Address reprint requests to: X.W., Department of Radiology, Peking University First Hospital, No. 8 Xishiku Street, Xicheng District, Beijing 100034, China.

E-mail: [email protected]

Search for more papers by this author

Zhaonan Sun MD,

Zhaonan Sun MD

Department of Radiology, Peking University First Hospital, Beijing, China

Search for more papers by this author

Pengsheng Wu BS,

Pengsheng Wu BS

Beijing Smart Tree Medical Technology Co. Ltd, Beijing, China

Search for more papers by this author

Yingpu Cui MD,

Yingpu Cui MD

Department of Nuclear Medicine, Sun Yat-Sen University Cancer Center, Guangzhou, Guangdong, China

State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Guangzhou, Guangdong, China

Search for more papers by this author

Xiang Liu PhD,

Xiang Liu PhD

Department of Radiology, Peking University First Hospital, Beijing, China

Search for more papers by this author

Kexin Wang,

Kexin Wang

School of Basic Medical Sciences, Capital Medical University, Beijing, China

Search for more papers by this author

Ge Gao PhD,

Ge Gao PhD

Department of Radiology, Peking University First Hospital, Beijing, China

Search for more papers by this author

Huihui Wang MD,

Huihui Wang MD

Department of Radiology, Peking University First Hospital, Beijing, China

Search for more papers by this author

Xiaodong Zhang PhD,

Xiaodong Zhang PhD

orcid.org/0000-0002-1058-480X

Department of Radiology, Peking University First Hospital, Beijing, China

Search for more papers by this author

Xiaoying Wang MD, PhD,

Corresponding Author

Xiaoying Wang MD, PhD

[email protected]

orcid.org/0000-0001-9822-961X

Department of Radiology, Peking University First Hospital, Beijing, China

Address reprint requests to: X.W., Department of Radiology, Peking University First Hospital, No. 8 Xishiku Street, Xicheng District, Beijing 100034, China.

E-mail: [email protected]

Search for more papers by this author

First published: 24 February 2023

https://doi.org/10.1002/jmri.28608

Citations: 7

Share a link

Email
Wechat
Bluesky

Abstract

Background

Deep learning for diagnosing clinically significant prostate cancer (csPCa) is feasible but needs further evaluation in patients with prostate-specific antigen (PSA) levels of 4–10 ng/mL.

Purpose

To explore diffusion-weighted imaging (DWI), alone and in combination with T2-weighted imaging (T2WI), for deep-learning-based models to detect and localize visible csPCa.

Study Type

Retrospective.

Population

One thousand six hundred twenty-eight patients with systematic and cognitive-targeted biopsy-confirmation (1007 csPCa, 621 non-csPCa) were divided into model development (N = 1428) and hold-out test (N = 200) datasets.

Field Strength/Sequence

DWI with diffusion-weighted single-shot gradient echo planar imaging sequence and T2WI with T2-weighted fast spin echo sequence at 3.0-T and 1.5-T.

Assessment

The ground truth of csPCa was annotated by two radiologists in consensus. A diffusion model, DWI and apparent diffusion coefficient (ADC) as input, and a biparametric model (DWI, ADC, and T2WI as input) were trained based on U-Net. Three radiologists provided the PI-RADS (version 2.1) assessment. The performances were determined at the lesion, location, and the patient level.

Statistical Tests

The performance was evaluated using the areas under the ROC curves (AUCs), sensitivity, specificity, and accuracy. A P value <0.05 was considered statistically significant.

Results

The lesion-level sensitivities of the diffusion model, the biparametric model, and the PI-RADS assessment were 89.0%, 85.3%, and 90.8% (P = 0.289–0.754). At the patient level, the diffusion model had significantly higher sensitivity than the biparametric model (96.0% vs. 90.0%), while there was no significant difference in specificity (77.0%. vs. 85.0%, P = 0.096). For location analysis, there were no significant differences in AUCs between the models (sextant-level, 0.895 vs. 0.893, P = 0.777; zone-level, 0.931 vs. 0.917, P = 0.282), and both models had significantly higher AUCs than the PI-RADS assessment (sextant-level, 0.734; zone-level, 0.863).

Data Conclusion

The diffusion model achieved the best performance in detecting and localizing csPCa in patients with PSA levels of 4–10 ng/mL.

