Browse State-of-the-Art › Medical Report Generation

Medical Report Generation

46 papers with code · 3 benchmarks · 9 datasets archive 2025-07-28

MedicalMethodology

Medical report generation (MRG) is a task which focus on training AI to automatically generate professional report according the input image data. This can help clinicians make faster and more accurate decision since the task itself is both time consuming and error prone even for experienced doctors.

Aggfgg

Deep neural network and transformer based architecture are currently the most popular methods for this certain task, however, when we try to transfer out pre-trained model into this certain domain, their performance always degrade.

The following are some of the reasons why RSG is hard for pre-trained models:

  • Language datasets in a particular domain can sometimes be quite different from the large number of datasets available on the Internet
  • During the fine-tuning phase, datasets in the medical field are often unevenly distributed

More recently, multi-modal learning and contrastive learning have shown some inspiring results in this field, but it's still challenging and requires further attention.

Here are some additional readings to go deeper on the task:

  • On the Automatic Generation of Medical Imaging Reports

https://doi.org/10.48550/arXiv.1711.08195

  • A scoping review of transfer learning research on medical image analysis using ImageNet

https://arxiv.org/abs/2004.13175

  • A Survey on Incorporating Domain Knowledge into Deep Learning for Medical Image Analysis

https://arxiv.org/abs/2004.12150

(Image credit : Transformers in Medical Imaging: A Survey)

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

3 leaderboard tables shown for this task, 3 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.

DatasetBest model (first row in archive order)PaperCodeSyntologyCompare
MIMIC-CXR (2 rows) RGRG Interactive and Explainable Region-guided Radiology Report Generation code Syntology ran 0 of 10 samples · 10 unverified Compare
HistGen WSI-Report Dataset (1 row) HistGen HistGen: Histopathology Report Generation via Local-Global Feature... code Syntology ran 6 of 6 samples · 0 unverified Compare
IU X-Ray (1 row) X-RGen Act Like a Radiologist: Radiology Report Generation across... code — Compare

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

9 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

No subtask under this task in the archive's task tree.

Most implemented papers archive 2025-07-28

30 shown of 46 papers with code (110 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

Syntology lines on 6 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections