Understanding the robustness of vision-language models to medical image artefacts Article Swipe
Zijie Cheng
,
Ariel Yuhan Ong
,
Siegfried Wagner
,
David A. Merle
,
Lie Ju
,
Boxuan Li
,
Tiantian He
,
An Ran Ran
,
Hongyang Jiang
,
Dawei Yang
,
Ke Zou
,
Jocelyn Hui Lin Goh
,
Sahana Srinivasan
,
André Altmann
,
Daniel C. Alexander
,
Carol Y. Cheung
,
Yih Chung Tham
,
Pearse A. Keane
,
Yukun Zhou
·
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.1101/2025.05.13.25327495
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.1101/2025.05.13.25327495
Vision-language models (VLMs) can answer clinically relevant questions with their reasoning capabilities and user-friendly interfaces. However, their robustness to commonly existing medical image artefacts has not been explored, leaving major concerns in trustworthy clinical decision-making. In this study, we assessed the robustness of recent VLMs to medical image artefacts in disease detection across three different medical fields. Specifically, we included five categories of image artefacts, and evaluated the VLMs’ performance on images with and without artefacts. We build evaluation benchmarks in brain MRI, Chest X-ray, and retinal images, involving four real-world medical datasets. Our results demonstrate that VLMs showed poor performance on original unaltered images and performed even worse when weak artefacts were introduced. The strong artefacts were barely detected by those VLMs. Our findings indicate that VLMs are not yet capable of performing medical tasks with image artefacts, underscoring the critical need to explicitly incorporate artefact-aware method design and robustness tests into VLM development.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- https://doi.org/10.1101/2025.05.13.25327495
- https://www.medrxiv.org/content/medrxiv/early/2025/05/13/2025.05.13.25327495.full.pdf
- OA Status
- green
- References
- 43
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4410335782
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4410335782Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.1101/2025.05.13.25327495Digital Object Identifier
- Title
-
Understanding the robustness of vision-language models to medical image artefactsWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2025Year of publication
- Publication date
-
2025-05-13Full publication date if available
- Authors
-
Zijie Cheng, Ariel Yuhan Ong, Siegfried Wagner, David A. Merle, Lie Ju, Boxuan Li, Tiantian He, An Ran Ran, Hongyang Jiang, Dawei Yang, Ke Zou, Jocelyn Hui Lin Goh, Sahana Srinivasan, André Altmann, Daniel C. Alexander, Carol Y. Cheung, Yih Chung Tham, Pearse A. Keane, Yukun ZhouList of authors in order
- Landing page
-
https://doi.org/10.1101/2025.05.13.25327495Publisher landing page
- PDF URL
-
https://www.medrxiv.org/content/medrxiv/early/2025/05/13/2025.05.13.25327495.full.pdfDirect link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
greenOpen access status per OpenAlex
- OA URL
-
https://www.medrxiv.org/content/medrxiv/early/2025/05/13/2025.05.13.25327495.full.pdfDirect OA link when available
- Concepts
-
Robustness (evolution), Computer vision, Artificial intelligence, Computer science, Optometry, Medicine, Gene, Biochemistry, ChemistryTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
0Total citation count in OpenAlex
- References (count)
-
43Number of works referenced by this work
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4410335782 |
|---|---|
| doi | https://doi.org/10.1101/2025.05.13.25327495 |
| ids.doi | https://doi.org/10.1101/2025.05.13.25327495 |
| ids.openalex | https://openalex.org/W4410335782 |
| fwci | 0.0 |
| type | preprint |
| title | Understanding the robustness of vision-language models to medical image artefacts |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T11714 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9517999887466431 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/1707 |
| topics[0].subfield.display_name | Computer Vision and Pattern Recognition |
| topics[0].display_name | Multimodal Machine Learning Applications |
| topics[1].id | https://openalex.org/T12422 |