Evidence Level

Technical Efficacy

Stage 2

Supporting Information

References

1Heidenreich A, Bellmunt J, Bolla M, et al. EAU guidelines on prostate cancer. Part 1: Screening, diagnosis, and treatment of clinically localised disease. Eur Urol 2011; 59(1): 61-71.
10.1016/j.eururo.2010.10.039
PubMed Web of Science® Google Scholar
2Turkbey B, Rosenkrantz AB, Haider MA, et al. Prostate imaging reporting and data system version 2.1: 2019 update of prostate imaging reporting and data system version 2. Eur Urol 2019; 76(3): 340-351.
10.1016/j.eururo.2019.02.033
PubMed Web of Science® Google Scholar
3Woo S, Suh CH, Kim SY, Cho JY, Kim SH. Diagnostic performance of prostate imaging reporting and data system version 2 for detection of prostate cancer: A systematic review and diagnostic meta-analysis. Eur Urol 2017; 72(2): 177-188.
10.1016/j.eururo.2017.01.042
PubMed Web of Science® Google Scholar
4Lee MS, Moon MH, Kim YA, et al. Is prostate imaging reporting and data system version 2 sufficiently discovering clinically significant prostate cancer? Per-lesion radiology-pathology correlation study. AJR Am J Roentgenol 2018; 211(1): 114-120.
10.2214/AJR.17.18684
PubMed Web of Science® Google Scholar
5Johnson DC, Raman SS, Mirak SA, et al. Detection of individual prostate cancer foci via multiparametric magnetic resonance imaging. Eur Urol 2019; 75(5): 712-720.
10.1016/j.eururo.2018.11.031
CAS PubMed Web of Science® Google Scholar
6Dwivedi DK, Kumar R, Dwivedi AK, et al. Prebiopsy multiparametric MRI-based risk score for predicting prostate cancer in biopsy-naive men with prostate-specific antigen between 4-10 ng/mL. J Magn Reson Imaging 2018; 47(5): 1227-1236.
10.1002/jmri.25850
PubMed Web of Science® Google Scholar
7Liu J, Dong B, Qu W, et al. Using clinical parameters to predict prostate cancer and reduce the unnecessary biopsy among patients with PSA in the gray zone. Sci Rep 2020; 10(1): 5157.
10.1038/s41598-020-62015-w
CAS PubMed Web of Science® Google Scholar
8Huang Y, Li ZZ, Huang YL, Song HJ, Wang YJ. Value of free/total prostate-specific antigen (f/t PSA) ratios for prostate cancer detection in patients with total serum prostate-specific antigen between 4 and 10 ng/mL: A meta-analysis. Medicine 2018; 97(13):e0249.
10.1097/MD.0000000000010249
CAS PubMed Web of Science® Google Scholar
9Siegel RL, Miller KD, Fuchs HE, Jemal A. Cancer statistics, 2022. CA Cancer J Clin 2022; 72(1): 7-33.
10.3322/caac.21708
PubMed Web of Science® Google Scholar
10Padhani AR, Turkbey B. Detecting prostate cancer with deep learning for MRI: A small step forward. Radiology 2019; 293(3): 618-619.
10.1148/radiol.2019192012
PubMed Web of Science® Google Scholar
11Cipollari S, Pecoraro M, Forookhi A, et al. 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. Radiol Med 2022; 127(11): 1245-1253.
10.1007/s11547-022-01555-9
PubMed Web of Science® Google Scholar
12Khosravi P, Lysandrou M, Eljalby M, et al. A deep learning approach to diagnostic classification of prostate cancer using pathology-radiology fusion. J Magn Reson Imaging 2021; 54(2): 462-471.
10.1002/jmri.27599
PubMed Web of Science® Google Scholar
13Hosseinzadeh M, Saha A, Brand P, Slootweg I, de Rooij M, Huisman H. Deep learning-assisted prostate cancer detection on bi-parametric MRI: Minimum training data size requirements and effect of prior knowledge. Eur Radiol 2022; 32(4): 2224-2234.
10.1007/s00330-021-08320-y
CAS PubMed Web of Science® Google Scholar
14Mehralivand S, Yang D, Harmon SA, et al. Deep learning-based artificial intelligence for prostate cancer detection at biparametric MRI. Abdom Radiol (NY) 2022; 47(4): 1425-1434.
