Artificial Intelligence Compared to Radiologists for the Initial Diagnosis of Prostate Cancer on Magnetic Resonance Imaging: A Systematic Review and Recommendations for Future Studies
Computer-aided diagnosis (CAD) of prostate cancer on multiparametric magnetic resonance imaging (mpMRI), using artificial intelligence (AI), may reduce missed cancers and unnecessary biopsies, increase inter-observer agreement between radiologists, and alleviate pressures caused by rising case incid...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-07-01
|
| Series: | Cancers |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-6694/13/13/3318 |
| _version_ | 1797528041169092608 |
|---|---|
| author | Tom Syer Pritesh Mehta Michela Antonelli Sue Mallett David Atkinson Sébastien Ourselin Shonit Punwani |
| author_facet | Tom Syer Pritesh Mehta Michela Antonelli Sue Mallett David Atkinson Sébastien Ourselin Shonit Punwani |
| author_sort | Tom Syer |
| collection | DOAJ |
| description | Computer-aided diagnosis (CAD) of prostate cancer on multiparametric magnetic resonance imaging (mpMRI), using artificial intelligence (AI), may reduce missed cancers and unnecessary biopsies, increase inter-observer agreement between radiologists, and alleviate pressures caused by rising case incidence and a shortage of specialist radiologists to read prostate mpMRI. However, well-designed evaluation studies are required to prove efficacy above current clinical practice. A systematic search of the MEDLINE, EMBASE, and arXiv electronic databases was conducted for studies that compared CAD for prostate cancer detection or classification on MRI against radiologist interpretation and a histopathological reference standard, in treatment-naïve men with a clinical suspicion of prostate cancer. Twenty-seven studies were included in the final analysis. Due to substantial heterogeneities in the included studies, a narrative synthesis is presented. Several studies reported superior diagnostic accuracy for CAD over radiologist interpretation on small, internal patient datasets, though this was not observed in the few studies that performed evaluation using external patient data. Our review found insufficient evidence to suggest the clinical deployment of artificial intelligence algorithms at present. Further work is needed to develop and enforce methodological standards, promote access to large diverse datasets, and conduct prospective evaluations before clinical adoption can be considered. |
| first_indexed | 2024-03-10T09:52:29Z |
| format | Article |
| id | doaj.art-0c033ff65d064b3ea4799d827b42b488 |
| institution | Directory Open Access Journal |
| issn | 2072-6694 |
| language | English |
| last_indexed | 2024-03-10T09:52:29Z |
| publishDate | 2021-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Cancers |
| spelling | doaj.art-0c033ff65d064b3ea4799d827b42b4882023-11-22T02:36:00ZengMDPI AGCancers2072-66942021-07-011313331810.3390/cancers13133318Artificial Intelligence Compared to Radiologists for the Initial Diagnosis of Prostate Cancer on Magnetic Resonance Imaging: A Systematic Review and Recommendations for Future StudiesTom Syer0Pritesh Mehta1Michela Antonelli2Sue Mallett3David Atkinson4Sébastien Ourselin5Shonit Punwani6Centre for Medical Imaging, Division of Medicine, Bloomsbury Campus, University College London, London WC1E 6DH, UKDepartment of Medical Physics and Biomedical Engineering, Faculty of Engineering Sciences, Bloomsbury Campus, University College London, London WC1E 6DH, UKSchool of Biomedical Engineering & Imaging Sciences, Faculty of Life Sciences and Medicine, St Thomas’ Campus, King’s College London, London SE1 7EH, UKCentre for Medical Imaging, Division of Medicine, Bloomsbury Campus, University College London, London WC1E 6DH, UKCentre for Medical Imaging, Division of Medicine, Bloomsbury Campus, University College London, London WC1E 6DH, UKSchool of Biomedical Engineering & Imaging Sciences, Faculty of Life Sciences and Medicine, St Thomas’ Campus, King’s College London, London SE1 7EH, UKCentre for Medical Imaging, Division of Medicine, Bloomsbury Campus, University College London, London WC1E 6DH, UKComputer-aided diagnosis (CAD) of prostate cancer on multiparametric magnetic resonance imaging (mpMRI), using artificial intelligence (AI), may reduce missed cancers and unnecessary biopsies, increase inter-observer agreement between radiologists, and alleviate pressures caused by rising