Share：
Share this content in WeChat
X
[Chinese][PDF]1383
• Clinical Article •
Predicting malignancy of PI-RADS 4-5 lesions with radiomics features based on multiparametric magnetic resonance imaging
ZHU Li  MENG Jie  WANG Huanhuan  LI Danyan 

Cite this article as: ZHU L, MENG J, WANG H H, et al. Predicting malignancy of PI-RADS 4-5 lesions with radiomics features based on multiparametric magnetic resonance imaging[J]. Chin J Magn Reson Imaging, 2024, 15(4): 93-98, 119. DOI:10.12015/issn.1674-8034.2024.04.015.


[Abstract] Objective This study was aimed to distinguish benign and malignant prostate lesions prostate imaging reporting and data system (PI-RADS) 4-5 scored using multiparametric MRI (mpMRI) combined with imaging radiomics, and to construct a diagnostic model for predicting malignancy of prostate lesions scored PI-RADS 4-5.Materials and Methods Clinical, pathological and imaging data of patients who underwent prostate mpMRI examination and scored PI-RADS 4-5 in our hospital from January 2018 to June 2021 were retrospectively collected. A total of 135 patients were enrolled, including 64 benign and 71 malignant cases. They were then randomly divided into training set (n=95, 45 benign cases, 50 malignant cases) and test set (n=40, 19 benign cases, 21 malignant cases). Different radiomics models were used for identification.Results Higher apparent diffusion coefficient (ADC) value and lower total prostate specific antigen (tPSA) concentration were observed in benign group. ADC values in benign and malignant groups were (0.791±0.149) and (0.612±0.110) ×10-3 mm2/s, respectively, with cut-off value of 0.712×10-3 mm2/s, area under the curve (AUC) values in training set and test set were 0.870 and 0.772, respectively. The AUC of radiomics model based on mpMRI [ADC, diffusion weighted imaging (DWI) and T2WI] in training set and test set was 0.942 and 0.850, respectively. The AUC of multimodal radiomics model combined ADC value and radiomics score (Radscore) in the training set and test set was 0.952 and 0.842, respectively.Conclusions Traditional mpMRI parameters combined with imaging features did great job in identifying benign and malignant prostate PI-RADS 4-5 lesions, which shows immense potential in further clinical practice by assisting the formulation of subsequent individual treatment strategies.
[Keywords] prostate cancer；radiomics；magnetic resonance imaging；prostate imaging reporting and data system

ZHU Li   MENG Jie   WANG Huanhuan   LI Danyan*  

Department of Radiology, Nanjing Drum Tower Hospital, The Affiliated Hospital of Nanjing University Medical School, Nanjing 210009, China

Corresponding author: LI D Y, E-mail: lidanyan1982@163.com

Conflicts of interest   None.

Received  2023-12-15
Accepted  2024-03-22
DOI: 10.12015/issn.1674-8034.2024.04.015
Cite this article as: ZHU L, MENG J, WANG H H, et al. Predicting malignancy of PI-RADS 4-5 lesions with radiomics features based on multiparametric magnetic resonance imaging[J]. Chin J Magn Reson Imaging, 2024, 15(4): 93-98, 119. DOI:10.12015/issn.1674-8034.2024.04.015.

