Automated detection of pulmonary embolism from CT-angiograms using deep learning Article Swipe
Heidi Huhtanen
,
Mikko Nyman
,
Tarek Mohsen
,
Arho Virkki
,
Antti Karlsson
,
Jussi Hirvonen
·
YOU?
·
· 2022
· Open Access
·
· DOI: https://doi.org/10.1186/s12880-022-00763-z
YOU?
·
· 2022
· Open Access
·
· DOI: https://doi.org/10.1186/s12880-022-00763-z
Background The aim of this study was to develop and evaluate a deep neural network model in the automated detection of pulmonary embolism (PE) from computed tomography pulmonary angiograms (CTPAs) using only weakly labelled training data. Methods We developed a deep neural network model consisting of two parts: a convolutional neural network architecture called InceptionResNet V2 and a long-short term memory network to process whole CTPA stacks as sequences of slices. Two versions of the model were created using either chest X-rays (Model A) or natural images (Model B) as pre-training data. We retrospectively collected 600 CTPAs to use in training and validation and 200 CTPAs to use in testing. CTPAs were annotated only with binary labels on both stack- and slice-based levels. Performance of the models was evaluated with ROC and precision–recall curves, specificity, sensitivity, accuracy, as well as positive and negative predictive values. Results Both models performed well on both stack- and slice-based levels. On the stack-based level, Model A reached specificity and sensitivity of 93.5% and 86.6%, respectively, outperforming Model B slightly (specificity 90.7% and sensitivity 83.5%). However, the difference between their ROC AUC scores was not statistically significant (0.94 vs 0.91, p = 0.07). Conclusions We show that a deep learning model trained with a relatively small, weakly annotated dataset can achieve excellent performance results in detecting PE from CTPAs.
Related Topics
Concepts
Artificial intelligence
Deep learning
Convolutional neural network
Receiver operating characteristic
Computer science
Pulmonary embolism
Binary classification
Sensitivity (control systems)
Artificial neural network
Pattern recognition (psychology)
Gold standard (test)
Radiology
Medicine
Machine learning
Support vector machine
Surgery
Engineering
Electronic engineering
Metadata
- Type
- article
- Language
- en
- Landing Page
- https://doi.org/10.1186/s12880-022-00763-z
- https://bmcmedimaging.biomedcentral.com/track/pdf/10.1186/s12880-022-00763-z
- OA Status
- gold
- Cited By
- 73
- References
- 40
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4220661517
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4220661517Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.1186/s12880-022-00763-zDigital Object Identifier
- Title
-
Automated detection of pulmonary embolism from CT-angiograms using deep learningWork title
- Type
-
articleOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2022Year of publication
- Publication date
-
2022-03-14Full publication date if available
- Authors
-
Heidi Huhtanen, Mikko Nyman, Tarek Mohsen, Arho Virkki, Antti Karlsson, Jussi HirvonenList of authors in order
- Landing page
-
https://doi.org/10.1186/s12880-022-00763-zPublisher landing page
- PDF URL
-
https://bmcmedimaging.biomedcentral.com/track/pdf/10.1186/s12880-022-00763-zDirect link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
goldOpen access status per OpenAlex
- OA URL
-
https://bmcmedimaging.biomedcentral.com/track/pdf/10.1186/s12880-022-00763-zDirect OA link when available
- Concepts
-
Artificial intelligence, Deep learning, Convolutional neural network, Receiver operating characteristic, Computer science, Pulmonary embolism, Binary classification, Sensitivity (control systems), Artificial neural network, Pattern recognition (psychology), Gold standard (test), Radiology, Medicine, Machine learning, Support vector machine, Surgery, Engineering, Electronic engineeringTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
73Total citation count in OpenAlex
- Citations by year (recent)
-
2025: 30, 2024: 21, 2023: 15, 2022: 7Per-year citation counts (last 5 years)
- References (count)
-
40Number of works referenced by this work
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4220661517 |
|---|---|
| doi | https://doi.org/10.1186/s12880-022-00763-z |
| ids.doi | https://doi.org/10.1186/s12880-022-00763-z |
| ids.pmid | https://pubmed.ncbi.nlm.nih.gov/35282821 |
| ids.openalex | https://openalex.org/W4220661517 |
| fwci | 21.68486435 |
| mesh[0].qualifier_ui | |
| mesh[0].descriptor_ui | D000792 |
| mesh[0].is_major_topic | False |
| mesh[0].qualifier_name | |
| mesh[0].descriptor_name | Angiography |
| mesh[1].qualifier_ui | |
| mesh[1].descriptor_ui | D000077321 |
| mesh[1].is_major_topic | True |
| mesh[1].qualifier_name | |
| mesh[1].descriptor_name | Deep Learning |
| mesh[2].qualifier_ui | |
| mesh[2].descriptor_ui | D006801 |
| mesh[2].is_major_topic | False |
| mesh[2].qualifier_name | |
| mesh[2].descriptor_name | Humans |
| mesh[3].qualifier_ui | Q000000981 |
| mesh[3].descriptor_ui | D011655 |
| mesh[3].is_major_topic | True |
| mesh[3].qualifier_name | diagnostic imaging |
| mesh[3].descriptor_name | Pulmonary Embolism |
| mesh[4].qualifier_ui | |
