# Medical Report Generation on DeepEyeNet Source: [Medical Report Generation on DeepEyeNet]() Collection index: [llms.txt]() Data updated: 2026-04-21T09:56:18.671Z Evaluation of models generating medical reports using the DeepEyeNet dataset, assessed using standard text generation metrics (BLEU, ROUGE, CIDEr) and BERT-F1. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Medical Report Generation | | Dataset (including any stated split) | DeepEyeNet | | Metric | BLEU-1 | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 14 of 14 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [BLEU-1](): Higher is better; unit: SCALAR. - [BLEU-2](): Higher is better; unit: SCALAR. - [BLEU-3](): Higher is better; unit: SCALAR. - [BLEU-4](): Higher is better; unit: SCALAR. - [CIDEr](): Higher is better; unit: SCALAR. - [ROUGE](): Higher is better; unit: SCALAR. - [BERT-F1](): Higher is better; unit: SCALAR. ## Recorded results | Method | BLEU-1 | Result date | Report paper | | --- | --- | --- | --- | | DREAM | 0.447 | Not recorded | 69e704ca7d0172140ec7ef90 | | GCS-M3VLT | 0.43 | Not recorded | 69e704ca7d0172140ec7ef90 | | mPLUG-Owl2 Adaptor | 0.416 | Not recorded | 69e704ca7d0172140ec7ef90 | | M3 Transformer | 0.394 | Not recorded | 69e704ca7d0172140ec7ef90 | | LLaVA-Med | 0.386 | Not recorded | 69e704ca7d0172140ec7ef90 | | Expert Transformer | 0.382 | Not recorded | 69e704ca7d0172140ec7ef90 | | VisionGPT | 0.353 | Not recorded | 69e704ca7d0172140ec7ef90 | | GC Transformer | 0.297 | Not recorded | 69e704ca7d0172140ec7ef90 | | Show, Attend & Tell | 0.264 | Not recorded | 69e704ca7d0172140ec7ef90 | | Non-local Attention | 0.23 | Not recorded | 69e704ca7d0172140ec7ef90 | | Deep Context Model | 0.219 | Not recorded | 69e704ca7d0172140ec7ef90 | | Show and Tell | 0.207 | Not recorded | 69e704ca7d0172140ec7ef90 | | Contextualized GPT | 0.203 | Not recorded | 69e704ca7d0172140ec7ef90 | | DeepOpth | 0.184 | Not recorded | 69e704ca7d0172140ec7ef90 | ### DREAM BLEU-1: 0.447. Result ID: 69e749b347f34ce924cdff53. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of parameters":"0.36B","GFLOPs":"5"}. This record does not assert independent reproduction. ### GCS-M3VLT BLEU-1: 0.43. Result ID: 69e749b347f34ce924cdff4f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### mPLUG-Owl2 Adaptor BLEU-1: 0.416. Result ID: 69e749b347f34ce924cdff52. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Fine-tuned":"true"}. This record does not assert independent reproduction. ### M3 Transformer BLEU-1: 0.394. Result ID: 69e749b347f34ce924cdff4e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### LLaVA-Med BLEU-1: 0.386. Result ID: 69e749b347f34ce924cdff51. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Fine-tuned":"true"}. This record does not assert independent reproduction. ### Expert Transformer BLEU-1: 0.382. Result ID: 69e749b347f34ce924cdff4d. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### VisionGPT BLEU-1: 0.353. Result ID: 69e749b347f34ce924cdff50. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Fine-tuned":"true"}. This record does not assert independent reproduction. ### GC Transformer BLEU-1: 0.297. Result ID: 69e749b347f34ce924cdff4c. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Show, Attend & Tell BLEU-1: 0.264. Result ID: 69e749b347f34ce924cdff47. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Non-local Attention BLEU-1: 0.23. Result ID: 69e749b347f34ce924cdff4b. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Deep Context Model BLEU-1: 0.219. Result ID: 69e749b347f34ce924cdff49. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Show and Tell BLEU-1: 0.207. Result ID: 69e749b347f34ce924cdff46. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Contextualized GPT BLEU-1: 0.203. Result ID: 69e749b347f34ce924cdff4a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### DeepOpth BLEU-1: 0.184. Result ID: 69e749b347f34ce924cdff48. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.