10.1007/s00261-022-03419-2
PubMed Web of Science® Google Scholar
15Hiremath A, Shiradkar R, Fu P, et al. An integrated nomogram combining deep learning, Prostate Imaging-Reporting and Data System (PI-RADS) scoring, and clinical variables for identification of clinically significant prostate cancer on biparametric MRI: A retrospective multicentre study. Lancet Digit Health 2021; 3(7): e445-e454.
10.1016/S2589-7500(21)00082-0
CAS PubMed Google Scholar
16Arif M, Schoots IG, Castillo Tovar J, et al. Clinically significant prostate cancer detection and segmentation in low-risk patients using a convolutional neural network on multi-parametric MRI. Eur Radiol 2020; 30(12): 6582-6592.
10.1007/s00330-020-07008-z
PubMed Web of Science® Google Scholar
17Reda I, Khalil A, Elmogy M, et al. Deep learning role in early diagnosis of prostate cancer. Technol Cancer Res Treat 2018; 17: 1533034618775530.
10.1177/1533034618775530
Web of Science® Google Scholar
18Hiremath A, Shiradkar R, Merisaari H, et al. Test-retest repeatability of a deep learning architecture in detecting and segmenting clinically significant prostate cancer on apparent diffusion coefficient (ADC) maps. Eur Radiol 2021; 31(1): 379-391.
10.1007/s00330-020-07065-4
PubMed Web of Science® Google Scholar
19Yan K, Wang X, Kim J, Khadra M, Fulham M, Feng D. A propagation-DNN: Deep combination learning of multi-level features for MR prostate segmentation. Comput Methods Programs Biomed 2019; 170: 11-21.
10.1016/j.cmpb.2018.12.031
PubMed Web of Science® Google Scholar
20Thon A, Teichgraber U, Tennstedt-Schenk C, et al. Computer aided detection in prostate cancer diagnostics: A promising alternative to biopsy? A retrospective study from 104 lesions with histological ground truth. PLoS One 2017; 12(10):e0185995.
10.1371/journal.pone.0185995
PubMed Web of Science® Google Scholar
21Weinreb JC, Barentsz JO, Choyke PL, et al. PI-RADS prostate imaging - reporting and data system: 2015, version 2. Eur Urol 2016; 69(1): 16-40.
10.1016/j.eururo.2015.08.052
PubMed Web of Science® Google Scholar
22Radtke JP, Schwab C, Wolf MB, et al. Multiparametric magnetic resonance imaging (MRI) and MRI-transrectal ultrasound fusion biopsy for index tumor detection: Correlation with radical prostatectomy specimen. Eur Urol 2016; 70(5): 846-853.
10.1016/j.eururo.2015.12.052
PubMed Web of Science® Google Scholar
23Epstein JI, Egevad L, Amin MB, Delahunt B, Srigley JR, Humphrey PA. The 2014 International Society of Urological Pathology (ISUP) consensus conference on Gleason grading of prostatic carcinoma: Definition of grading patterns and proposal for a new grading system. Am J Surg Pathol 2016; 40(2): 244-252.
10.1097/PAS.0000000000000530
PubMed Web of Science® Google Scholar
24Yushkevich PA, Piven J, Hazlett HC, et al. User-guided 3D active contour segmentation of anatomical structures: Significantly improved efficiency and reliability. Neuroimage 2006; 31(3): 1116-1128.
10.1016/j.neuroimage.2006.01.015
PubMed Web of Science® Google Scholar
25Zhu Y, Wei R, Gao G, et al. Fully automatic segmentation on prostate MR images based on cascaded fully convolution network. J Magn Reson Imaging 2019; 49(4): 1149-1156.
10.1002/jmri.26337
PubMed Web of Science® Google Scholar
26Presti JC. Prostate biopsy: Current status and limitations. Rev Urol 2007; 9(3): 93-98.
PubMed Google Scholar
27Çiçek Ö, Abdulkadir A, Lienkamp SS, Brox T, Ronneberger OJA. 3D U-net: Learning dense volumetric segmentation from sparse annotation. 2016. abs/1606.06650.
Google Scholar
28Gaur S, Lay N, Harmon SA, et al. Can computer-aided diagnosis assist in the identification of prostate cancer on prostate MRI? A multi-center, multi-reader investigation. Oncotarget 2018; 9(73): 33804-33817.