[1]
SMITH C P, TÜRKBEY B. PI-RADS v2: current standing and future outlook[J]. Turk J Urol, 2018, 44(3): 189-194. DOI: 10.5152/tud.2018.12144.
[2]
SIEGEL R L, MILLER K D, JEMAL A. Cancer statistics, 2016[J]. CA A Cancer J Clin, 2016, 66(1): 7-30. DOI: 10.3322/caac.21332.
[3]
BARRETT T, RAJESH A, ROSENKRANTZ A B, et al. PI-RADS version 2.1: one small step for prostate MRI[J]. Clin Radiol, 2019, 74(11): 841-852. DOI: 10.1016/j.crad.2019.05.019.
[4]
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.
[5]
DUTRUEL S P, JEPH S, MARGOLIS D J A, et al. PI-RADS: what is new and how to use it[J]. Abdom Radiol, 2020, 45(12): 3951-3960. DOI: 10.1007/s00261-020-02482-x.
[6]
KOZEL Z, MARTIN C, MIKHAIL D, et al. Initial experience and cancer detection rates of office-based transperineal magnetic resonance imaging-ultrasound fusion prostate biopsy under local anesthesia[J/OL]. J De L'association Des Urol Du Can, 2022, 16(7): E350-E356 [2024-03-13]. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9328860. DOI: 10.5489/cuaj.7472.
[7]
MEHRALIVAND S, BEDNAROVA S, SHIH J H, et al. Prospective evaluation of PI-RADS™ version 2 using the international society of urological pathology prostate cancer grade group system[J]. J Urol, 2017, 198(3): 583-590. DOI: 10.1016/j.juro.2017.03.131.
[8]
CROCETTO F, BARONE B, LUCA L D, et al. Granulomatous prostatitis: a challenging differential diagnosis to take into consideration[J]. Future Oncol, 2020, 16(13): 805-806. DOI: 10.2217/fon-2020-0185.
[9]
CUOCOLO R, CIPULLO M B, STANZIONE A, et al. Machine learning applications in prostate cancer magnetic resonance imaging[J/OL]. Eur Radiol Exp, 2019, 3(1): 35 [2024-03-13]. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6686027. DOI: 10.1186/s41747-019-0109-2.
[10]
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.
[11]
ZHANG X, SU G H, CHEN Y, et al. Decoding Intratumoral Heterogeneity: clinical Potential of Habitat Imaging based on Radiomics[J/OL]. Radiology, 2023, 309(3): e232047 [2024-03-13]. https://pubmed.ncbi.nlm.nih.gov/38085080. DOI: 10.1148/radiol.232047.
[12]
SUN Y, REYNOLDS H M, PARAMESWARAN B, et al. Multiparametric MRI and radiomics in prostate cancer: a review[J]. Australas Phys Eng Sci Med, 2019, 42(1): 3-25. DOI: 10.1007/s13246-019-00730-z.
[13]
PONSIGLIONE A, GAMBARDELLA M, STANZIONE A, et al. Radiomics for the identification of extraprostatic extension with prostate MRI: a systematic review and meta-analysis[J/OL]. Eur Radiol, 2023 [2024-03-13]. https://pubmed.ncbi.nlm.nih.gov/37955670. DOI: 10.1007/s00330-023-10427-3.
[14]
STRÖM P, KARTASALO K, OLSSON H, et al. Artificial intelligence for diagnosis and grading of prostate cancer in biopsies: a population-based, diagnostic study[J]. Lancet Oncol, 2020, 21(2): 222-232. DOI: 10.1016/S1470-2045(19)30738-7.
[15]
NOTO B, EVESLAGE M, AUF DER SPRINGE K, et al. Robustness of apparent diffusion coefficient-based lymph node classification for diagnosis of prostate cancer metastasis[J/OL]. Eur Radiol, 2023 [2024-03-13]. https://pubmed.ncbi.nlm.nih.gov/38099965. DOI: 10.1007/s00330-023-10406-8.
[16]
CHEN T, LI M J, GU Y F, et al. Prostate cancer differentiation and aggressiveness: assessment with a radiomic-based model vs. PI-RADS v2[J]. J Magn Reson Imaging, 2019, 49(3): 875-884. DOI: 10.1002/jmri.26243.
[17]
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.
[18]
ZHAO Y Y, XIONG M L, LIU Y F, et al. Magnetic resonance imaging radiomics-based prediction of clinically significant prostate cancer in equivocal PI-RADS 3 lesions in the transitional zone[J/OL]. Front Oncol, 2023, 13: 1247682 [2024-03-13]. https://pubmed.ncbi.nlm.nih.gov/38074651. DOI: 10.3389/fonc.2023.1247682.
[19]
GAUDIANO C, MOTTOLA M, BIANCHI L, et al. An apparent diffusion coefficient-based machine learning model can improve prostate cancer detection in the grey area of the prostate imaging reporting and data system category 3: a single-centre experience[J/OL]. Cancers, 2023, 15(13): 3438 [2024-03-13]. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10340607. DOI: 10.3390/cancers15133438.
[20]