| topics[1].field.id | https://openalex.org/fields/27 |
| topics[1].field.display_name | Medicine |
| topics[1].score | 0.945900022983551 |
| topics[1].domain.id | https://openalex.org/domains/4 |
| topics[1].domain.display_name | Health Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/2741 |
| topics[1].subfield.display_name | Radiology, Nuclear Medicine and Imaging |
| topics[1].display_name | Radiomics and Machine Learning in Medical Imaging |
| topics[2].id | https://openalex.org/T10862 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9308000206947327 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/1702 |
| topics[2].subfield.display_name | Artificial Intelligence |
| topics[2].display_name | AI in cancer detection |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C63479239 |
| concepts[0].level | 3 |
| concepts[0].score | 0.7712928652763367 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q7353546 |
| concepts[0].display_name | Robustness (evolution) |
| concepts[1].id | https://openalex.org/C31972630 |
| concepts[1].level | 1 |
| concepts[1].score | 0.5884482860565186 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q844240 |
| concepts[1].display_name | Computer vision |
| concepts[2].id | https://openalex.org/C154945302 |
| concepts[2].level | 1 |
| concepts[2].score | 0.5736399292945862 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[2].display_name | Artificial intelligence |
| concepts[3].id | https://openalex.org/C41008148 |
| concepts[3].level | 0 |
| concepts[3].score | 0.5714148879051208 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[3].display_name | Computer science |
| concepts[4].id | https://openalex.org/C119767625 |
| concepts[4].level | 1 |
| concepts[4].score | 0.34172323346138 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q618211 |
| concepts[4].display_name | Optometry |
| concepts[5].id | https://openalex.org/C71924100 |
| concepts[5].level | 0 |
| concepts[5].score | 0.12227249145507812 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q11190 |
| concepts[5].display_name | Medicine |
| concepts[6].id | https://openalex.org/C104317684 |
| concepts[6].level | 2 |
| concepts[6].score | 0.0 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q7187 |
| concepts[6].display_name | Gene |
| concepts[7].id | https://openalex.org/C55493867 |
| concepts[7].level | 1 |
| concepts[7].score | 0.0 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q7094 |
| concepts[7].display_name | Biochemistry |
| concepts[8].id | https://openalex.org/C185592680 |
| concepts[8].level | 0 |
| concepts[8].score | 0.0 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q2329 |
| concepts[8].display_name | Chemistry |
| keywords[0].id | https://openalex.org/keywords/robustness |
| keywords[0].score | 0.7712928652763367 |
| keywords[0].display_name | Robustness (evolution) |
| keywords[1].id | https://openalex.org/keywords/computer-vision |
| keywords[1].score | 0.5884482860565186 |
| keywords[1].display_name | Computer vision |
| keywords[2].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[2].score | 0.5736399292945862 |
| keywords[2].display_name | Artificial intelligence |
| keywords[3].id | https://openalex.org/keywords/computer-science |
| keywords[3].score | 0.5714148879051208 |
| keywords[3].display_name | Computer science |
| keywords[4].id | https://openalex.org/keywords/optometry |
| keywords[4].score | 0.34172323346138 |
| keywords[4].display_name | Optometry |
| keywords[5].id | https://openalex.org/keywords/medicine |
| keywords[5].score | 0.12227249145507812 |
| keywords[5].display_name | Medicine |
| language | en |
| locations[0].id | doi:10.1101/2025.05.13.25327495 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S4306402567 |
| locations[0].source.issn | |
| locations[0].source.type | repository |
| locations[0].source.is_oa | False |
| locations[0].source.issn_l | |
| locations[0].source.is_core | False |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | bioRxiv (Cold Spring Harbor Laboratory) |
| locations[0].source.host_organization | https://openalex.org/I2750212522 |
| locations[0].source.host_organization_name | Cold Spring Harbor Laboratory |