case incidence and a shortage of specialist radiologists to read prostate mpMRI. However, well-designed evaluation studies are required to prove efficacy above current clinical practice. A systematic search of the MEDLINE, EMBASE, and arXiv electronic databases was conducted for studies that compared CAD for prostate cancer detection or classification on MRI against radiologist interpretation and a histopathological reference standard, in treatment-naïve men with a clinical suspicion of prostate cancer. Twenty-seven studies were included in the final analysis. Due to substantial heterogeneities in the included studies, a narrative synthesis is presented. Several studies reported superior diagnostic accuracy for CAD over radiologist interpretation on small, internal patient datasets, though this was not observed in the few studies that performed evaluation using external patient data. Our review found insufficient evidence to suggest the clinical deployment of artificial intelligence algorithms at present. Further work is needed to develop and enforce methodological standards, promote access to large diverse datasets, and conduct prospective evaluations before clinical adoption can be considered.https://www.mdpi.com/2072-6694/13/13/3318artificial intelligencecomputer-aided diagnosismachine learningdeep learningmagnetic resonance imagingPRISMA-DTA |
| spellingShingle | Tom Syer Pritesh Mehta Michela Antonelli Sue Mallett David Atkinson Sébastien Ourselin Shonit Punwani Artificial Intelligence Compared to Radiologists for the Initial Diagnosis of Prostate Cancer on Magnetic Resonance Imaging: A Systematic Review and Recommendations for Future Studies Cancers artificial intelligence computer-aided diagnosis machine learning deep learning magnetic resonance imaging PRISMA-DTA |
| title | Artificial Intelligence Compared to Radiologists for the Initial Diagnosis of Prostate Cancer on Magnetic Resonance Imaging: A Systematic Review and Recommendations for Future Studies |
| title_full | Artificial Intelligence Compared to Radiologists for the Initial Diagnosis of Prostate Cancer on Magnetic Resonance Imaging: A Systematic Review and Recommendations for Future Studies |
| title_fullStr | Artificial Intelligence Compared to Radiologists for the Initial Diagnosis of Prostate Cancer on Magnetic Resonance Imaging: A Systematic Review and Recommendations for Future Studies |
| title_full_unstemmed | Artificial Intelligence Compared to Radiologists for the Initial Diagnosis of Prostate Cancer on Magnetic Resonance Imaging: A Systematic Review and Recommendations for Future Studies |
| title_short | Artificial Intelligence Compared to Radiologists for the Initial Diagnosis of Prostate Cancer on Magnetic Resonance Imaging: A Systematic Review and Recommendations for Future Studies |
| title_sort | artificial intelligence compared to radiologists for the initial diagnosis of prostate cancer on magnetic resonance imaging a systematic review and recommendations for future studies |
| topic | artificial intelligence computer-aided diagnosis machine learning deep learning magnetic resonance imaging PRISMA-DTA |
| url | https://www.mdpi.com/2072-6694/13/13/3318 |
| work_keys_str_mv | AT tomsyer artificialintelligencecomparedtoradiologistsfortheinitialdiagnosisofprostatecanceronmagneticresonanceimagingasystematicreviewandrecommendationsforfuturestudies AT priteshmehta artificialintelligencecomparedtoradiologistsfortheinitialdiagnosisofprostatecanceronmagneticresonanceimagingasystematicreviewandrecommendationsforfuturestudies AT michelaantonelli artificialintelligencecomparedtoradiologistsfortheinitialdiagnosisofprostatecanceronmagneticresonanceimagingasystematicreviewandrecommendationsforfuturestudies AT suemallett artificialintelligencecomparedtoradiologistsfortheinitialdiagnosisofprostatecanceronmagneticresonanceimagingasystematicreviewandrecommendationsforfuturestudies AT davidatkinson artificialintelligencecomparedtoradiologistsfortheinitialdiagnosisofprostatecanceronmagneticresonanceimagingasystematicreviewandrecommendationsforfuturestudies AT sebastienourselin artificialintelligencecomparedtoradiologistsfortheinitialdiagnosisofprostatecanceronmagneticresonanceimagingasystematicreviewandrecommendationsforfuturestudies AT shonitpunwani artificialintelligencecomparedtoradiologistsfortheinitialdiagnosisofprostatecanceronmagneticresonanceimagingasystematicreviewandrecommendationsforfuturestudies |