Artificial intelligence for prostate MRI: open datasets, available applications, and grand challenges
Abstract Artificial intelligence (AI) for prostate magnetic resonance imaging (MRI) is starting to play a clinical role for prostate cancer (PCa) patients. AI-assisted reading is feasible, allowing workflow reduction. A total of 3,369 multi-vendor prostate MRI cases are available in open datasets, a...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2022-08-01
|
| Series: | European Radiology Experimental |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s41747-022-00288-8 |
| _version_ | 1818505231583936512 |
|---|---|
| author | Mohammed R. S. Sunoqrot Anindo Saha Matin Hosseinzadeh Mattijs Elschot Henkjan Huisman |
| author_facet | Mohammed R. S. Sunoqrot Anindo Saha Matin Hosseinzadeh Mattijs Elschot Henkjan Huisman |
| author_sort | Mohammed R. S. Sunoqrot |
| collection | DOAJ |
| description | Abstract Artificial intelligence (AI) for prostate magnetic resonance imaging (MRI) is starting to play a clinical role for prostate cancer (PCa) patients. AI-assisted reading is feasible, allowing workflow reduction. A total of 3,369 multi-vendor prostate MRI cases are available in open datasets, acquired from 2003 to 2021 in Europe or USA at 3 T (n = 3,018; 89.6%) or 1.5 T (n = 296; 8.8%), 346 cases scanned with endorectal coil (10.3%), 3,023 (89.7%) with phased-array surface coils; 412 collected for anatomical segmentation tasks, 3,096 for PCa detection/classification; for 2,240 cases lesions delineation is available and 56 cases have matching histopathologic images; for 2,620 cases the PSA level is provided; the total size of all open datasets amounts to approximately 253 GB. Of note, quality of annotations provided per dataset highly differ and attention must be paid when using these datasets (e.g., data overlap). Seven grand challenges and commercial applications from eleven vendors are here considered. Few small studies provided prospective validation. More work is needed, in particular validation on large-scale multi-institutional, well-curated public datasets to test general applicability. Moreover, AI needs to be explored for clinical stages other than detection/characterization (e.g., follow-up, prognosis, interventions, and focal treatment). |
| first_indexed | 2024-12-10T21:47:53Z |
| format | Article |
| id | doaj.art-d1ac11e9eaaf428cb9635a8d6095d340 |
| institution | Directory Open Access Journal |
| issn | 2509-9280 |
| language | English |
| last_indexed | 2024-12-10T21:47:53Z |
| publishDate | 2022-08-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | European Radiology Experimental |
| spelling | doaj.art-d1ac11e9eaaf428cb9635a8d6095d3402022-12-22T01:32:19ZengSpringerOpenEuropean Radiology Experimental2509-92802022-08-016111310.1186/s41747-022-00288-8Artificial intelligence for prostate MRI: open datasets, available applications, and grand challengesMohammed R. S. Sunoqrot0Anindo Saha1Matin Hosseinzadeh2Mattijs Elschot3Henkjan Huisman4Department of Circulation and Medical Imaging, NTNU–Norwegian University of Science and TechnologyDiagnostic Image Analysis Group, Department of Medical Imaging, Radboud University Medical CenterDiagnostic Image Analysis Group, Department of Medical Imaging, Radboud University Medical CenterDepartment of Circulation and Medical Imaging, NTNU–Norwegian University of Science and TechnologyDepartment of Circulation and Medical Imaging, NTNU–Norwegian University of Science and TechnologyAbstract Artificial intelligence (AI) for prostate magnetic resonance imaging (MRI) is starting to play a clinical role for prostate cancer (PCa) patients. AI-assisted reading is feasible, allowing workflow reduction. A total of 3,369 multi-vendor prostate MRI cases are available in open datasets, acquired from 2003 to 2021 in Europe or USA at 3 T (n = 3,018; 89.6%) or 1.5 T (n = 296; 8.8%), 346 cases scanned with endorectal coil (10.3%), 3,023 (89.7%) with phased-array surface coils; 412 collected for anatomical segmentation tasks, 3,096 for PCa detection/classification; for 2,240 cases lesions delineation is available and 56 cases have matching histopathologic images; for 2,620 cases the PSA level is provided; the total size of all open datasets amounts to approximately 253 GB. Of note, quality of annotations provided per dataset highly differ and attention must be paid when using these datasets (e.g., data overlap). Seven grand challenges and commercial applications from eleven vendors are here considered. Few small studies provided prospective validation. More work is needed, in particular validation on large-scale multi-institutional, well-curated public datasets to test general applicability. Moreover, AI needs to be explored for clinical stages other than detection/characterization (e.g., follow-up, prognosis, interventions, and focal treatment).https://doi.org/10.1186/s41747-022-00288-8Artificial intelligenceDeep learningImage processing (computer-assisted)Multiparametric magnetic resonance imagingProstatic neoplasms |
| spellingShingle | Mohammed R. S. Sunoqrot Anindo Saha Matin Hosseinzadeh Mattijs Elschot Henkjan Huisman Artificial intelligence for prostate MRI: open datasets, available applications, and grand challenges European Radiology Experimental Artificial intelligence Deep learning Image processing (computer-assisted) Multiparametric magnetic resonance imaging Prostatic neoplasms |
| title | Artificial intelligence for prostate MRI: open datasets, available applications, and grand challenges |
| title_full | Artificial intelligence for prostate MRI: open datasets, available applications, and grand challenges |
| title_fullStr | Artificial intelligence for prostate MRI: open datasets, available applications, and grand challenges |
| title_full_unstemmed | Artificial intelligence for prostate MRI: open datasets, available applications, and grand challenges |
| title_short | Artificial intelligence for prostate MRI: open datasets, available applications, and grand challenges |
| title_sort | artificial intelligence for prostate mri open datasets available applications and grand challenges |
| topic | Artificial intelligence Deep learning Image processing (computer-assisted) Multiparametric magnetic resonance imaging Prostatic neoplasms |
| url | https://doi.org/10.1186/s41747-022-00288-8 |
| work_keys_str_mv | AT mohammedrssunoqrot artificialintelligenceforprostatemriopendatasetsavailableapplicationsandgrandchallenges AT anindosaha artificialintelligenceforprostatemriopendatasetsavailableapplicationsandgrandchallenges AT matinhosseinzadeh artificialintelligenceforprostatemriopendatasetsavailableapplicationsandgrandchallenges AT mattijselschot artificialintelligenceforprostatemriopendatasetsavailableapplicationsandgrandchallenges AT henkjanhuisman artificialintelligenceforprostatemriopendatasetsavailableapplicationsandgrandchallenges |