Purpose: The Prostate Imaging Reporting and Data System (PI-RADS) was introduced to standardize prostate cancer diagnosis by MRI. However, the inter-reader agreement by PI-RADS scoring is not always high. The purpose of this study was to validate a deep-learning-based diagnostic algorithm of PI-RADS. Methods: We applied a Siemens Healthineers Prostate Artificial Intelligence (AI) prototype (work in progress) for fully automated prostate lesion detection, classification and reporting. More than 2000 bi-parametric MRI studies along with the PI-RADS reports were included as training, validation, and test data. This prospective validation study includes 101 consecutive patients suspected of prostate cancer, and 100 patients were included in the analysis. All subjects underwent a noncontrast-enhanced bi-parametric MRI including T2-weighted and diffusion-weighted imaging. Two board-certified radiologists independently scored the PI-RADS, and if there were disagreements; another radiologist confirmed the diagnosis. We compared the AI results with the interpretation results by the radiologists. Results: The sensitivity of our AI model for PI-RADS ≥ 4 was 0.76, and the specificity was 0.76. For the cases with PI-RADS ≥ 3, the sensitivity was 0.69, and the specificity was 0.76. In the lesion-based analysis, AI detection rates of PI-RADS 3, 4, 5 lesions in the peripheral zone were 43%, 63%, and 100%, respectively. In the transition zone, AI detection rates of PI-RADS 3, 4, 5 were 30%, 54%, and 100%, respectively. Conclusion: Our deep-learning-based algorithm has been validated and shown to help score PI-RADS.
References
[1]
Torre, L.A., Bray, F., Siegel, R.L., Ferlay, J., Lortet-Tieulent, J. and Jemal, A. (2015) Global Cancer Statistics, 2012. CA: A Cancer Journal for Clinicians, 65, 87-108.
https://doi.org/10.3322/caac.21262
[2]
Bashir, M.N. (2015) Epidemiology of Prostate Cancer. Asian Pacific Journal of Cancer Prevention, 16, 5137-5141. https://doi.org/10.7314/APJCP.2015.16.13.5137
[3]
Stamey, T.A., Yang, N., Hay, A.R., McNeal, J.E., Freiha, F.S. and Redwine, E. (1987) Prostate-Specific Antigen as a Serum Marker for Adenocarcinoma of the Prostate. New England Journal of Medicine, 317, 909-916.
https://doi.org/10.1056/NEJM198710083171501
[4]
Barry, M.J. and Simmons, L.H. (2017) Prevention of Prostate Cancer Morbidity and Mortality: Primary Prevention and Early Detection. Medical Clinics of North America, 101, 787-806. https://doi.org/10.1016/j.mcna.2017.03.009
[5]
Wade, J., Rosario, D.J., Macefield, R.C., Avery, K.N., Salter, C.E., Goodwin, M.L., et al. (2013) Psychological Impact of Prostate Biopsy: Physical Symptoms, Anxiety, and Depression. Journal of Clinical Oncology, 31, 4235-4241.
https://doi.org/10.1200/JCO.2012.45.4801
[6]
Salami, S.S., Vira, M.A., Turkbey, B., Fakhoury, M., Yaskiv, O., Villani, R., et al. (2014) Multiparametric Magnetic Resonance Imaging Outperforms the Prostate Cancer Prevention Trial Risk Calculator in Predicting Clinically Significant Prostate Cancer. Cancer, 120, 2876-2882. https://doi.org/10.1002/cncr.28790
[7]
Hamoen, E.H.J., de Rooij, M., Witjes, J.A., Barentsz, J.O. and Rovers, M.M. (2015) Use of the Prostate Imaging Reporting and Data System (PI-RADS) for Prostate Cancer Detection with Multiparametric Magnetic Resonance Imaging: A Diagnostic Meta-Analysis. European Urology, 67, 1112-1121.
https://doi.org/10.1016/j.eururo.2014.10.033
[8]
Woo, S., Suh, C.H., Kim, S.Y., Cho, J.Y. and Kim, S.H. (2017) Diagnostic Performance of Prostate Imaging Reporting and Data System Version 2 for Detection of Prostate Cancer: A Systematic Review and Diagnostic Meta-Analysis. European Urology, 72, 177-188. https://doi.org/10.1016/j.eururo.2017.01.042
[9]
Hofbauer, S.L., Maxeiner, A., Kittner, B., Heckmann, R., Reimann, M., Wiemer, L., et al. (2018) Validation of Prostate Imaging Reporting and Data System Version 2 for the Detection of Prostate Cancer. Journal of Urology, 200, 767-773.
https://doi.org/10.1016/j.juro.2018.05.003
[10]
Thai, J.N., Narayanan, H.A., George, A.K., Siddiqui, M.M., Shah, P., Mertan, F.V., et al. (2018) Validation of PI-RADS Version 2 in Transition Zone Lesions for the Detection of Prostate Cancer. Radiology, 288, 485-491.
https://doi.org/10.1148/radiol.2018170425
[11]
Greer, M.D., Lay, N., Shih, J.H., Barrett, T., Bittencourt, L.K., Borofsky, S., et al. (2018) Computer-Aided Diagnosis Prior to Conventional Interpretation of Prostate mpMRI: An International Multi-Reader study. European Radiology, 28, 4407-4417.
https://doi.org/10.1007/s00330-018-5374-6
[12]
Yuan, Y., Qin, W., Buyyounouski, M., Ibragimov, B., Hancock, S., Han, B., et al. (2019) Prostate Cancer Classification with Multiparametric MRI Transfer Learning Model. Medical Physics, 46, 756-765. https://doi.org/10.1002/mp.13367
[13]
Nagpal, K., Foote, D., Liu, Y., Chen, P.C., Wulczyn, E., Tan, F., et al. (2019) Development and Validation of a Deep Learning Algorithm for Improving Gleason Scoring of Prostate Cancer. NPJ Digital Medicine, 2, Article No. 48.
https://doi.org/10.1038/s41746-019-0112-2
[14]
Yu, X., Lou, B., Shi, B., Winkel, D., Arrahmane, N., Diallo, M., et al. (2020) False Positive Reduction Using Multiscale Contextual Features for Prostate Cancer Detection in Multi-Parametric MRI Scans. Proceedings of 2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI), Iowa City, 3-7 April 2020, 1355-1359.
https://doi.org/10.1109/ISBI45749.2020.9098338
[15]
Winkel, D.J., Tong, A., Lou, B., Kamen, A., Comaniciu, D., Disselhorst, J.A., et al. (2021) A Novel Deep Learning Based Computer-Aided Diagnosis System Improves the Accuracy and Efficiency of Radiologists in Reading Biparametric Magnetic Resonance Images of the Prostate: Results of a Multireader, Multicase Study. Investigative Radiology, 56, 605-613. https://doi.org/10.1097/RLI.0000000000000780