| mesh[4].descriptor_ui | D012189 |
| mesh[4].is_major_topic | False |
| mesh[4].qualifier_name | |
| mesh[4].descriptor_name | Retrospective Studies |
| mesh[5].qualifier_ui | |
| mesh[5].descriptor_ui | D014057 |
| mesh[5].is_major_topic | False |
| mesh[5].qualifier_name | |
| mesh[5].descriptor_name | Tomography, X-Ray Computed |
| mesh[6].qualifier_ui | |
| mesh[6].descriptor_ui | D000792 |
| mesh[6].is_major_topic | False |
| mesh[6].qualifier_name | |
| mesh[6].descriptor_name | Angiography |
| mesh[7].qualifier_ui | |
| mesh[7].descriptor_ui | D000077321 |
| mesh[7].is_major_topic | True |
| mesh[7].qualifier_name | |
| mesh[7].descriptor_name | Deep Learning |
| mesh[8].qualifier_ui | |
| mesh[8].descriptor_ui | D006801 |
| mesh[8].is_major_topic | False |
| mesh[8].qualifier_name | |
| mesh[8].descriptor_name | Humans |
| mesh[9].qualifier_ui | Q000000981 |
| mesh[9].descriptor_ui | D011655 |
| mesh[9].is_major_topic | True |
| mesh[9].qualifier_name | diagnostic imaging |
| mesh[9].descriptor_name | Pulmonary Embolism |
| mesh[10].qualifier_ui | |
| mesh[10].descriptor_ui | D012189 |
| mesh[10].is_major_topic | False |
| mesh[10].qualifier_name | |
| mesh[10].descriptor_name | Retrospective Studies |
| mesh[11].qualifier_ui | |
| mesh[11].descriptor_ui | D014057 |
| mesh[11].is_major_topic | False |
| mesh[11].qualifier_name | |
| mesh[11].descriptor_name | Tomography, X-Ray Computed |
| type | article |
| title | Automated detection of pulmonary embolism from CT-angiograms using deep learning |
| biblio.issue | 1 |
| biblio.volume | 22 |
| biblio.last_page | 43 |
| biblio.first_page | 43 |
| topics[0].id | https://openalex.org/T10285 |
| topics[0].field.id | https://openalex.org/fields/27 |
| topics[0].field.display_name | Medicine |
| topics[0].score | 0.9988999962806702 |
| topics[0].domain.id | https://openalex.org/domains/4 |
| topics[0].domain.display_name | Health Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/2724 |
| topics[0].subfield.display_name | Internal Medicine |
| topics[0].display_name | Venous Thromboembolism Diagnosis and Management |
| topics[1].id | https://openalex.org/T10227 |
| topics[1].field.id | https://openalex.org/fields/27 |
| topics[1].field.display_name | Medicine |
| topics[1].score | 0.9939000010490417 |
| topics[1].domain.id | https://openalex.org/domains/4 |
| topics[1].domain.display_name | Health Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/2713 |
| topics[1].subfield.display_name | Epidemiology |
| topics[1].display_name | Acute Ischemic Stroke Management |
| topics[2].id | https://openalex.org/T11738 |
| topics[2].field.id | https://openalex.org/fields/27 |
| topics[2].field.display_name | Medicine |
| topics[2].score | 0.9703999757766724 |
| topics[2].domain.id | https://openalex.org/domains/4 |
| topics[2].domain.display_name | Health Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/2706 |
| topics[2].subfield.display_name | Critical Care and Intensive Care Medicine |
| topics[2].display_name | Ultrasound in Clinical Applications |
| funders[0].id | https://openalex.org/F4320324406 |
| funders[0].ror | https://ror.org/048e7gn38 |
| funders[0].display_name | Paulon Säätiö |
| is_xpac | False |
| apc_list.value | 1690 |
| apc_list.currency | GBP |
| apc_list.value_usd | 2072 |
| apc_paid.value | 1690 |
| apc_paid.currency | GBP |
| apc_paid.value_usd | 2072 |
| concepts[0].id | https://openalex.org/C154945302 |
| concepts[0].level | 1 |
| concepts[0].score | 0.6998074650764465 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[0].display_name | Artificial intelligence |
| concepts[1].id | https://openalex.org/C108583219 |
| concepts[1].level | 2 |
| concepts[1].score | 0.6907534599304199 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q197536 |
| concepts[1].display_name | Deep learning |
| concepts[2].id | https://openalex.org/C81363708 |
| concepts[2].level | 2 |
| concepts[2].score | 0.6842669248580933 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q17084460 |
| concepts[2].display_name | Convolutional neural network |
| concepts[3].id | https://openalex.org/C58471807 |
| concepts[3].level | 2 |
| concepts[3].score | 0.6811137199401855 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q327120 |
| concepts[3].display_name | Receiver operating characteristic |
| concepts[4].id | https://openalex.org/C41008148 |
| concepts[4].level | 0 |
| concepts[4].score | 0.6460928320884705 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[4].display_name | Computer science |
| concepts[5].id | https://openalex.org/C2776265017 |
| concepts[5].level | 2 |
| concepts[5].score | 0.6127417683601379 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q220570 |
| concepts[5].display_name | Pulmonary embolism |
| concepts[6].id | https://openalex.org/C66905080 |
| concepts[6].level | 3 |
| concepts[6].score | 0.5427423119544983 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q17005494 |
| concepts[6].display_name | Binary classification |
| concepts[7].id | https://openalex.org/C21200559 |
| concepts[7].level | 2 |
| concepts[7].score | 0.530888020992279 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q7451068 |