| locations[0].source.host_organization_lineage | https://openalex.org/I2750212522 |
| locations[0].license | cc-by |
| locations[0].pdf_url | https://www.medrxiv.org/content/medrxiv/early/2025/05/13/2025.05.13.25327495.full.pdf |
| locations[0].version | acceptedVersion |
| locations[0].raw_type | posted-content |
| locations[0].license_id | https://openalex.org/licenses/cc-by |
| locations[0].is_accepted | True |
| locations[0].is_published | False |
| locations[0].raw_source_name | |
| locations[0].landing_page_url | https://doi.org/10.1101/2025.05.13.25327495 |
| indexed_in | crossref |
| authorships[0].author.id | https://openalex.org/A5037957119 |
| authorships[0].author.orcid | |
| authorships[0].author.display_name | Zijie Cheng |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Zijie Cheng |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5049283573 |
| authorships[1].author.orcid | https://orcid.org/0000-0001-9300-573X |
| authorships[1].author.display_name | Ariel Yuhan Ong |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Ariel Yuhan Ong |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5028939056 |
| authorships[2].author.orcid | https://orcid.org/0000-0003-4915-4353 |
| authorships[2].author.display_name | Siegfried Wagner |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Siegfried K. Wagner |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5044824530 |
| authorships[3].author.orcid | https://orcid.org/0000-0003-4485-5580 |
| authorships[3].author.display_name | David A. Merle |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | David A. Merle |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5100597439 |
| authorships[4].author.orcid | |
| authorships[4].author.display_name | Lie Ju |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Lie Ju |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5069878827 |
| authorships[5].author.orcid | https://orcid.org/0000-0001-9510-1098 |
| authorships[5].author.display_name | Boxuan Li |
| authorships[5].author_position | middle |
| authorships[5].raw_author_name | Boxuan Li |
| authorships[5].is_corresponding | False |
| authorships[6].author.id | https://openalex.org/A5101562779 |
| authorships[6].author.orcid | https://orcid.org/0000-0002-1604-3131 |
| authorships[6].author.display_name | Tiantian He |
| authorships[6].author_position | middle |
| authorships[6].raw_author_name | Tiantian He |
| authorships[6].is_corresponding | False |
| authorships[7].author.id | https://openalex.org/A5017279723 |
| authorships[7].author.orcid | https://orcid.org/0000-0003-4592-4867 |
| authorships[7].author.display_name | An Ran Ran |
| authorships[7].author_position | middle |
| authorships[7].raw_author_name | An Ran Ran |
| authorships[7].is_corresponding | False |
| authorships[8].author.id | https://openalex.org/A5065821874 |
| authorships[8].author.orcid | https://orcid.org/0000-0003-0287-8581 |
| authorships[8].author.display_name | Hongyang Jiang |
| authorships[8].author_position | middle |
| authorships[8].raw_author_name | Hongyang Jiang |
| authorships[8].is_corresponding | False |
| authorships[9].author.id | https://openalex.org/A5107958561 |
| authorships[9].author.orcid | https://orcid.org/0009-0002-0619-5059 |
| authorships[9].author.display_name | Dawei Yang |
| authorships[9].author_position | middle |
| authorships[9].raw_author_name | Dawei Yang |
| authorships[9].is_corresponding | False |
| authorships[10].author.id | https://openalex.org/A5060934622 |
| authorships[10].author.orcid | https://orcid.org/0000-0002-1181-1779 |
| authorships[10].author.display_name | Ke Zou |
| authorships[10].author_position | middle |
| authorships[10].raw_author_name | Ke Zou |
| authorships[10].is_corresponding | False |
| authorships[11].author.id | https://openalex.org/A5009380042 |
| authorships[11].author.orcid | https://orcid.org/0000-0002-5052-6081 |
| authorships[11].author.display_name | Jocelyn Hui Lin Goh |
| authorships[11].author_position | middle |
| authorships[11].raw_author_name | Jocelyn Hui Lin Goh |
| authorships[11].is_corresponding | False |
| authorships[12].author.id | https://openalex.org/A5083904001 |
