Share：
Share this content in WeChat
X
[Chinese][PDF]3155
• Clinical Article •
The utility of deep learning-clinical combined model based on bi-parametric MRI for diagnosis of clinically significant prostate cancer
HU Chenhan  QIAO Xiaomeng  HU Jisu  BAO Jie  CAO Changhao  WANG Ximing 

Cite this article as: HU C H, QIAO X M, HU J S, et al. The utility of deep learning-clinical combined model based on bi-parametric MRI for diagnosis of clinically significant prostate cancer[J]. Chin J Magn Reson Imaging, 2024, 15(2): 90-96. DOI:10.12015/issn.1674-8034.2024.02.013.


[Abstract] Objective To compare the diagnostic performance of the deep learning model based on bi-parametric MRI with a clinical model for clinically significant prostate cancer (csPCa) and explore the value of a combined model incorporating deep learning model and clinical variables to enhance the diagnostic efficacy of csPCa.Materials and Methods Imaging and clinical data from 531 patients (319 csPCa and 212 non-csPCa) who underwent pre-operative MRI and subsequent biopsy and/or surgical pathology examination for clinically suspected PCa at our hospital from February 2017 to May 2022 were retrospectively analyzed. The patients were randomly divided into a training cohort (425 cases) and a testing cohort (106 cases) at a ratio of 8∶2. The volumes of interests were manually segmented on T2-weighted imaging (T2WI), diffusion-weighted imaging (DWI), and its derivative apparent diffusion coefficient (ADC) maps and a deep learning model was developed utilizing the DenseNet network. Through univariate and multivariate logistic regressions, clinical features were selected to build a clinical model. A deep learning-clinical combined model was created by integrating the output of the deep learning model with clinical variables based on logistic regression. The receiver operating characteristic (ROC) curve was used to assess the model performance, and the DeLong test was employed to compare the diagnostic performance of different models.Results Logistic analyses showed that age, prostate specific antigen (PSA) value and prostate imaging reporting and data system (PI-RADS) score were significant factors for predicting csPCa. In the testing set, the AUC of the deep learning model was 0.90 [95% confidence interval (CI): 0.85-0.96], which showed no significant difference with the clinical model [0.85 (95% CI: 0.78-0.92), P=0.245]. The AUC of the deep learning-clinical combined model reached 0.93 (95% CI: 0.88-0.98), which significantly outperformed both the clinical model (P=0.034) and the deep learning model (P=0.048).Conclusions The diagnostic performance of the deep learning model for csPCa was comparable to the clinical model. The deep learning-clinical combined mode achieved the highest diagnostic efficacy, which possessed good practical utility and could be utilized as an auxiliary method for clinical diagnosis of csPCa.
[Keywords] prostate cancer；magnetic resonance imaging；deep learning；machine learning；diagnostic efficacy

HU Chenhan1   QIAO Xiaomeng1   HU Jisu2   BAO Jie1   CAO Changhao1   WANG Ximing1*  

1 Department of Radiology, First Affiliated Hospital of Soochow University, Suzhou 215006, China

2 Suzhou Institute of Biomedical Engineering and Technology, Chinese Academy of Sciences, Suzhou 215006, China

Corresponding author: WANG X M, E-mail: wangximing1998@163.com

Conflicts of interest   None.

Received  2023-08-15
Accepted  2024-01-15
DOI: 10.12015/issn.1674-8034.2024.02.013
Cite this article as: HU C H, QIAO X M, HU J S, et al. The utility of deep learning-clinical combined model based on bi-parametric MRI for diagnosis of clinically significant prostate cancer[J]. Chin J Magn Reson Imaging, 2024, 15(2): 90-96. DOI:10.12015/issn.1674-8034.2024.02.013.