| concepts[7].display_name | Sensitivity (control systems) |
| concepts[8].id | https://openalex.org/C50644808 |
| concepts[8].level | 2 |
| concepts[8].score | 0.520932137966156 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q192776 |
| concepts[8].display_name | Artificial neural network |
| concepts[9].id | https://openalex.org/C153180895 |
| concepts[9].level | 2 |
| concepts[9].score | 0.49571549892425537 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q7148389 |
| concepts[9].display_name | Pattern recognition (psychology) |
| concepts[10].id | https://openalex.org/C40993552 |
| concepts[10].level | 2 |
| concepts[10].score | 0.4443069398403168 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q514654 |
| concepts[10].display_name | Gold standard (test) |
| concepts[11].id | https://openalex.org/C126838900 |
| concepts[11].level | 1 |
| concepts[11].score | 0.3684840500354767 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q77604 |
| concepts[11].display_name | Radiology |
| concepts[12].id | https://openalex.org/C71924100 |
| concepts[12].level | 0 |
| concepts[12].score | 0.3040158748626709 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q11190 |
| concepts[12].display_name | Medicine |
| concepts[13].id | https://openalex.org/C119857082 |
| concepts[13].level | 1 |
| concepts[13].score | 0.26338842511177063 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[13].display_name | Machine learning |
| concepts[14].id | https://openalex.org/C12267149 |
| concepts[14].level | 2 |
| concepts[14].score | 0.2230222225189209 |
| concepts[14].wikidata | https://www.wikidata.org/wiki/Q282453 |
| concepts[14].display_name | Support vector machine |
| concepts[15].id | https://openalex.org/C141071460 |
| concepts[15].level | 1 |
| concepts[15].score | 0.0875883400440216 |
| concepts[15].wikidata | https://www.wikidata.org/wiki/Q40821 |
| concepts[15].display_name | Surgery |
| concepts[16].id | https://openalex.org/C127413603 |
| concepts[16].level | 0 |
| concepts[16].score | 0.0 |
| concepts[16].wikidata | https://www.wikidata.org/wiki/Q11023 |
| concepts[16].display_name | Engineering |
| concepts[17].id | https://openalex.org/C24326235 |
| concepts[17].level | 1 |
| concepts[17].score | 0.0 |
| concepts[17].wikidata | https://www.wikidata.org/wiki/Q126095 |
| concepts[17].display_name | Electronic engineering |
| keywords[0].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[0].score | 0.6998074650764465 |
| keywords[0].display_name | Artificial intelligence |
| keywords[1].id | https://openalex.org/keywords/deep-learning |
| keywords[1].score | 0.6907534599304199 |
| keywords[1].display_name | Deep learning |
| keywords[2].id | https://openalex.org/keywords/convolutional-neural-network |
| keywords[2].score | 0.6842669248580933 |
| keywords[2].display_name | Convolutional neural network |
| keywords[3].id | https://openalex.org/keywords/receiver-operating-characteristic |
| keywords[3].score | 0.6811137199401855 |
| keywords[3].display_name | Receiver operating characteristic |
| keywords[4].id | https://openalex.org/keywords/computer-science |
| keywords[4].score | 0.6460928320884705 |
| keywords[4].display_name | Computer science |
| keywords[5].id | https://openalex.org/keywords/pulmonary-embolism |
| keywords[5].score | 0.6127417683601379 |
| keywords[5].display_name | Pulmonary embolism |
| keywords[6].id | https://openalex.org/keywords/binary-classification |
| keywords[6].score | 0.5427423119544983 |
| keywords[6].display_name | Binary classification |
| keywords[7].id | https://openalex.org/keywords/sensitivity |
| keywords[7].score | 0.530888020992279 |
| keywords[7].display_name | Sensitivity (control systems) |
| keywords[8].id | https://openalex.org/keywords/artificial-neural-network |
| keywords[8].score | 0.520932137966156 |
| keywords[8].display_name | Artificial neural network |
| keywords[9].id | https://openalex.org/keywords/pattern-recognition |
| keywords[9].score | 0.49571549892425537 |
| keywords[9].display_name | Pattern recognition (psychology) |
| keywords[10].id | https://openalex.org/keywords/gold-standard |
| keywords[10].score | 0.4443069398403168 |
| keywords[10].display_name | Gold standard (test) |
| keywords[11].id | https://openalex.org/keywords/radiology |
| keywords[11].score | 0.3684840500354767 |
| keywords[11].display_name | Radiology |
| keywords[12].id | https://openalex.org/keywords/medicine |
| keywords[12].score | 0.3040158748626709 |
| keywords[12].display_name | Medicine |
| keywords[13].id | https://openalex.org/keywords/machine-learning |
| keywords[13].score | 0.26338842511177063 |
| keywords[13].display_name | Machine learning |
| keywords[14].id | https://openalex.org/keywords/support-vector-machine |
| keywords[14].score | 0.2230222225189209 |
| keywords[14].display_name | Support vector machine |
| keywords[15].id | https://openalex.org/keywords/surgery |
| keywords[15].score | 0.0875883400440216 |
| keywords[15].display_name | Surgery |
| language | en |
| locations[0].id | doi:10.1186/s12880-022-00763-z |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S6505649 |
| locations[0].source.issn | 1471-2342 |
