{"url":"/sota/medical-report-generation-on-mimic-cxr","task":{"name":"Medical Report Generation","url":"/task/medical-report-generation","note":null},"dataset":{"name":"MIMIC-CXR","url":"/dataset/mimic-cxr"},"category":"Medical","categories":["Medical","Methodology"],"category_note":null,"description":"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.\r\n\r\nAggfgg\r\n\r\nDeep 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. \r\n\r\n\r\n\r\nThe following are some of the reasons why RSG is hard for pre-trained models:\r\n\r\n* Language datasets in a particular domain can sometimes be quite different from the large number of datasets available on the Internet\r\n* During the fine-tuning phase, datasets in the medical field are often unevenly distributed\r\n\r\n\r\n\r\nMore recently, multi-modal learning and contrastive learning have shown some inspiring results in this field, but it's still challenging and requires further attention.\r\n\r\n\r\n\r\nHere are some additional readings to go deeper on the task:\r\n\r\n* On the Automatic Generation of Medical Imaging Reports\r\n\r\n  [ https://doi.org/10.48550/arXiv.1711.08195](https://doi.org/10.48550/arXiv.1711.08195)\r\n\r\n* A scoping review of transfer learning research on medical image analysis using ImageNet \r\n\r\n  [ https://arxiv.org/abs/2004.13175](https://arxiv.org/abs/2004.13175)\r\n\r\n* A Survey on Incorporating Domain Knowledge into Deep Learning for Medical Image Analysis\r\n\r\n [ https://arxiv.org/abs/2004.12150]( https://arxiv.org/abs/2004.12150)\r\n\r\n\r\n\r\n\r\n\r\n(Image credit : Transformers in Medical Imaging: A Survey)","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["BLEU-1","BLEU-2","BLEU-3","BLEU-4","CIDEr","Example-F1-14","Example-Precision-14","Example-Recall-14","METEOR","Micro-F1-5","Micro-Precision-5","Micro-Recall-5","ROUGE-L","F1 RadGraph"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"BLEU-1":"higher","BLEU-2":"higher","BLEU-3":"higher","BLEU-4":"higher","CIDEr":null,"Example-F1-14":"higher","Example-Precision-14":"higher","Example-Recall-14":"higher","METEOR":null,"Micro-F1-5":"higher","Micro-Precision-5":"higher","Micro-Recall-5":"higher","ROUGE-L":"higher","F1 RadGraph":"higher"}},"counts":{"rows":2,"rows_with_code":2,"rows_with_paper_page":2,"rows_dated":2,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"RGRG","metrics":{"BLEU-1":"37.3","BLEU-2":"24.9","BLEU-3":"17.5","BLEU-4":"12.6","CIDEr":"49.5","Example-F1-14":"0.447","Example-Precision-14":"0.461","Example-Recall-14":"0.475","METEOR":"16.8","Micro-F1-5":"0.547","Micro-Precision-5":"0.491","Micro-Recall-5":"0.617","ROUGE-L":"26.4"},"uses_additional_data":false,"paper_date":"2023-04-17","paper":"/paper/interactive-and-explainable-region-guided","paper_url":"https://arxiv.org/abs/2304.08295v1","paper_title":"Interactive and Explainable Region-guided Radiology Report Generation","code":"https://github.com/ttanida/rgrg","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":10,"n_samples":10,"n_pointer_only_licence":0}},{"rank_in_archive_order":2,"model":"SEI-1","metrics":{"BLEU-2":"0.247","BLEU-4":"0.135","Example-F1-14":"0.460","F1 RadGraph":"0.249","METEOR":"0.158","Micro-F1-5":"0.542","ROUGE-L":"0.299"},"uses_additional_data":false,"paper_date":"2024-05-23","paper":"/paper/structural-entities-extraction-and-patient","paper_url":"https://arxiv.org/abs/2405.14905v1","paper_title":"Structural Entities Extraction and Patient Indications Incorporation for Chest X-ray Report Generation","code":"https://github.com/mk-runner/sei","n_code_links":1,"syntology":null}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,264 of the 9,581 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9581,"papers_checked":6264,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":3316},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":1,"rows_with_any_sample_ran":0,"distinct_papers_with_graph_line":1,"distinct_papers_with_any_sample_ran":0,"samples_over_distinct_papers":{"n_ran":0,"n_unverified":10,"n_samples":10,"n_pointer_only_licence":0,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":0,"n_unverified":10,"n_samples":10,"n_pointer_only_licence":0,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}