51 ± 0.00 | 0.38 ± 0.01 | 0.36 ± 0.03 |
| CheXpertPlus_CheX | 0.71 ± 0.01 | 0.13 ± 0.00 | 0.30 ± 0.00 | 0.34 ± 0.01 | 0.17 ± 0.00 | 0.51 ± 0.00 | 0.30 ± 0.01 | 0.35 ± 0.03 |
| RadFM | 0.62 ± 0.02 | 0.08 ± 0.00 | 0.28 ± 0.00 | 0.24 ± 0.01 | 0.11 ± 0.00 | 0.45 ± 0.00 | 0.21 ± 0.01 | 0.35 ± 0.03 |
| GPT4V | 0.55 ± 0.01 | 0.07 ± 0.00 | 0.20 ± 0.00 | 0.19 ± 0.01 | 0.09 ± 0.00 | 0.43 ± 0.00 | 0.13 ± 0.01 | 0.33 ± 0.03 |
| Findings | ||||||||
| MedVersa | 1.10 ± 0.02 | 0.21 ± 0.00 | 0.45 ± 0.01 | 0.47 ± 0.01 | 0.27 ± 0.01 | 0.55 ± 0.01 | 0.37 ± 0.01 | 0.36 ± 0.03 |
| CheXpertPlus_CheX_MIMIC | 0.81 ± 0.02 | 0.14 ± 0.00 | 0.37 ± 0.00 | 0.38 ± 0.01 | 0.18 ± 0.01 | 0.49 ± 0.01 | 0.30 ± 0.01 | 0.36 ± 0.03 |
| RaDialog | 0.80 ± 0.02 | 0.13 ± 0.00 | 0.36 ± 0.00 | 0.39 ± 0.01 | 0.17 ± 0.00 | 0.48 ± 0.00 | 0.27 ± 0.01 | 0.36 ± 0.03 |
| CheXpertPlus_MIMIC | 0.79 ± 0.02 | 0.14 ± 0.00 | 0.36 ± 0.00 | 0.38 ± 0.01 | 0.17 ± 0.00 | 0.48 ± 0.01 | 0.31 ± 0.01 | 0.36 ± 0.03 |
| RGRG | 0.76 ± 0.02 | 0.13 ± 0.00 | 0.35 ± 0.00 | 0.34 ± 0.01 | 0.17 ± 0.00 | 0.49 ± 0.00 | 0.27 ± 0.01 | 0.35 ± 0.03 |
| CheXagent | 0.74 ± 0.02 | 0.11 ± 0.00 | 0.35 ± 0.01 | 0.35 ± 0.01 | 0.15 ± 0.00 | 0.47 ± 0.01 | 0.26 ± 0.01 | 0.35 ± 0.03 |
| Cvt2distilgpt2_MIMIC | 0.72 ± 0.02 | 0.13 ± 0.00 | 0.33 ± 0.01 | 0.33 ± 0.01 | 0.15 ± 0.01 | 0.43 ± 0.01 | 0.27 ± 0.01 | 0.36 ± 0.03 |
| CheXpertPlus_CheX | 0.70 ± 0.01 | 0.08 ± 0.00 | 0.31 ± 0.00 | 0.33 ± 0.01 | 0.14 ± 0.00 | 0.47 ± 0.00 | 0.23 ± 0.01 | 0.35 ± 0.03 |
| MAIRA-2 | 0.69 ± 0.02 | 0.09 ± 0.00 | 0.31 ± 0.00 | 0.34 ± 0.01 | 0.13 ± 0.00 | 0.52 ± 0.00 | 0.22 ± 0.01 | 0.36 ± 0.03 |
| VLCI_MIMIC | 0.68 ± 0.02 | 0.14 ± 0.00 | 0.30 ± 0.00 | 0.30 ± 0.01 | 0.14 ± 0.00 | 0.45 ± 0.01 | 0.26 ± 0.01 | 0.36 ± 0.03 |
| RadFM | 0.65 ± 0.02 | 0.09 ± 0.00 | 0.31 ± 0.00 | 0.26 ± 0.01 | 0.11 ± 0.00 | 0.45 ± 0.01 | 0.18 ± 0.01 | 0.35 ± 0.03 |
| Cvt2distilgpt2_IU | 0.61 ± 0.02 | 0.06 ± 0.00 | 0.30 ± 0.00 | 0.19 ± 0.01 | 0.10 ± 0.00 | 0.45 ± 0.01 | 0.16 ± 0.01 | 0.35 ± 0.03 |
| VLCI_IU | 0.60 ± 0.02 | 0.07 ± 0.00 | 0.26 ± 0.00 | 0.21 ± 0.01 | 0.11 ± 0.00 | 0.45 ± 0.01 | 0.21 ± 0.01 | 0.35 ± 0.03 |
| GPT4V | 0.56 ± 0.01 | 0.07 ± 0.00 | 0.21 ± 0.00 | 0.21 ± 0.01 | 0.08 ± 0.00 | 0.42 ± 0.00 | 0.16 ± 0.01 | 0.34 ± 0.03 |
| BiomedGPT_IU | 0.54 ± 0.01 | 0.02 ± 0.00 | 0.19 ± 0.00 | 0.22 ± 0.01 | 0.06 ± 0.00 | 0.36 ± 0.00 | 0.12 ± 0.01 | 0.34 ± 0.03 |
| LLM-CXR | 0.52 ± 0.01 | 0.04 ± 0.00 | 0.18 ± 0.00 | 0.16 ± 0.01 | 0.05 ± 0.00 | 0.34 ± 0.00 | 0.04 ± 0.00 | 0.31 ± 0.03 |