| locations[0].source.type | journal |
| locations[0].source.is_oa | True |
| locations[0].source.issn_l | 1471-2342 |
| locations[0].source.is_core | True |
| locations[0].source.is_in_doaj | True |
| locations[0].source.display_name | BMC Medical Imaging |
| locations[0].source.host_organization | https://openalex.org/P4310320256 |
| locations[0].source.host_organization_name | BioMed Central |
| locations[0].source.host_organization_lineage | https://openalex.org/P4310320256, https://openalex.org/P4310319965 |
| locations[0].source.host_organization_lineage_names | BioMed Central, Springer Nature |
| locations[0].license | cc-by |
| locations[0].pdf_url | https://bmcmedimaging.biomedcentral.com/track/pdf/10.1186/s12880-022-00763-z |
| locations[0].version | publishedVersion |
| locations[0].raw_type | journal-article |
| locations[0].license_id | https://openalex.org/licenses/cc-by |
| locations[0].is_accepted | True |
| locations[0].is_published | True |
| locations[0].raw_source_name | BMC Medical Imaging |
| locations[0].landing_page_url | https://doi.org/10.1186/s12880-022-00763-z |
| locations[1].id | pmid:35282821 |
| locations[1].is_oa | False |
| locations[1].source.id | https://openalex.org/S4306525036 |
| locations[1].source.issn | |
| locations[1].source.type | repository |
| locations[1].source.is_oa | False |
| locations[1].source.issn_l | |
| locations[1].source.is_core | False |
| locations[1].source.is_in_doaj | False |
| locations[1].source.display_name | PubMed |
| locations[1].source.host_organization | https://openalex.org/I1299303238 |
| locations[1].source.host_organization_name | National Institutes of Health |
| locations[1].source.host_organization_lineage | https://openalex.org/I1299303238 |
| locations[1].license | |
| locations[1].pdf_url | |
| locations[1].version | publishedVersion |
| locations[1].raw_type | |
| locations[1].license_id | |
| locations[1].is_accepted | True |
| locations[1].is_published | True |
| locations[1].raw_source_name | BMC medical imaging |
| locations[1].landing_page_url | https://pubmed.ncbi.nlm.nih.gov/35282821 |
| locations[2].id | pmh:oai:doaj.org/article:90c0bbe7b23c47a8932152d093a3790b |
| locations[2].is_oa | True |
| locations[2].source.id | https://openalex.org/S4306401280 |
| locations[2].source.issn | |
| locations[2].source.type | repository |
| locations[2].source.is_oa | False |
| locations[2].source.issn_l | |
| locations[2].source.is_core | False |
| locations[2].source.is_in_doaj | False |
| locations[2].source.display_name | DOAJ (DOAJ: Directory of Open Access Journals) |
| locations[2].source.host_organization | |
| locations[2].source.host_organization_name | |
| locations[2].license | cc-by-sa |
| locations[2].pdf_url | |
| locations[2].version | submittedVersion |
| locations[2].raw_type | article |
| locations[2].license_id | https://openalex.org/licenses/cc-by-sa |
| locations[2].is_accepted | False |
| locations[2].is_published | False |
| locations[2].raw_source_name | BMC Medical Imaging, Vol 22, Iss 1, Pp 1-10 (2022) |
| locations[2].landing_page_url | https://doaj.org/article/90c0bbe7b23c47a8932152d093a3790b |
| locations[3].id | pmh:oai:pubmedcentral.nih.gov:8919639 |
| locations[3].is_oa | True |
| locations[3].source.id | https://openalex.org/S2764455111 |
| locations[3].source.issn | |
| locations[3].source.type | repository |
| locations[3].source.is_oa | False |
| locations[3].source.issn_l | |
| locations[3].source.is_core | False |
| locations[3].source.is_in_doaj | False |
| locations[3].source.display_name | PubMed Central |
| locations[3].source.host_organization | https://openalex.org/I1299303238 |
| locations[3].source.host_organization_name | National Institutes of Health |
| locations[3].source.host_organization_lineage | https://openalex.org/I1299303238 |
| locations[3].license | other-oa |
| locations[3].pdf_url | |
| locations[3].version | submittedVersion |
| locations[3].raw_type | Text |
| locations[3].license_id | https://openalex.org/licenses/other-oa |
| locations[3].is_accepted | False |
| locations[3].is_published | False |
| locations[3].raw_source_name | BMC Med Imaging |
| locations[3].landing_page_url | https://www.ncbi.nlm.nih.gov/pmc/articles/8919639 |
| locations[4].id | pmh:oai:www.utupub.fi:10024/166723 |
| locations[4].is_oa | False |
| locations[4].source.id | https://openalex.org/S4306402470 |
| locations[4].source.issn | |
| locations[4].source.type | repository |
| locations[4].source.is_oa | False |
| locations[4].source.issn_l | |
| locations[4].source.is_core | False |
| locations[4].source.is_in_doaj | False |
| locations[4].source.display_name | UTUPub (University of Turku) |
| locations[4].source.host_organization | https://openalex.org/I155660961 |
| locations[4].source.host_organization_name | University of Turku |
| locations[4].source.host_organization_lineage | https://openalex.org/I155660961 |
| locations[4].license | |
| locations[4].pdf_url | |
| locations[4].version | submittedVersion |
| locations[4].raw_type | |
| locations[4].license_id | |
| locations[4].is_accepted | False |
| locations[4].is_published | False |
| locations[4].raw_source_name | |