MOYA, MEIJER J, SCHUBERT S, et al. Assessment of miR-98-5p, miR-152-3p, miR-326 and miR-4289 expression as biomarker for prostate cancer diagnosis[J/OL]. Int J Mol Sci, 2019, 20(5): 1154 [2024-03-13]. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6429489. DOI: 10.3390/ijms20051154.
[21]
DJAVAN B, ZLOTTA A R, REMZI M, et al. Total and transition zone prostate volume and age: how do they affect the utility of PSA-based diagnostic parameters for early prostate cancer detection?[J]. Urology, 1999, 54(5): 846-852. DOI: 10.1016/s0090-4295(99)00329-5.
[22]
WANG Z B, WEI C G, ZHANG Y Y, et al. The role of PSA density among PI-RADS v2.1 categories to avoid an unnecessary transition zone biopsy in patients with PSA 4-20 ng/mL[J/OL]. Biomed Res Int, 2021, 2021: 3995789 [2024-03-13]. https://pubmed.ncbi.nlm.nih.gov/34671673/. DOI: 10.1155/2021/3995789.
[23]
WEI X T, XU J M, ZHONG S Y, et al. Diagnostic value of combining PI-RADS v2.1 with PSAD in clinically significant prostate cancer[J]. Abdom Radiol, 2022, 47(10): 3574-3582. DOI: 10.1007/s00261-022-03592-4.
[24]
ZHANG K S, SCHELB P, KOHL S, et al. Improvement of PI-RADS-dependent prostate cancer classification by quantitative image assessment using radiomics or mean ADC[J]. Magn Reson Imaging, 2021, 82: 9-17. DOI: 10.1016/j.mri.2021.06.013.
[25]
BALIYAN V, DAS C J, SHARMA R, et al. Diffusion weighted imaging: technique and applications[J]. World J Radiol, 2016, 8(9): 785-798. DOI: 10.4329/wjr.v8.i9.785.
[26]
PENG Y H, JIANG Y L, YANG C, et al. Quantitative analysis of multiparametric prostate MR images: differentiation between prostate cancer and normal tissue and correlation with Gleason score: a computer-aided diagnosis development study[J]. Radiology, 2013, 267(3): 787-796. DOI: 10.1148/radiol.13121454.
[27]
DONATI O F, MAZAHERI Y, AFAQ A, et al. Prostate cancer aggressiveness: assessment with whole-lesion histogram analysis of the apparent diffusion coefficient[J]. Radiology, 2014, 271(1): 143-152. DOI: 10.1148/radiol.13130973.
[28]
JORDAN E J, FISKE C, ZAGORIA R, et al. PI-RADS v2 and ADC values: is there room for improvement?[J]. Abdom Radiol, 2018, 43(11): 3109-3116. DOI: 10.1007/s00261-018-1557-5.
[29]
SMITH C P, CZARNIECKI M, MEHRALIVAND S, et al. Radiomics and radiogenomics of prostate cancer[J]. Abdom Radiol, 2019, 44(6): 2021-2029. DOI: 10.1007/s00261-018-1660-7.
[30]
CHRISTODOULOU E, MA J, COLLINS G S, et al. A systematic review shows no performance benefit of machine learning over logistic regression for clinical prediction models[J]. J Clin Epidemiol, 2019, 110: 12-22. DOI: 10.1016/j.jclinepi.2019.02.004.
[31]
LI M J, CHEN T, ZHAO W L, et al. Radiomics prediction model for the improved diagnosis of clinically significant prostate cancer on biparametric MRI[J]. Quant Imaging Med Surg, 2020, 10(2): 368-379. DOI: 10.21037/qims.2019.12.06.
[32]
WOŹNICKI P, WESTHOFF N, HUBER T, et al. Multiparametric MRI for prostate cancer characterization: combined use of radiomics model with PI-RADS and clinical parameters[J/OL]. Cancers, 2020, 12(7): 1767 [2024-03-13]. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7407326. DOI: 10.3390/cancers12071767.
[33]
SRIGLEY J R. Benign mimickers of prostatic adenocarcinoma[J]. Mod Pathol, 2004, 17(3): 328-348. DOI: 10.1038/modpathol.3800055.
[34]
BERTELLI E, ZANTONELLI G, CINELLI A, et al. Granulomatous prostatitis, the great mimicker of prostate cancer: can multiparametric MRI features help in this challenging differential diagnosis?[J/OL]. Diagnostics, 2022, 12(10): 2302 [2024-03-13]. https://pubmed.ncbi.nlm.nih.gov/36291991. DOI: 10.3390/diagnostics12102302.
[35]
LEE S M, WOLFE K, ACHER P, et al. Multiparametric MRI appearances of primary granulomatous prostatitis[J/OL]. Br J Radiol, 2019, 92(1098): 20180075 [2024-03-13]. https://pubmed.ncbi.nlm.nih.gov/30964700. DOI: 10.1259/bjr.20180075.

PREV The value of whole-volume ADC histogram analysis combined with ADC value in preoperatively prediction of tumor deposits in rectal cancer
NEXT Feasibility study of the MAGiC technique for quantitative assessment of primary osteoporosis
  


LINK


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