[1]
YE D W, ZHU Y. Epidemiology of prostate cancer in China: an overview and clinical implication[J]. Chin J Surg, 2015, 53(4): 249-252. DOI: 10.3760/cma.j.issn.0529-5815.2015.04.003.
[2]
MOTTET N, VAN DEN BERGH R C N, BRIERS E, et al. EAU-EANM-ESTRO-ESUR-SIOG guidelines on prostate cancer-2020 update. part 1: screening, diagnosis, and local treatment with curative intent[J]. Eur Urol, 2021, 79(2): 243-262. DOI: 10.1016/j.eururo.2020.09.042.
[3]
CARROLL P H, MOHLER J L. NCCN guidelines updates: prostate cancer and prostate cancer early detection[J]. J Natl Compr Canc Netw, 2018, 16(5S): 620-623. DOI: 10.6004/jnccn.2018.0036.
[4]
ANDRIOLE G L, CRAWFORD E D, GRUBB R L, et al. Mortality results from a randomized prostate-cancer screening trial[J]. N Engl J Med, 2009, 360(13): 1310-1319. DOI: 10.1056/NEJMoa0810696.
[5]
LOWRANCE W T, BREAU R H, CHOU R, et al. Advanced prostate cancer: AUA/ASTRO/SUO guideline PART I[J]. J Urol, 2021, 205(1): 14-21. DOI: 10.1097/JU.0000000000001375.
[6]
BJURLIN M A, MENG X S, NOBIN J L, et al. Optimization of prostate biopsy: the role of magnetic resonance imaging targeted biopsy in detection, localization and risk assessment[J]. J Urol, 2014, 192(3): 648-658. DOI: 10.1016/j.juro.2014.03.117.
[7]
HAMOEN E H J, ROOIJ M D, WITJES J A, et al. Use of the prostate imaging reporting and data system (PI-RADS) for prostate cancer detection with multiparametric magnetic resonance imaging: a diagnostic meta-analysis[J]. Eur Urol, 2015, 67(6): 1112-1121. DOI: 10.1016/j.eururo.2014.10.033.
[8]
MICHAELY H J, ARINGHIERI G, CIONI D, et al. Current value of biparametric prostate MRI with machine-learning or deep-learning in the detection, grading, and characterization of prostate cancer: a systematic review[J/OL]. Diagnostics, 2022, 12(4): 799 [2023-06-15]. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9027206/. DOI: 10.3390/diagnostics12040799.
[9]
ALABOUSI M, SALAMEH J P, GUSENBAUER K, et al. Biparametric vs multiparametric prostate magnetic resonance imaging for the detection of prostate cancer in treatment-naïve patients: a diagnostic test accuracy systematic review and meta-analysis[J]. BJU Int, 2019, 124(2): 209-220. DOI: 10.1111/bju.14759.
[10]
GONG L X, XU M, FANG M J, et al. Noninvasive prediction of high-grade prostate cancer via biparametric MRI radiomics[J]. J Magn Reson Imaging, 2020, 52(4): 1102-1109. DOI: 10.1002/jmri.27132.
[11]
TURKBEY B, ROSENKRANTZ A B, HAIDER M A, et al. Prostate Imaging Reporting and Data System Version 2.1: 2019 Update of Prostate Imaging Reporting and Data System Version 2[J]. Eur Urol, 2019, 76(3): 340-351. DOI: 10.1016/j.eururo.2019.02.033.
[12]
TAN S X, ZHANG Y Y, WANG S, et al. Comparison of the diagnostic value of prostate imaging reporting and data system version 2 and version 2.1 in the detection of clinically significant prostate cancer[J]. Chin J Radiol, 2021, 55(2): 160-165. DOI: 10.3760/cma.j.cn112149-20200212-00144.
[13]
ROSENKRANTZ A B, GINOCCHIO L A, CORNFELD D, et al. Interobserver reproducibility of the PI-RADS version 2 lexicon: a multicenter study of six experienced prostate radiologists[J]. Radiology, 2016, 280(3): 793-804. DOI: 10.1148/radiol.2016152542.
[14]
ROSENKRANTZ A B, LIM R P, HAGHIGHI M, et al. Comparison of interreader reproducibility of the prostate imaging reporting and data system and likert scales for evaluation of multiparametric prostate MRI[J]. AJR Am J Roentgenol, 2013, 201(4): W612-W618. DOI: 10.2214/AJR.12.10173.
[15]
SMITH C P, HARMON S A, BARRETT T, et al. Intra- and interreader reproducibility of PI-RADSv2: a multireader study[J]. J Magn Reson Imaging, 2019, 49(6): 1694-1703. DOI: 10.1002/jmri.26555.
[16]
LAMBIN P, RIOS-VELAZQUEZ E, LEIJENAAR R, et al. Radiomics: extracting more information from medical images using advanced feature analysis[J]. Eur J Cancer, 2012, 48(4): 441-446. DOI: 10.1016/j.ejca.2011.11.036.
[17]
ZHANG H, LI X L, ZHANG Y X, et al. Diagnostic nomogram based on intralesional and perilesional radiomics features and clinical factors of clinically significant prostate cancer[J]. J Magn Reson Imaging, 2021, 53(5): 1550-1558. DOI: 10.1002/jmri.27486.