| locations[4].landing_page_url | https://www.utupub.fi/handle/10024/166723 |
| indexed_in | crossref, doaj, pubmed |
| authorships[0].author.id | https://openalex.org/A5083483100 |
| authorships[0].author.orcid | https://orcid.org/0000-0002-1581-1709 |
| authorships[0].author.display_name | Heidi Huhtanen |
| authorships[0].countries | FI |
| authorships[0].affiliations[0].institution_ids | https://openalex.org/I155660961, https://openalex.org/I2801970007 |
| authorships[0].affiliations[0].raw_affiliation_string | Department of Radiology, University of Turku and Turku University Hospital, Turku, Finland |
| authorships[0].institutions[0].id | https://openalex.org/I2801970007 |
| authorships[0].institutions[0].ror | https://ror.org/05dbzj528 |
| authorships[0].institutions[0].type | healthcare |
| authorships[0].institutions[0].lineage | https://openalex.org/I2801970007, https://openalex.org/I4210127022 |
| authorships[0].institutions[0].country_code | FI |
| authorships[0].institutions[0].display_name | Turku University Hospital |
| authorships[0].institutions[1].id | https://openalex.org/I155660961 |
| authorships[0].institutions[1].ror | https://ror.org/05vghhr25 |
| authorships[0].institutions[1].type | education |
| authorships[0].institutions[1].lineage | https://openalex.org/I155660961 |
| authorships[0].institutions[1].country_code | FI |
| authorships[0].institutions[1].display_name | University of Turku |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Heidi Huhtanen |
| authorships[0].is_corresponding | True |
| authorships[0].raw_affiliation_strings | Department of Radiology, University of Turku and Turku University Hospital, Turku, Finland |
| authorships[1].author.id | https://openalex.org/A5037100393 |
| authorships[1].author.orcid | https://orcid.org/0000-0002-2104-6302 |
| authorships[1].author.display_name | Mikko Nyman |
| authorships[1].countries | FI |
| authorships[1].affiliations[0].institution_ids | https://openalex.org/I155660961, https://openalex.org/I2801970007 |
| authorships[1].affiliations[0].raw_affiliation_string | Department of Radiology, University of Turku and Turku University Hospital, Turku, Finland |
| authorships[1].institutions[0].id | https://openalex.org/I2801970007 |
| authorships[1].institutions[0].ror | https://ror.org/05dbzj528 |
| authorships[1].institutions[0].type | healthcare |
| authorships[1].institutions[0].lineage | https://openalex.org/I2801970007, https://openalex.org/I4210127022 |
| authorships[1].institutions[0].country_code | FI |
| authorships[1].institutions[0].display_name | Turku University Hospital |
| authorships[1].institutions[1].id | https://openalex.org/I155660961 |
| authorships[1].institutions[1].ror | https://ror.org/05vghhr25 |
| authorships[1].institutions[1].type | education |
| authorships[1].institutions[1].lineage | https://openalex.org/I155660961 |
| authorships[1].institutions[1].country_code | FI |
| authorships[1].institutions[1].display_name | University of Turku |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Mikko Nyman |
| authorships[1].is_corresponding | False |
| authorships[1].raw_affiliation_strings | Department of Radiology, University of Turku and Turku University Hospital, Turku, Finland |
| authorships[2].author.id | https://openalex.org/A5108420805 |
| authorships[2].author.orcid | |
| authorships[2].author.display_name | Tarek Mohsen |
| authorships[2].affiliations[0].raw_affiliation_string | Reaktor Innovations Oy, Helsinki, Finland |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Tarek Mohsen |
| authorships[2].is_corresponding | False |
| authorships[2].raw_affiliation_strings | Reaktor Innovations Oy, Helsinki, Finland |
| authorships[3].author.id | https://openalex.org/A5002022503 |
| authorships[3].author.orcid | |
| authorships[3].author.display_name | Arho Virkki |
| authorships[3].countries | FI |
| authorships[3].affiliations[0].institution_ids | https://openalex.org/I2801970007 |
| authorships[3].affiliations[0].raw_affiliation_string | Auria Clinical Informatics, Turku University Hospital, Turku, Finland |
| authorships[3].institutions[0].id | https://openalex.org/I2801970007 |
| authorships[3].institutions[0].ror | https://ror.org/05dbzj528 |
| authorships[3].institutions[0].type | healthcare |
| authorships[3].institutions[0].lineage | https://openalex.org/I2801970007, https://openalex.org/I4210127022 |
| authorships[3].institutions[0].country_code | FI |
| authorships[3].institutions[0].display_name | Turku University Hospital |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Arho Virkki |
| authorships[3].is_corresponding | False |
| authorships[3].raw_affiliation_strings | Auria Clinical Informatics, Turku University Hospital, Turku, Finland |
| authorships[4].author.id | https://openalex.org/A5031740781 |
| authorships[4].author.orcid | https://orcid.org/0000-0003-1556-3351 |
| authorships[4].author.display_name | Antti Karlsson |
| authorships[4].countries | FI |
| authorships[4].affiliations[0].institution_ids | https://openalex.org/I155660961, https://openalex.org/I2801970007 |
| authorships[4].affiliations[0].raw_affiliation_string | Auria Biobank, Turku University Hospital, University of Turku, Turku, Finland |