| authorships[12].author.orcid | |
| authorships[12].author.display_name | Sahana Srinivasan |
| authorships[12].author_position | middle |
| authorships[12].raw_author_name | Sahana Srinivasan |
| authorships[12].is_corresponding | False |
| authorships[13].author.id | https://openalex.org/A5069743881 |
| authorships[13].author.orcid | https://orcid.org/0000-0002-9265-2393 |
| authorships[13].author.display_name | André Altmann |
| authorships[13].author_position | middle |
| authorships[13].raw_author_name | Andre Altmann |
| authorships[13].is_corresponding | False |
| authorships[14].author.id | https://openalex.org/A5033449704 |
| authorships[14].author.orcid | https://orcid.org/0000-0003-2439-350X |
| authorships[14].author.display_name | Daniel C. Alexander |
| authorships[14].author_position | middle |
| authorships[14].raw_author_name | Daniel C. Alexander |
| authorships[14].is_corresponding | False |
| authorships[15].author.id | https://openalex.org/A5019493583 |
| authorships[15].author.orcid | https://orcid.org/0000-0002-9672-1819 |
| authorships[15].author.display_name | Carol Y. Cheung |
| authorships[15].author_position | middle |
| authorships[15].raw_author_name | Carol Y. Cheung |
| authorships[15].is_corresponding | False |
| authorships[16].author.id | https://openalex.org/A5085096438 |
| authorships[16].author.orcid | https://orcid.org/0000-0002-6752-797X |
| authorships[16].author.display_name | Yih Chung Tham |
| authorships[16].author_position | middle |
| authorships[16].raw_author_name | Yih Chung Tham |
| authorships[16].is_corresponding | False |
| authorships[17].author.id | https://openalex.org/A5003259452 |
| authorships[17].author.orcid | https://orcid.org/0000-0002-9239-745X |
| authorships[17].author.display_name | Pearse A. Keane |
| authorships[17].author_position | middle |
| authorships[17].raw_author_name | Pearse A. Keane |
| authorships[17].is_corresponding | False |
| authorships[18].author.id | https://openalex.org/A5087083706 |
| authorships[18].author.orcid | https://orcid.org/0000-0002-0840-6422 |
| authorships[18].author.display_name | Yukun Zhou |
| authorships[18].author_position | last |
| authorships[18].raw_author_name | Yukun Zhou |
| authorships[18].is_corresponding | False |
| has_content.pdf | True |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://www.medrxiv.org/content/medrxiv/early/2025/05/13/2025.05.13.25327495.full.pdf |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Understanding the robustness of vision-language models to medical image artefacts |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T03:46:38.306776 |
| primary_topic.id | https://openalex.org/T11714 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9517999887466431 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/1707 |
| primary_topic.subfield.display_name | Computer Vision and Pattern Recognition |
| primary_topic.display_name | Multimodal Machine Learning Applications |
| related_works | https://openalex.org/W2772917594, https://openalex.org/W2036807459, https://openalex.org/W2058170566, https://openalex.org/W2755342338, https://openalex.org/W2166024367, https://openalex.org/W3116076068, https://openalex.org/W2229312674, https://openalex.org/W2951359407, https://openalex.org/W2079911747, https://openalex.org/W1969923398 |
| cited_by_count | 0 |
| locations_count | 1 |
| best_oa_location.id | doi:10.1101/2025.05.13.25327495 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S4306402567 |
| best_oa_location.source.issn | |
| best_oa_location.source.type | repository |
| best_oa_location.source.is_oa | False |
| best_oa_location.source.issn_l | |
| best_oa_location.source.is_core | False |
| best_oa_location.source.is_in_doaj | False |
| best_oa_location.source.display_name | bioRxiv (Cold Spring Harbor Laboratory) |
| best_oa_location.source.host_organization | https://openalex.org/I2750212522 |
| best_oa_location.source.host_organization_name | Cold Spring Harbor Laboratory |
| best_oa_location.source.host_organization_lineage | https://openalex.org/I2750212522 |
| best_oa_location.license | cc-by |
