Brendan S Kelly1,2,3,4,5, Conor Judge6,7, Stephanie M Bollard6,8, Simon M Clifford9, Gerard M Healy9, Awsam Aziz8, Prateek Mathur10, Shah Islam11, Kristen W Yeom12, Aonghus Lawlor10, Ronan P Killeen9,8. 1. St Vincent's University Hospital, Dublin, Ireland. brendanskelly@me.com. 2. Insight Centre for Data Analytics, UCD, Dublin, Ireland. brendanskelly@me.com. 3. Wellcome Trust - HRB, Irish Clinical Academic Training, Dublin, Ireland. brendanskelly@me.com. 4. School of Medicine, University College Dublin, Dublin, Ireland. brendanskelly@me.com. 5. HRB-Clinical Research Facility, NUI Galway, Galway, Ireland. brendanskelly@me.com. 6. Wellcome Trust - HRB, Irish Clinical Academic Training, Dublin, Ireland. 7. Lucille Packard Children's Hospital at Stanford, Stanford, CA, USA. 8. School of Medicine, University College Dublin, Dublin, Ireland. 9. St Vincent's University Hospital, Dublin, Ireland. 10. Insight Centre for Data Analytics, UCD, Dublin, Ireland. 11. Division of Brain Sciences, Imperial College London, GN1 Commonwealth Building, Hammersmith Hospital, Du Cane Road, London, W12 0HS, UK. 12. HRB-Clinical Research Facility, NUI Galway, Galway, Ireland.
Abstract
OBJECTIVE: There has been a large amount of research in the field of artificial intelligence (AI) as applied to clinical radiology. However, these studies vary in design and quality and systematic reviews of the entire field are lacking.This systematic review aimed to identify all papers that used deep learning in radiology to survey the literature and to evaluate their methods. We aimed to identify the key questions being addressed in the literature and to identify the most effective methods employed. METHODS: We followed the PRISMA guidelines and performed a systematic review of studies of AI in radiology published from 2015 to 2019. Our published protocol was prospectively registered. RESULTS: Our search yielded 11,083 results. Seven hundred sixty-seven full texts were reviewed, and 535 articles were included. Ninety-eight percent were retrospective cohort studies. The median number of patients included was 460. Most studies involved MRI (37%). Neuroradiology was the most common subspecialty. Eighty-eight percent used supervised learning. The majority of studies undertook a segmentation task (39%). Performance comparison was with a state-of-the-art model in 37%. The most used established architecture was UNet (14%). The median performance for the most utilised evaluation metrics was Dice of 0.89 (range .49-.99), AUC of 0.903 (range 1.00-0.61) and Accuracy of 89.4 (range 70.2-100). Of the 77 studies that externally validated their results and allowed for direct comparison, performance on average decreased by 6% at external validation (range increase of 4% to decrease 44%). CONCLUSION: This systematic review has surveyed the major advances in AI as applied to clinical radiology. KEY POINTS: • While there are many papers reporting expert-level results by using deep learning in radiology, most apply only a narrow range of techniques to a narrow selection of use cases. • The literature is dominated by retrospective cohort studies with limited external validation with high potential for bias. • The recent advent of AI extensions to systematic reporting guidelines and prospective trial registration along with a focus on external validation and explanations show potential for translation of the hype surrounding AI from code to clinic.
OBJECTIVE: There has been a large amount of research in the field of artificial intelligence (AI) as applied to clinical radiology. However, these studies vary in design and quality and systematic reviews of the entire field are lacking.This systematic review aimed to identify all papers that used deep learning in radiology to survey the literature and to evaluate their methods. We aimed to identify the key questions being addressed in the literature and to identify the most effective methods employed. METHODS: We followed the PRISMA guidelines and performed a systematic review of studies of AI in radiology published from 2015 to 2019. Our published protocol was prospectively registered. RESULTS: Our search yielded 11,083 results. Seven hundred sixty-seven full texts were reviewed, and 535 articles were included. Ninety-eight percent were retrospective cohort studies. The median number of patients included was 460. Most studies involved MRI (37%). Neuroradiology was the most common subspecialty. Eighty-eight percent used supervised learning. The majority of studies undertook a segmentation task (39%). Performance comparison was with a state-of-the-art model in 37%. The most used established architecture was UNet (14%). The median performance for the most utilised evaluation metrics was Dice of 0.89 (range .49-.99), AUC of 0.903 (range 1.00-0.61) and Accuracy of 89.4 (range 70.2-100). Of the 77 studies that externally validated their results and allowed for direct comparison, performance on average decreased by 6% at external validation (range increase of 4% to decrease 44%). CONCLUSION: This systematic review has surveyed the major advances in AI as applied to clinical radiology. KEY POINTS: • While there are many papers reporting expert-level results by using deep learning in radiology, most apply only a narrow range of techniques to a narrow selection of use cases. • The literature is dominated by retrospective cohort studies with limited external validation with high potential for bias. • The recent advent of AI extensions to systematic reporting guidelines and prospective trial registration along with a focus on external validation and explanations show potential for translation of the hype surrounding AI from code to clinic.
Authors: Elisa Luyckx; Jan M L Bosmans; Bart J G Broeckx; Sarah Ceyssens; Paul M Parizel; Annemie Snoeckx Journal: J Am Coll Radiol Date: 2018-09-21 Impact factor: 5.532
Authors: Mohammad R Arbabshirani; Brandon K Fornwalt; Gino J Mongelluzzo; Jonathan D Suever; Brandon D Geise; Aalpen A Patel; Gregory J Moore Journal: NPJ Digit Med Date: 2018-04-04
Authors: Brendan Kelly; Conor Judge; Stephanie M Bollard; Simon M Clifford; Gerard M Healy; Kristen W Yeom; Aonghus Lawlor; Ronan P Killeen Journal: Insights Imaging Date: 2020-12-09
Authors: Kaining Sheng; Cecilie Mørck Offersen; Jon Middleton; Jonathan Frederik Carlsen; Thomas Clement Truelsen; Akshay Pai; Jacob Johansen; Michael Bachmann Nielsen Journal: Diagnostics (Basel) Date: 2022-08-03