Clinical-radiomics combination model for predicting the short-term efficacy of bipolar transurethral enucleation of the prostate in patients with benign prostatic hyperplasia

Abstract

Background: Bipolar transurethral enucleation of the prostate (B-TUEP) is a well-established surgical treatment for benign prostatic hyperplasia (BPH); however, its efficacy may vary depending on patient characteristics. Magnetic resonance imaging (MRI) with radiomics analysis can offer comprehensive and quantitative information about prostate characteristics that may relate to surgical outcomes. This study aimed to explore the value of MRI and radiomics analysis in predicting the short-term efficacy of B-TUEP for BPH.

Materials and methods: A total of 137 patients with BPH who underwent B-TUEP at 2 institutions were included. Radiological features were measured in the MRIs, and the radiomics score was developed from 1702 radiomics features extracted from the prostate and transitional zone regions of interest. Three prediction models were developed and validated based on clinical-radiological features, radiomic features, and their combinations. The models were evaluated using the area under the receiver operating characteristic curve, calibration curve, and decision curve analysis.

Results: The combination model exhibited the highest area under curve in both the training set (0.838) and the external validation set (0.802), indicating superior predictive performance and robustness. Furthermore, the combination model demonstrated good calibration (p > 0.05) and optimal clinical utility. The combination model indicated that a higher maximum urine flow rate, lower transitional zone index, and higher radiomics score were associated with an increased risk of poor efficacy.

Conclusions: Magnetic resonance imaging with radiomic analysis can offer valuable insights for predicting the short-term efficacy of B-TUEP in patients with BPH. A combination model based on clinical and radiomics features can assist urologists in making more precise clinical decisions.

Keywords

Benign prostatic hyperplasia / Radiomics / Prediction model / Surgical efficacy / Transurethral enucleation of the prostate

Acknowledgments

None.

Statement of ethics

This study was conducted following approval from the Institutional Committee of the Sixth Affiliation Hospital of Sun Yat-sen University and the Institutional Committee of the Second Affiliated Hospital of Kunming Medical University. Given its retrospective nature, the necessity for obtaining informed consent from patients was waived. All procedures performed in this study involving human participants were in accordance with the ethical standards of the institutional and national research committee and with the 1964 Helsinki declaration and its later amendments or comparable ethical standards.

Conflict of interest statement

The authors declare that they have no conflicts of interest.

Funding source

This study was supported by a grant from the Basic and Applied Basic Research Foundation of Guangdong Province, China (grant no. 2019A1515010386).

Author contributions

TZ: Research design, data analysis and original draft writing;

ZM, JH: Data collection and analysis;

JW: performance of research;

YT, LY, WZ, BY, BM, JM: Providing resource and data collection;

HQ, DW: Project administration;

CY, JZ: Supervision and review;

JQ: Research design and editing.

Data availability

We would like to share the data collected for this study to investigators for individual participant data meta-analysis, including individual participant data that underlie the results reported in this article, after deidentification (text, tables, figures, and appendices). Data availability begins 9 months following article publication and ends 36 months following article publication. Proposals should be directed to [e-mail]. To gain access, data requestors will need to sign a data access agreement.

References

[1] Gravas S, Bach T, Drake M, et al. Management of non-neurogenic male lower urinary tract symptoms lastname (LUTS), incl. benign prostatic obstruction (BPO): EAU Guidelines. Proceedings of the EAU Annual Congress. Amsterdam, The Netherlands, 2022.

[2] Lerner LB, McVary KT, Barry MJ, et al. Management of lower urinary tract symptoms attributed to benign prostatic hyperplasia: AUA GUIDELINE PART I—Initial work-up and medical management. J Urol 2021; 206(4):806-817.

[3] Foo KT. What is a disease? What is the disease clinical benign prostatic hyperplasia (BPH)? World J Urol 2019; 37(7):1293-1296.

[4] Shim M, Bang WJ, Oh CY, Lee YS, Cho JS. Correlation between prostatic urethral angulation and symptomatic improvement after surgery in patients with lower urinary tract symptoms according to prostate size. World J Urol 2020; 38(8):1997-2003.

[5] Lu W-W, Zhang D, Ni X-J. A review of the role of ultrasound radiomics and its application and limitations in the investigation of thyroid disease. Med Sci Monit 2022;28:e937738.

[6] Turkbey B, Fotin SV, Huang RJ, et al. Fully automated prostate segmentation on MRI: Comparison with manual segmentation methods and specimen volumes. AJR Am J Roentgenol 2013; 201(5):W720-W729.

[7] Gillies RJ, Kinahan PE, Hricak H. Radiomics: Images are more than pictures, they are data. Radiology 2016; 278(2):563-577.

[8] Lambin P, Leijenaar RTH, Deist TM, et al. Radiomics: The bridge between medical imaging and personalized medicine. Nat Rev Clin Oncol 2017; 14(12):749-762.

[9] Suarez-Ibarrola R, Hein S, Reis G, Gratzke C, Miernik A. Current and future applications of machine and deep learning in urology: A review of the literature on urolithiasis, renal cell carcinoma, and bladder and prostate cancer. World J Urol 2020; 38(10):2329-2347.

[10] Tian Y, Zhang H, Cao Y, Yang L, Luo G. The P.R.OS.T.A.T.E nomogram for the preoperative prediction of clinical efficacy of transurethral resection of the prostate in benign prostatic hyperplasia patients. Clin Interv Aging 2022;17:845-855.

[11] Homma Y, Kawabe K, Tsukamoto T, et al. Estimate criteria for efficacy of treatment in benign prostatic hyperplasia. Int J Urol 1996; 3(4):267-273.

[12] Chen X, Man Q, Wei X, et al. Predictive value of preoperative comprehensive evaluation on the efficacy of HoLEP. Transl Androl Urol 2020; 9(4):1603-1610.

[13] Kaplan SA, Te AE, Pressler LB, Olsson CA. Transition zone index as a method of assessing benign prostatic hyperplasia: Correlation with symptoms, urine flow and detrusor pressure. J Urol 1995; 154(5):1764-1769.

[14] Ohtani T, Hayashi Y, Kishino TE, et al. A new parameter in decision making for transurethral electroresection of benign prostate hyperplasia. