Bridging the experience gap in prostate multiparametric magnetic resonance imaging using artificial intelligence: A prospective multi-reader comparison study on inter-reader agreement in PI-RADS v2.1, image quality and reporting time between novice and expert readers

被引:12
作者
Forookhi, Ali [1 ]
Laschena, Ludovica [1 ]
Pecoraro, Martina [1 ]
Borrelli, Antonella [1 ]
Massaro, Michele [1 ]
Dehghanpour, Ailin [1 ]
Cipollari, Stefano [1 ]
Catalano, Carlo [1 ]
Panebianco, Valeria [1 ,2 ]
机构
[1] Sapienza Univ Rome, Dept Radiol Sci Oncol & Pathol, Rome, Italy
[2] Sapienza Policlin Umberto I, Dept Radiol Sci Oncol & Pathol, Viale Regina Elena 324, I-00161 Rome, Italy
关键词
Artificial Intelligence; Prostate cancer; Magnetic Resonance Imaging; PI; -QUAL; -RADS; Learning Curve; MRI; SYSTEM; RADIOLOGISTS; DIAGNOSIS; ACCURACY;
D O I
10.1016/j.ejrad.2023.110749
中图分类号
R8 [特种医学]; R445 [影像诊断学];
学科分类号
1002 ; 100207 ; 1009 ;
摘要
Purpose: The aim of the study was to determine the impact of using a semi-automatic commercially available AIassisted software (Quantib (R) Prostate) on inter-reader agreement in PI-RADS scoring at different PI-QUAL ratings and grades of reader confidence and on reporting times among novice readers in multiparametric prostate MRI. Methods: A prospective observational study, with a final cohort of 200 patients undergoing mpMRI scans, was performed at our institution. An expert fellowship-trained urogenital radiologist interpreted all 200 scans based on PI-RADS v2.1. The scans were divided into four equal batches of 50 patients. Four independent readers evaluated each batch with and without the use of AI-assisted software, blinded to expert and individual reports. Dedicated training sessions were held before and after each batch. Image quality rated according to PI-QUAL and reporting times were recorded. Readers' confidence was also evaluated. A final evaluation of the first batch was conducted at the end of the study to assess for any changes in performance. Results: The overall kappa coefficient differences in PI-RADS scoring agreement without and with Quantib (R) were 0.673 to 0.736 for Reader 1, 0.628 to 0.483 for Reader 2, 0.603 to 0.292 for Reader 3 and 0.586 to 0.613 for Reader 4. Using PI-RADS >= 4 as cut-off for biopsy, the AUCs with AI ranged from 0.799 (95 % CI: 0.743, 0.856) to 0.820 (95 % CI: 0.765, 0.874). Inter-reader agreements at different PI-QUAL scores were higher with the use of Quantib, particularly for readers 1 and 4, with Kappa coefficient values showing moderate to slight agreement. Conclusion: Quantib (R) Prostate could potentially be useful in improving inter-reader agreement among less experienced to completely novice readers if used as a supplement to PACS.
引用
收藏
页数:10
相关论文
共 38 条
[1]  
Ahmed H.U., LANCET
[2]   Interactive dedicated training curriculum improves accuracy in the interpretation of MR imaging of prostate cancer [J].
Akin, Oguz ;
Riedl, Christopher C. ;
Ishill, Nicole M. ;
Moskowitz, Chaya S. ;
Zhang, Jingbo ;
Hricak, Hedvig .
EUROPEAN RADIOLOGY, 2010, 20 (04) :995-1002
[3]   Interobserver Agreement and Accuracy in Interpreting mpMRI of the Prostate: a Systematic Review [J].
Annamalai, Arvind ;
Fustok, Judy N. ;
Beltran-Perez, Jesus ;
Rashad, Ahmed T. ;
Krane, Louis S. ;
Triche, Benjamin L. .
CURRENT UROLOGY REPORTS, 2022, 23 (01) :1-10
[4]   Biparametric prostate MRI: impact of a deep learning-based software and of quantitative ADC values on the inter-reader agreement of experienced and inexperienced readers [J].
Cipollari, Stefano ;
Pecoraro, Martina ;
Forookhi, Ali ;
Laschena, Ludovica ;
Bicchetti, Marco ;
Messina, Emanuele ;
Lucciola, Sara ;
Catalano, Carlo ;
Panebianco, Valeria .
RADIOLOGIA MEDICA, 2022, 127 (11) :1245-1253
[5]   Clinically Significant Prostate Cancer Detection With Biparametric MRI: A Systematic Review and Meta-Analysis [J].
Cuocolo, Renato ;
Verde, Francesco ;
Ponsiglione, Andrea ;
Romeo, Valeria ;
Petretta, Mario ;
Imbriaco, Massimo ;
Stanzione, Arnaldo .
AMERICAN JOURNAL OF ROENTGENOLOGY, 2021, 216 (03) :608-621
[6]   Focus on the Quality of Prostate Multiparametric Magnetic Resonance Imaging: Synopsis of the ESUR/ESUI Recommendations on Quality Assessment and Interpretation of Images and Radiologists' Training [J].
de Rooij, Maarten ;
Israel, Bas ;
Barrett, Tristan ;
Giganti, Francesco ;
Padhani, Anwar R. ;
Panebianco, Valeria ;
Richenberg, Jonathan ;
Salomon, Georg ;
Schoots, Ivo G. ;
Villeirs, Geert ;
Walz, Jochen ;
Barentsz, Jelle O. .
EUROPEAN UROLOGY, 2020, 78 (04) :483-485
[7]   ESUR/ESUI consensus statements on multi-parametric MRI for the detection of clinically significant prostate cancer: quality requirements for image acquisition, interpretation and radiologists' training [J].
de Rooij, Maarten ;
Israel, Bas ;
Tummers, Marcia ;
Ahmed, Hashim U. ;
Barrett, Tristan ;
Giganti, Francesco ;
Hamm, Bernd ;
Logager, Vibeke ;
Padhani, Anwar ;
Panebianco, Valeria ;
Puech, Philippe ;
Richenberg, Jonathan ;
Rouviere, Olivier ;
Salomon, Georg ;
Schoots, Ivo ;
Veltman, Jeroen ;
Villeirs, Geert ;
Walz, Jochen ;
Barentsz, Jelle O. .
EUROPEAN RADIOLOGY, 2020, 30 (10) :5404-5416
[8]   Prostate Magnetic Resonance Imaging, with or Without Magnetic Resonance Imaging-targeted Biopsy, and Systematic Biopsy for Detecting Prostate Cancer: A Cochrane Systematic Review and Meta-analysis [J].
Drost, Frank-Jan H. ;
Osses, Daniel ;
Nieboer, Daan ;
Bangma, Chris H. ;
Steyerberg, Ewout W. ;
Roobol, Monique J. ;
Schoots, Ivo G. .
EUROPEAN UROLOGY, 2020, 77 (01) :78-94
[9]   Deep learning-accelerated T2-weighted imaging of the prostate: Reduction of acquisition time and improvement of image quality [J].
Gassenmaier, Sebastian ;
Afat, Saif ;
Nickel, Dominik ;
Mostapha, Mahmoud ;
Herrmann, Judith ;
Othman, Ahmed E. .
EUROPEAN JOURNAL OF RADIOLOGY, 2021, 137
[10]   Is Artificial Intelligence Replacing Our Radiology Stars in Prostate Magnetic Resonance Imaging? The Stars Do Not Look Big, But They Can Look Brighter [J].
Giganti, Francesco ;
Panebianco, Valeria ;
Tempany, Clare M. ;
Purysko, Andrei S. .
EUROPEAN UROLOGY OPEN SCIENCE, 2023, 48 :12-13