No abstract

No 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.

M ultiparametric MRI (mpMRI) has emerged as an integral part of the diagnostic pathway of prostate cancer (PCa) resulting in improved detection and localization of clinically significant PCa (csPCa). Multiple guidelines now recommend mpMRI before biopsy for all men with a clinical suspicion of csPCa (1-3). In a binary Prostate Imaging Reporting and Data System (PI-RADS)-directed biopsy pathway, men with intermediate (PI-RADS category 3) to high likelihood of csPCa (PI-RADS category 4 or 5) are considered for biopsy (4,5). The major challenges in using this approach clinically are the low positive predictive value (6,7) and moderate interreader and intercenter reproducibility (7,8). To reduce the number of false-positive mpMRI results and to improve the clinical benefits of an MRI pathway, additional laboratory and clinical factors may identify patients that can forego biopsy (1-4). Strategies for enhanced risk stratification include using prostate-specific antigen (PSA) density (PSAd) (9-14), other PSA-related analyses (15), or multivariable risk models incorporating . These models estimate the patient's risk of csPCa, which can guide decisions on prostate biopsy.Key aspects of prediction model performance are discrimination, calibration (ie, agreement between predicted Background: In validation studies, risk models for clinically significant prostate cancer (csPCa; Gleason score 314) combining multiparametric MRI and clinical factors have demonstrated poor calibration (over-and underprediction) and limited use in avoiding unnecessary prostate biopsies.Purpose: MRI-based risk models following local recalibration were compared with a strategy that combined Prostate Imaging Data and Reporting System (PI-RADS; version 2) and prostate-specific antigen density (PSAd) to assess the potential reduction of unnecessary prostate biopsies. Materials and Methods: This retrospective study included 385 patients without prostate cancer diagnosis who underwent multiparametric MRI (PI-RADS category 3) and MRI-targeted biopsy between 2015 and 2019. Recalibration and selection of the bestperforming MRI model (MRI-European Randomized Study of Screening for Prostate Cancer [ERSPC], van Leeuwen, Radtke, and Mehralivand models) were undertaken in cohort C1 (n = 242; 2015-2017). The impact on biopsy decisions was compared with an alternative strategy (no biopsy for PI-RADS category 3 plus PSAd ,0.1 ng/mL per milliliter) in cohort C2 (n = 143; 2018-2019). Discrimination, calibration, and clinical utility were assessed by using the area under the receiver operating characteristic curve (AUC), calibration plots, and decision curve analysis, respectively. Results:The prevalence of csPCa was 38% (93 of 242 patients) and 45% (64 of 143 patients) in cohorts C1 and C2, respectively. Decision curve analysis demonstrated the highest net benefit for the van Leeuwen and Mehralivand models in C1. Used for biopsy decisions in C2, van Leeuwen (AUC, 0.84; 95% CI: 0.77, 0.9) and Mehralivand (AUC, 0.79; 95% CI: 0.72, 0.86) enabled no net benefit at a r...

This is a patient-centred, mixed methodology study on patient education in IBD. Patients' preferences for education include components such as what to expect and diet and patients seem to distrust the internet as an IBD information source. International validation would be valuable to create a consensus education programme.