10.18632/oncotarget.26100
PubMed Google Scholar
29Giannini V, Mazzetti S, Armando E, et al. Multiparametric magnetic resonance imaging of the prostate with computer-aided detection: Experienced observer performance study. Eur Radiol 2017; 27(10): 4200-4208.
10.1007/s00330-017-4805-0
PubMed Web of Science® Google Scholar
30Schelb P, Kohl S, Radtke JP, et al. Classification of cancer at prostate MRI: Deep learning versus clinical PI-RADS assessment. Radiology 2019; 293(3): 607-617.
10.1148/radiol.2019190938
PubMed Web of Science® Google Scholar
31Schröder FH, Hugosson J, Roobol MJ, et al. Screening and prostate cancer mortality: Results of the European Randomised Study of Screening for Prostate Cancer (ERSPC) at 13 years of follow-up. Lancet (London, England) 2014; 384(9959): 2027-2035.
10.1016/S0140-6736(14)60525-0
PubMed Web of Science® Google Scholar
32Liu C, Liu SL, Wang ZX, et al. Using the prostate imaging reporting and data system version 2 (PI-RIDS v2) to detect prostate cancer can prevent unnecessary biopsies and invasive treatment. Asian J Androl 2018; 20(5): 459-464.
10.4103/aja.aja_19_18
CAS PubMed Web of Science® Google Scholar
33Qi Y, Zhang S, Wei J, et al. Multiparametric MRI-based radiomics for prostate cancer screening with PSA in 4-10 ng/mL to reduce unnecessary biopsies. J Magn Reson Imaging 2020; 51(6): 1890-1899.
10.1002/jmri.27008
PubMed Web of Science® Google Scholar
34Chen Y, Ruan M, Zhou B, et al. Cutoff values of prostate imaging reporting and data system version 2.1 score in men with prostate-specific antigen level 4 to 10 ng/mL: Importance of lesion location. Clin Genitourin Cancer 2021; 19(4): 288-295.
10.1016/j.clgc.2020.12.007
PubMed Web of Science® Google Scholar
35Bi WL, Hosny A, Schabath MB, et al. Artificial intelligence in cancer imaging: Clinical challenges and applications. CA Cancer J Clin 2019; 69(2): 127-157.
10.3322/caac.21552
PubMed Web of Science® Google Scholar
36Wake N, Rosenkrantz AB, Huang R, et al. Patient-specific 3D printed and augmented reality kidney and prostate cancer models: impact on patient education. 3D Print Med 2019; 5(1): 4.
10.1186/s41205-019-0041-3
PubMed Google Scholar
37Yuan Y, Qin W, Buyyounouski M, et al. Prostate cancer classification with multiparametric MRI transfer learning model. Med Phys 2019; 46(2): 756-765.
10.1002/mp.13367
PubMed Web of Science® Google Scholar
38Wang B, Lei Y, Tian S, et al. Deeply supervised 3D fully convolutional networks with group dilated convolution for automatic MRI prostate segmentation. Med Phys 2019; 46(4): 1707-1718.
10.1002/mp.13416
PubMed Web of Science® Google Scholar

Citing Literature

Volume58, Issue4

October 2023

Pages 1067-1081

Deep-Learning Models for Detection and Localization of Visible Clinically Significant Prostate Cancer on Multi-Parametric MRI

Abstract

Background

Purpose

Study Type

Population

Field Strength/Sequence

Assessment

Statistical Tests

Results

Data Conclusion

Evidence Level

Technical Efficacy

Supporting Information

References

Citing Literature

References

Information

About Wiley Online Library

Help & Support

Opportunities

Connect with Wiley

Deep-Learning Models for Detection and Localization of Visible Clinically Significant Prostate Cancer on Multi-Parametric MRI

Abstract

Background

Purpose

Study Type

Population

Field Strength/Sequence

Assessment

Statistical Tests

Results

Data Conclusion

Evidence Level

Technical Efficacy

Supporting Information

References

Citing Literature

References

Related

Information