| best_oa_location.pdf_url | https://www.medrxiv.org/content/medrxiv/early/2025/05/13/2025.05.13.25327495.full.pdf |
| best_oa_location.version | acceptedVersion |
| best_oa_location.raw_type | posted-content |
| best_oa_location.license_id | https://openalex.org/licenses/cc-by |
| best_oa_location.is_accepted | True |
| best_oa_location.is_published | False |
| best_oa_location.raw_source_name | |
| best_oa_location.landing_page_url | https://doi.org/10.1101/2025.05.13.25327495 |
| primary_location.id | doi:10.1101/2025.05.13.25327495 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S4306402567 |
| primary_location.source.issn | |
| primary_location.source.type | repository |
| primary_location.source.is_oa | False |
| primary_location.source.issn_l | |
| primary_location.source.is_core | False |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | bioRxiv (Cold Spring Harbor Laboratory) |
| primary_location.source.host_organization | https://openalex.org/I2750212522 |
| primary_location.source.host_organization_name | Cold Spring Harbor Laboratory |
| primary_location.source.host_organization_lineage | https://openalex.org/I2750212522 |
| primary_location.license | cc-by |
| primary_location.pdf_url | https://www.medrxiv.org/content/medrxiv/early/2025/05/13/2025.05.13.25327495.full.pdf |
| primary_location.version | acceptedVersion |
| primary_location.raw_type | posted-content |
| primary_location.license_id | https://openalex.org/licenses/cc-by |
| primary_location.is_accepted | True |
| primary_location.is_published | False |
| primary_location.raw_source_name | |
| primary_location.landing_page_url | https://doi.org/10.1101/2025.05.13.25327495 |
| publication_date | 2025-05-13 |
| publication_year | 2025 |
| referenced_works | https://openalex.org/W4378474069, https://openalex.org/W4405081677, https://openalex.org/W4233926883, https://openalex.org/W4327909703, https://openalex.org/W2089445878, https://openalex.org/W3126423324, https://openalex.org/W4312114404, https://openalex.org/W2117276243, https://openalex.org/W2062091095, https://openalex.org/W2101891472, https://openalex.org/W3042451184, https://openalex.org/W2134346052, https://openalex.org/W2065767368, https://openalex.org/W2036792757, https://openalex.org/W2102887268, https://openalex.org/W3004179238, https://openalex.org/W4391310501, https://openalex.org/W4320914483, https://openalex.org/W4394797911, https://openalex.org/W4392120599, https://openalex.org/W4391472369, https://openalex.org/W4394014083, https://openalex.org/W4404143589, https://openalex.org/W4405063711, https://openalex.org/W4401336186, https://openalex.org/W4405995927, https://openalex.org/W4385387622, https://openalex.org/W4401750528, https://openalex.org/W2147065841, https://openalex.org/W2067018983, https://openalex.org/W4221143046, https://openalex.org/W4378498603, https://openalex.org/W4406260179, https://openalex.org/W4396673725, https://openalex.org/W4404584849, https://openalex.org/W6964665992, https://openalex.org/W4394117973, https://openalex.org/W6908586867, https://openalex.org/W6888486279, https://openalex.org/W2798251715, https://openalex.org/W2788633781, https://openalex.org/W3012412627, https://openalex.org/W2948685905 |
| referenced_works_count | 43 |
| abstract_inverted_index.In | 36 |
| abstract_inverted_index.We | 77 |
| abstract_inverted_index.by | 121 |
| abstract_inverted_index.in | 32, 50, 81 |
| abstract_inverted_index.of | 43, 63, 133 |
| abstract_inverted_index.on | 71, 102 |
| abstract_inverted_index.to | 19, 46, 144 |
| abstract_inverted_index.we | 39, 59 |
| abstract_inverted_index.Our | 94, 124 |
| abstract_inverted_index.The | 115 |
| abstract_inverted_index.VLM | 154 |
| abstract_inverted_index.and | 13, 66, 74, 86, 106, 150 |
| abstract_inverted_index.are | 129 |
| abstract_inverted_index.can | 4 |
| abstract_inverted_index.has | 25 |
| abstract_inverted_index.not | 26, 130 |
| abstract_inverted_index.the | 41, 68, 141 |
| abstract_inverted_index.yet | 131 |
| abstract_inverted_index.MRI, | 83 |
| abstract_inverted_index.VLMs | 45, 98, 128 |
| abstract_inverted_index.been | 27 |
| abstract_inverted_index.even | 108 |
| abstract_inverted_index.five | 61 |
| abstract_inverted_index.four | 90 |