[18]
QIAO X M, HU C H, HU S, et al. The value of machine learning models based on biparametric MRI for diagnosis of prostate cancer and clinically significant prostate cancer[J]. Natl Med J China, 2023, 103(19): 1446-1454. DOI: 10.3760/cma.j.cn112137-20221018-02174.
[19]
CASTIGLIONI I, RUNDO L, CODARI M, et al. AI applications to medical images: from machine learning to deep learning[J]. Phys Med, 2021, 83: 9-24. DOI: 10.1016/j.ejmp.2021.02.006.
[20]
WU H C, BIAN Y, SHAO C W. The applicationof deep learning combined with MRI in evaluation of prostate cancer[J]. Int J Med Radiol, 2023, 46(3): 317-321. DOI: 10.19300/j.2023.Z20163.
[21]
SCHELB P, KOHL S, RADTKE J P, et al. Classification of cancer at prostate MRI: deep learning versus clinical PI-RADS assessment[J]. Radiology, 2019, 293(3): 607-617. DOI: 10.1148/radiol.2019190938.
[22]
ZHU L N, HAN C, LIU X, et al. U-Net deep learning network for automatic segmentation and localization of prostate cancer on MRI apparent diffusion coefficient map[J]. Chin J Radiol, 2020, 54(10): 974-979. DOI: 10.3760/cma.j.cn112149-20191004-00745.
[23]
VAN LEENDERS G J L H, VAN DER KWAST T H, GRIGNON D J, et al. The 2019 international society of urological pathology (ISUP) consensus conference on grading of prostatic carcinoma[J/OL]. Am J Surg Pathol, 2020, 44(8): e87-e99 [2023-06-15]. https://pubmed.ncbi.nlm.nih.gov/32459716/. DOI: 10.1097/PAS.0000000000001497.
[24]
GILLIES R J, KINAHAN P E, HRICAK H. Radiomics: images are more than pictures, they are data[J]. Radiology, 2016, 278(2): 563-577. DOI: 10.1148/radiol.2015151169.
[25]
HECTORS S J, CHEN C, CHEN J, et al. Magnetic resonance imaging radiomics-based machine learning prediction of clinically significant prostate cancer in equivocal PI-RADS 3 lesions[J]. J Magn Reson Imaging, 2021, 54(5): 1466-1473. DOI: 10.1002/jmri.27692.
[26]
LUNDERVOLD A S, LUNDERVOLD A. An overview of deep learning in medical imaging focusing on MRI[J]. Z Med Phys, 2019, 29(2): 102-127. DOI: 10.1016/j.zemedi.2018.11.002.
[27]
CASTILLO T J M, ARIF M, STARMANS M P A, et al. Classification of clinically significant prostate cancer on multi-parametric MRI: a validation study comparing deep learning and radiomics[J/OL]. Cancers, 2021, 14(1): 12 [2023-06-15]. https://www.ncbi.nlm.nih.gov/pmc/articles/pmid/35008177/. DOI: 10.3390/cancers14010012.
[28]
HUANG G, LIU Z, PLEISS G, et al. Convolutional networks with dense connectivity[J]. IEEE Trans Pattern Anal Mach Intell, 2022, 44(12): 8704-8716. DOI: 10.1109/TPAMI.2019.2918284.
[29]
ZHAO L T, BAO J, QIAO X M, et al. Predicting clinically significant prostate cancer with a deep learning approach: a multicentre retrospective study[J]. Eur J Nucl Med Mol Imaging, 2023, 50(3): 727-741. DOI: 10.1007/s00259-022-06036-9.
[30]
YAN Y, SHAO L Z, LIU Z Y, et al. Deep learning with quantitative features of magnetic resonance images to predict biochemical recurrence of radical prostatectomy: a multi-center study[J/OL]. Cancers, 2021, 13(12): 3098 [2023-06-15]. https://www.ncbi.nlm.nih.gov/pmc/articles/pmid/34205786/. DOI: 10.3390/cancers13123098.
[31]
LI S, WANG K X, LI J L, et al. AI-predicted mpMRI image features for the prediction of clinically significant prostate cancer[J]. Int Urol Nephrol, 2023, 55(11): 2703-2715. DOI: 10.1007/s11255-023-03722-x.
[32]
HOU Y, BAO J, SONG Y, et al. Integration of clinicopathologic identification and deep transferrable image feature representation improves predictions of lymph node metastasis in prostate cancer[J/OL]. EBioMedicine, 2021, 68: 103395 [2023-06-15]. https://www.ncbi.nlm.nih.gov/pmc/articles/pmid/34049247/. DOI: 10.1016/j.ebiom.2021.103395.

PREV To analyze the value of radiomics based on different diffusion model parameter maps in the early diagnosis of clinically significant prostate cancer by magnetic resonance imaging
NEXT Evaluation of the value of DWI combined with T2 mapping sequences to identify prostate cancer and benign prostatic hyperplasia
  


LINK


Tel & Fax: +8610-67113815    E-mail: editor@cjmri.cn