| authorships[4].institutions[0].id | https://openalex.org/I2801970007 |
| authorships[4].institutions[0].ror | https://ror.org/05dbzj528 |
| authorships[4].institutions[0].type | healthcare |
| authorships[4].institutions[0].lineage | https://openalex.org/I2801970007, https://openalex.org/I4210127022 |
| authorships[4].institutions[0].country_code | FI |
| authorships[4].institutions[0].display_name | Turku University Hospital |
| authorships[4].institutions[1].id | https://openalex.org/I155660961 |
| authorships[4].institutions[1].ror | https://ror.org/05vghhr25 |
| authorships[4].institutions[1].type | education |
| authorships[4].institutions[1].lineage | https://openalex.org/I155660961 |
| authorships[4].institutions[1].country_code | FI |
| authorships[4].institutions[1].display_name | University of Turku |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Antti Karlsson |
| authorships[4].is_corresponding | False |
| authorships[4].raw_affiliation_strings | Auria Biobank, Turku University Hospital, University of Turku, Turku, Finland |
| authorships[5].author.id | https://openalex.org/A5040900470 |
| authorships[5].author.orcid | https://orcid.org/0000-0002-0368-3746 |
| authorships[5].author.display_name | Jussi Hirvonen |
| authorships[5].countries | FI |
| authorships[5].affiliations[0].institution_ids | https://openalex.org/I155660961, https://openalex.org/I2801970007 |
| authorships[5].affiliations[0].raw_affiliation_string | Department of Radiology, University of Turku and Turku University Hospital, Turku, Finland |
| authorships[5].institutions[0].id | https://openalex.org/I2801970007 |
| authorships[5].institutions[0].ror | https://ror.org/05dbzj528 |
| authorships[5].institutions[0].type | healthcare |
| authorships[5].institutions[0].lineage | https://openalex.org/I2801970007, https://openalex.org/I4210127022 |
| authorships[5].institutions[0].country_code | FI |
| authorships[5].institutions[0].display_name | Turku University Hospital |
| authorships[5].institutions[1].id | https://openalex.org/I155660961 |
| authorships[5].institutions[1].ror | https://ror.org/05vghhr25 |
| authorships[5].institutions[1].type | education |
| authorships[5].institutions[1].lineage | https://openalex.org/I155660961 |
| authorships[5].institutions[1].country_code | FI |
| authorships[5].institutions[1].display_name | University of Turku |
| authorships[5].author_position | last |
| authorships[5].raw_author_name | Jussi Hirvonen |
| authorships[5].is_corresponding | False |
| authorships[5].raw_affiliation_strings | Department of Radiology, University of Turku and Turku University Hospital, Turku, Finland |
| has_content.pdf | True |
| has_content.grobid_xml | True |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://bmcmedimaging.biomedcentral.com/track/pdf/10.1186/s12880-022-00763-z |
| open_access.oa_status | gold |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Automated detection of pulmonary embolism from CT-angiograms using deep learning |
| has_fulltext | True |
| is_retracted | False |
| updated_date | 2025-11-06T03:46:38.306776 |
| primary_topic.id | https://openalex.org/T10285 |
| primary_topic.field.id | https://openalex.org/fields/27 |
| primary_topic.field.display_name | Medicine |
| primary_topic.score | 0.9988999962806702 |
| primary_topic.domain.id | https://openalex.org/domains/4 |
| primary_topic.domain.display_name | Health Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/2724 |
| primary_topic.subfield.display_name | Internal Medicine |
| primary_topic.display_name | Venous Thromboembolism Diagnosis and Management |
| related_works | https://openalex.org/W4385649027, https://openalex.org/W2050560466, https://openalex.org/W2940055329, https://openalex.org/W4287760213, https://openalex.org/W3034642336, https://openalex.org/W3216067289, https://openalex.org/W3202613528, https://openalex.org/W3179518614, https://openalex.org/W4200065130, https://openalex.org/W4388115992 |
| cited_by_count | 73 |
| counts_by_year[0].year | 2025 |
| counts_by_year[0].cited_by_count | 30 |
| counts_by_year[1].year | 2024 |
| counts_by_year[1].cited_by_count | 21 |
| counts_by_year[2].year | 2023 |
| counts_by_year[2].cited_by_count | 15 |
| counts_by_year[3].year | 2022 |
| counts_by_year[3].cited_by_count | 7 |
| locations_count | 5 |
| best_oa_location.id | doi:10.1186/s12880-022-00763-z |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S6505649 |
| best_oa_location.source.issn | 1471-2342 |
| best_oa_location.source.type | journal |
| best_oa_location.source.is_oa | True |
| best_oa_location.source.issn_l | 1471-2342 |
| best_oa_location.source.is_core | True |
| best_oa_location.source.is_in_doaj | True |
| best_oa_location.source.display_name | BMC Medical Imaging |
| best_oa_location.source.host_organization | https://openalex.org/P4310320256 |
| best_oa_location.source.host_organization_name | BioMed Central |
| best_oa_location.source.host_organization_lineage | https://openalex.org/P4310320256, https://openalex.org/P4310319965 |
| best_oa_location.source.host_organization_lineage_names | BioMed Central, Springer Nature |
| best_oa_location.license | cc-by |