| abstract_inverted_index.into | 153 |
| abstract_inverted_index.need | 143 |
| abstract_inverted_index.poor | 100 |
| abstract_inverted_index.that | 97, 127 |
| abstract_inverted_index.this | 37 |
| abstract_inverted_index.weak | 111 |
| abstract_inverted_index.were | 113, 118 |
| abstract_inverted_index.when | 110 |
| abstract_inverted_index.with | 9, 73, 137 |
| abstract_inverted_index.Chest | 84 |
| abstract_inverted_index.VLMs. | 123 |
| abstract_inverted_index.brain | 82 |
| abstract_inverted_index.build | 78 |
| abstract_inverted_index.image | 23, 48, 64, 138 |
| abstract_inverted_index.major | 30 |
| abstract_inverted_index.tasks | 136 |
| abstract_inverted_index.tests | 152 |
| abstract_inverted_index.their | 10, 17 |
| abstract_inverted_index.those | 122 |
| abstract_inverted_index.three | 54 |
| abstract_inverted_index.worse | 109 |
| abstract_inverted_index.(VLMs) | 3 |
| abstract_inverted_index.X-ray, | 85 |
| abstract_inverted_index.across | 53 |
| abstract_inverted_index.answer | 5 |
| abstract_inverted_index.barely | 119 |
| abstract_inverted_index.design | 149 |
| abstract_inverted_index.images | 72, 105 |
| abstract_inverted_index.method | 148 |
| abstract_inverted_index.models | 2 |
| abstract_inverted_index.recent | 44 |
| abstract_inverted_index.showed | 99 |
| abstract_inverted_index.strong | 116 |
| abstract_inverted_index.study, | 38 |
| abstract_inverted_index.VLMs’ | 69 |
| abstract_inverted_index.capable | 132 |
| abstract_inverted_index.disease | 51 |
| abstract_inverted_index.fields. | 57 |
| abstract_inverted_index.images, | 88 |
| abstract_inverted_index.leaving | 29 |
| abstract_inverted_index.medical | 22, 47, 56, 92, 135 |
| abstract_inverted_index.results | 95 |
| abstract_inverted_index.retinal | 87 |
| abstract_inverted_index.without | 75 |
| abstract_inverted_index.Abstract | 0 |
| abstract_inverted_index.However, | 16 |
| abstract_inverted_index.assessed | 40 |
| abstract_inverted_index.clinical | 34 |
| abstract_inverted_index.commonly | 20 |
| abstract_inverted_index.concerns | 31 |
| abstract_inverted_index.critical | 142 |
| abstract_inverted_index.detected | 120 |
| abstract_inverted_index.existing | 21 |
| abstract_inverted_index.findings | 125 |
| abstract_inverted_index.included | 60 |
| abstract_inverted_index.indicate | 126 |
| abstract_inverted_index.original | 103 |
| abstract_inverted_index.relevant | 7 |
| abstract_inverted_index.artefacts | 24, 49, 112, 117 |
| abstract_inverted_index.datasets. | 93 |
| abstract_inverted_index.detection | 52 |
| abstract_inverted_index.different | 55 |
| abstract_inverted_index.evaluated | 67 |
| abstract_inverted_index.explored, | 28 |
| abstract_inverted_index.involving | 89 |
| abstract_inverted_index.performed | 107 |
| abstract_inverted_index.questions | 8 |
| abstract_inverted_index.reasoning | 11 |
| abstract_inverted_index.unaltered | 104 |
| abstract_inverted_index.artefacts, | 65, 139 |
| abstract_inverted_index.artefacts. | 76 |
| abstract_inverted_index.benchmarks | 80 |
| abstract_inverted_index.categories | 62 |
| abstract_inverted_index.clinically | 6 |
| abstract_inverted_index.evaluation | 79 |
| abstract_inverted_index.explicitly | 145 |
| abstract_inverted_index.performing | 134 |
| abstract_inverted_index.real-world | 91 |
| abstract_inverted_index.robustness | 18, 42, 151 |
| abstract_inverted_index.demonstrate | 96 |
| abstract_inverted_index.incorporate | 146 |
| abstract_inverted_index.interfaces. | 15 |
| abstract_inverted_index.introduced. | 114 |
| abstract_inverted_index.performance | 70, 101 |
| abstract_inverted_index.trustworthy | 33 |
| abstract_inverted_index.capabilities | 12 |
| abstract_inverted_index.development. | 155 |
| abstract_inverted_index.underscoring | 140 |
| abstract_inverted_index.Specifically, | 58 |
| abstract_inverted_index.user-friendly | 14 |
| abstract_inverted_index.artefact-aware | 147 |
| abstract_inverted_index.Vision-language | 1 |
| abstract_inverted_index.decision-making. | 35 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 19 |
| citation_normalized_percentile.value | 0.16224323 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | False |