Enrichment of lung cancer computed tomography collections with AI-derived annotations
Abstract Public imaging datasets are critical for the development and evaluation of automated tools in cancer imaging. Unfortunately, many do not include annotations or image-derived features, complicating downstream analysis. Artificial intelligence-based annotation tools have been shown to achieve...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2024-01-01
|
| Series: | Scientific Data |
| Online Access: | https://doi.org/10.1038/s41597-023-02864-y |
| _version_ | 1827388834754592768 |
|---|---|
| author | Deepa Krishnaswamy Dennis Bontempi Vamsi Krishna Thiriveedhi Davide Punzo David Clunie Christopher P. Bridge Hugo J. W. L. Aerts Ron Kikinis Andrey Fedorov |
| author_facet | Deepa Krishnaswamy Dennis Bontempi Vamsi Krishna Thiriveedhi Davide Punzo David Clunie Christopher P. Bridge Hugo J. W. L. Aerts Ron Kikinis Andrey Fedorov |
| author_sort | Deepa Krishnaswamy |
| collection | DOAJ |
| description | Abstract Public imaging datasets are critical for the development and evaluation of automated tools in cancer imaging. Unfortunately, many do not include annotations or image-derived features, complicating downstream analysis. Artificial intelligence-based annotation tools have been shown to achieve acceptable performance and can be used to automatically annotate large datasets. As part of the effort to enrich public data available within NCI Imaging Data Commons (IDC), here we introduce AI-generated annotations for two collections containing computed tomography images of the chest, NSCLC-Radiomics, and a subset of the National Lung Screening Trial. Using publicly available AI algorithms, we derived volumetric annotations of thoracic organs-at-risk, their corresponding radiomics features, and slice-level annotations of anatomical landmarks and regions. The resulting annotations are publicly available within IDC, where the DICOM format is used to harmonize the data and achieve FAIR (Findable, Accessible, Interoperable, Reusable) data principles. The annotations are accompanied by cloud-enabled notebooks demonstrating their use. This study reinforces the need for large, publicly accessible curated datasets and demonstrates how AI can aid in cancer imaging. |
| first_indexed | 2024-03-08T16:24:45Z |
| format | Article |
| id | doaj.art-dcc71e61a06943b383830340b580a81d |
| institution | Directory Open Access Journal |
| issn | 2052-4463 |
| language | English |
| last_indexed | 2024-03-08T16:24:45Z |
| publishDate | 2024-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Data |
| spelling | doaj.art-dcc71e61a06943b383830340b580a81d2024-01-07T12:10:16ZengNature PortfolioScientific Data2052-44632024-01-0111111510.1038/s41597-023-02864-yEnrichment of lung cancer computed tomography collections with AI-derived annotationsDeepa Krishnaswamy0Dennis Bontempi1Vamsi Krishna Thiriveedhi2Davide Punzo3David Clunie4Christopher P. Bridge5Hugo J. W. L. Aerts6Ron Kikinis7Andrey Fedorov8Brigham and Women’s HospitalArtificial Intelligence in Medicine (AIM) Program, Mass General Brigham, Harvard Medical SchoolBrigham and Women’s HospitalRadical ImagingPixelMed PublishingDepartment of Radiology, Massachusetts General HospitalArtificial Intelligence in Medicine (AIM) Program, Mass General Brigham, Harvard Medical SchoolBrigham and Women’s HospitalBrigham and Women’s HospitalAbstract Public imaging datasets are critical for the development and evaluation of automated tools in cancer imaging. Unfortunately, many do not include annotations or image-derived features, complicating downstream analysis. Artificial intelligence-based annotation tools have been shown to achieve acceptable performance and can be used to automatically annotate large datasets. As part of the effort to enrich public data available within NCI Imaging Data Commons (IDC), here we introduce AI-generated annotations for two collections containing computed tomography images of the chest, NSCLC-Radiomics, and a subset of the National Lung Screening Trial. Using publicly available AI algorithms, we derived volumetric annotations of thoracic organs-at-risk, their corresponding radiomics features, and slice-level annotations of anatomical landmarks and regions. The resulting annotations are publicly available within IDC, where the DICOM format is used to harmonize the data and achieve FAIR (Findable, Accessible, Interoperable, Reusable) data principles. The annotations are accompanied by cloud-enabled notebooks demonstrating their use. This study reinforces the need for large, publicly accessible curated datasets and demonstrates how AI can aid in cancer imaging.https://doi.org/10.1038/s41597-023-02864-y |
| spellingShingle | Deepa Krishnaswamy Dennis Bontempi Vamsi Krishna Thiriveedhi Davide Punzo David Clunie Christopher P. Bridge Hugo J. W. L. Aerts Ron Kikinis Andrey Fedorov Enrichment of lung cancer computed tomography collections with AI-derived annotations Scientific Data |
| title | Enrichment of lung cancer computed tomography collections with AI-derived annotations |
| title_full | Enrichment of lung cancer computed tomography collections with AI-derived annotations |
| title_fullStr | Enrichment of lung cancer computed tomography collections with AI-derived annotations |
| title_full_unstemmed | Enrichment of lung cancer computed tomography collections with AI-derived annotations |
| title_short | Enrichment of lung cancer computed tomography collections with AI-derived annotations |
| title_sort | enrichment of lung cancer computed tomography collections with ai derived annotations |
| url | https://doi.org/10.1038/s41597-023-02864-y |
| work_keys_str_mv | AT deepakrishnaswamy enrichmentoflungcancercomputedtomographycollectionswithaiderivedannotations AT dennisbontempi enrichmentoflungcancercomputedtomographycollectionswithaiderivedannotations AT vamsikrishnathiriveedhi enrichmentoflungcancercomputedtomographycollectionswithaiderivedannotations AT davidepunzo enrichmentoflungcancercomputedtomographycollectionswithaiderivedannotations AT davidclunie enrichmentoflungcancercomputedtomographycollectionswithaiderivedannotations AT christopherpbridge enrichmentoflungcancercomputedtomographycollectionswithaiderivedannotations AT hugojwlaerts enrichmentoflungcancercomputedtomographycollectionswithaiderivedannotations AT ronkikinis enrichmentoflungcancercomputedtomographycollectionswithaiderivedannotations AT andreyfedorov enrichmentoflungcancercomputedtomographycollectionswithaiderivedannotations |