| best_oa_location.pdf_url | https://bmcmedimaging.biomedcentral.com/track/pdf/10.1186/s12880-022-00763-z |
| best_oa_location.version | publishedVersion |
| best_oa_location.raw_type | journal-article |
| best_oa_location.license_id | https://openalex.org/licenses/cc-by |
| best_oa_location.is_accepted | True |
| best_oa_location.is_published | True |
| best_oa_location.raw_source_name | BMC Medical Imaging |
| best_oa_location.landing_page_url | https://doi.org/10.1186/s12880-022-00763-z |
| primary_location.id | doi:10.1186/s12880-022-00763-z |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S6505649 |
| primary_location.source.issn | 1471-2342 |
| primary_location.source.type | journal |
| primary_location.source.is_oa | True |
| primary_location.source.issn_l | 1471-2342 |
| primary_location.source.is_core | True |
| primary_location.source.is_in_doaj | True |
| primary_location.source.display_name | BMC Medical Imaging |
| primary_location.source.host_organization | https://openalex.org/P4310320256 |
| primary_location.source.host_organization_name | BioMed Central |
| primary_location.source.host_organization_lineage | https://openalex.org/P4310320256, https://openalex.org/P4310319965 |
| primary_location.source.host_organization_lineage_names | BioMed Central, Springer Nature |
| primary_location.license | cc-by |
| primary_location.pdf_url | https://bmcmedimaging.biomedcentral.com/track/pdf/10.1186/s12880-022-00763-z |
| primary_location.version | publishedVersion |
| primary_location.raw_type | journal-article |
| primary_location.license_id | https://openalex.org/licenses/cc-by |
| primary_location.is_accepted | True |
| primary_location.is_published | True |
| primary_location.raw_source_name | BMC Medical Imaging |
| primary_location.landing_page_url | https://doi.org/10.1186/s12880-022-00763-z |
| publication_date | 2022-03-14 |
| publication_year | 2022 |
| referenced_works | https://openalex.org/W2043306284, https://openalex.org/W2624824520, https://openalex.org/W4297171911, https://openalex.org/W2466838272, https://openalex.org/W2563505833, https://openalex.org/W1980386605, https://openalex.org/W1994097052, https://openalex.org/W2560783415, https://openalex.org/W2558751017, https://openalex.org/W2165839911, https://openalex.org/W2180328040, https://openalex.org/W2784963350, https://openalex.org/W2767236661, https://openalex.org/W2019575515, https://openalex.org/W2135554434, https://openalex.org/W2167896953, https://openalex.org/W2512902140, https://openalex.org/W2020816258, https://openalex.org/W2954494473, https://openalex.org/W3123661268, https://openalex.org/W134759298, https://openalex.org/W3039113409, https://openalex.org/W3144842570, https://openalex.org/W3135096391, https://openalex.org/W2977403677, https://openalex.org/W3018185338, https://openalex.org/W2982587597, https://openalex.org/W3127694486, https://openalex.org/W3045459094, https://openalex.org/W2964350391, https://openalex.org/W2328176404, https://openalex.org/W2020018978, https://openalex.org/W3112990870, https://openalex.org/W2891492187, https://openalex.org/W2966744887, https://openalex.org/W6739651123, https://openalex.org/W3040814749, https://openalex.org/W2730853592, https://openalex.org/W3157328277, https://openalex.org/W2990519034 |
| referenced_works_count | 40 |
| abstract_inverted_index.= | 197 |
| abstract_inverted_index.A | 162 |
| abstract_inverted_index.B | 174 |
| abstract_inverted_index.a | 12, 40, 49, 58, 203, 209 |
| abstract_inverted_index.p | 196 |
| abstract_inverted_index.A) | 84 |
| abstract_inverted_index.B) | 89 |
| abstract_inverted_index.On | 157 |
| abstract_inverted_index.PE | 222 |
| abstract_inverted_index.V2 | 56 |
| abstract_inverted_index.We | 38, 93, 200 |
| abstract_inverted_index.as | 68, 90, 138, 140 |
| abstract_inverted_index.in | 17, 100, 109, 220 |
| abstract_inverted_index.of | 4, 21, 46, 70, 74, 125, 167 |
| abstract_inverted_index.on | 118, 151 |
| abstract_inverted_index.or | 85 |
| abstract_inverted_index.to | 8, 63, 98, 107 |
| abstract_inverted_index.vs | 194 |
| abstract_inverted_index.200 | 105 |
| abstract_inverted_index.600 | 96 |
| abstract_inverted_index.AUC | 187 |
| abstract_inverted_index.ROC | 131, 186 |
| abstract_inverted_index.The | 2 |
| abstract_inverted_index.Two | 72 |
| abstract_inverted_index.aim | 3 |
| abstract_inverted_index.and | 10, 57, 102, 104, 121, 132, 142, 154, 165, 169, 178 |
| abstract_inverted_index.can | 215 |
| abstract_inverted_index.not | 190 |
| abstract_inverted_index.the | 18, 75, 126, 158, 182 |
| abstract_inverted_index.two | 47 |
| abstract_inverted_index.use | 99, 108 |
| abstract_inverted_index.was | 7, 128, 189 |
| abstract_inverted_index.(PE) | 24 |
| abstract_inverted_index.Both | 147 |
| abstract_inverted_index.CTPA | 66 |
| abstract_inverted_index.both | 119, 152 |
| abstract_inverted_index.deep | 13, 41, 204 |
| abstract_inverted_index.from | 25, 223 |
| abstract_inverted_index.only | 32, 114 |
| abstract_inverted_index.show | 201 |
| abstract_inverted_index.term | 60 |
| abstract_inverted_index.that | 202 |
| abstract_inverted_index.this | 5 |
| abstract_inverted_index.well | 139, 150 |
| abstract_inverted_index.were | 77, 112 |
| abstract_inverted_index.with | 115, 130, 208 |
| abstract_inverted_index.(0.94 | 193 |
| abstract_inverted_index.0.91, | 195 |
| abstract_inverted_index.90.7% | 177 |
| abstract_inverted_index.93.5% | 168 |
| abstract_inverted_index.CTPAs | 97, 106, 111 |
| abstract_inverted_index.Model | 161, 173 |
| abstract_inverted_index.chest | 81 |
| abstract_inverted_index.data. | 36, 92 |
| abstract_inverted_index.model | 16, 44, 76, 206 |
| abstract_inverted_index.study | 6 |
| abstract_inverted_index.their | 185 |
| abstract_inverted_index.using | 31, 79 |
| abstract_inverted_index.whole | 65 |
| abstract_inverted_index.(Model | 83, 88 |
| abstract_inverted_index.0.07). | 198 |
| abstract_inverted_index.86.6%, | 170 |
| abstract_inverted_index.CTPAs. | 224 |
| abstract_inverted_index.X-rays | 82 |
| abstract_inverted_index.binary | 116 |
| abstract_inverted_index.called | 54 |
| abstract_inverted_index.either | 80 |
| abstract_inverted_index.images | 87 |
| abstract_inverted_index.labels | 117 |
| abstract_inverted_index.level, | 160 |
| abstract_inverted_index.memory | 61 |
| abstract_inverted_index.models | 127, 148 |
| abstract_inverted_index.neural | 14, 42, 51 |
| abstract_inverted_index.parts: | 48 |
| abstract_inverted_index.scores | 188 |
| abstract_inverted_index.small, | 211 |
| abstract_inverted_index.stack- | 120, 153 |
| abstract_inverted_index.stacks | 67 |
| abstract_inverted_index.weakly | 33, 212 |
| abstract_inverted_index.(CTPAs) | 30 |
| abstract_inverted_index.83.5%). | 180 |
| abstract_inverted_index.Methods | 37 |
| abstract_inverted_index.Results | 146 |
| abstract_inverted_index.achieve | 216 |
| abstract_inverted_index.between | 184 |
| abstract_inverted_index.created | 78 |
| abstract_inverted_index.curves, | 134 |
| abstract_inverted_index.dataset | 214 |
| abstract_inverted_index.develop | 9 |
| abstract_inverted_index.levels. | 123, 156 |
| abstract_inverted_index.natural | 86 |
| abstract_inverted_index.network | 15, 43, 52, 62 |
| abstract_inverted_index.process | 64 |
| abstract_inverted_index.reached | 163 |
| abstract_inverted_index.results | 219 |
| abstract_inverted_index.slices. | 71 |
| abstract_inverted_index.trained | 207 |
| abstract_inverted_index.values. | 145 |
| abstract_inverted_index.Abstract | 0 |
| abstract_inverted_index.However, | 181 |
| abstract_inverted_index.computed | 26 |
| abstract_inverted_index.embolism | 23 |
| abstract_inverted_index.evaluate | 11 |
| abstract_inverted_index.labelled | 34 |
| abstract_inverted_index.learning | 205 |
| abstract_inverted_index.negative | 143 |
| abstract_inverted_index.positive | 141 |
| abstract_inverted_index.slightly | 175 |
| abstract_inverted_index.testing. | 110 |
| abstract_inverted_index.training | 35, 101 |
| abstract_inverted_index.versions | 73 |
| abstract_inverted_index.accuracy, | 137 |
| abstract_inverted_index.annotated | 113, 213 |
| abstract_inverted_index.automated | 19 |
| abstract_inverted_index.collected | 95 |
| abstract_inverted_index.detecting | 221 |
| abstract_inverted_index.detection | 20 |
| abstract_inverted_index.developed | 39 |
| abstract_inverted_index.evaluated | 129 |
| abstract_inverted_index.excellent | 217 |
| abstract_inverted_index.performed | 149 |
| abstract_inverted_index.pulmonary | 22, 28 |
| abstract_inverted_index.sequences | 69 |
| abstract_inverted_index.Background | 1 |
| abstract_inverted_index.angiograms | 29 |
| abstract_inverted_index.consisting | 45 |
| abstract_inverted_index.difference | 183 |
| abstract_inverted_index.long-short | 59 |
| abstract_inverted_index.predictive | 144 |
| abstract_inverted_index.relatively | 210 |
| abstract_inverted_index.tomography | 27 |
| abstract_inverted_index.validation | 103 |
| abstract_inverted_index.Conclusions | 199 |
| abstract_inverted_index.Performance | 124 |
| abstract_inverted_index.performance | 218 |
| abstract_inverted_index.sensitivity | 166, 179 |
| abstract_inverted_index.significant | 192 |
| abstract_inverted_index.slice-based | 122, 155 |
| abstract_inverted_index.specificity | 164 |
| abstract_inverted_index.stack-based | 159 |
| abstract_inverted_index.(specificity | 176 |
| abstract_inverted_index.architecture | 53 |
| abstract_inverted_index.pre-training | 91 |
| abstract_inverted_index.sensitivity, | 136 |
| abstract_inverted_index.specificity, | 135 |
| abstract_inverted_index.convolutional | 50 |
| abstract_inverted_index.outperforming | 172 |
| abstract_inverted_index.respectively, | 171 |
| abstract_inverted_index.statistically | 191 |
| abstract_inverted_index.InceptionResNet | 55 |
| abstract_inverted_index.retrospectively | 94 |
| abstract_inverted_index.precision–recall | 133 |
| cited_by_percentile_year.max | 100 |
| cited_by_percentile_year.min | 98 |
| corresponding_author_ids | https://openalex.org/A5083483100 |
| countries_distinct_count | 1 |
| institutions_distinct_count | 6 |
| corresponding_institution_ids | https://openalex.org/I155660961, https://openalex.org/I2801970007 |
| citation_normalized_percentile.value | 0.99494477 |
| citation_normalized_percentile.is_in_top_1_percent | True |
| citation_normalized_percentile.is_in_top_10_percent | True |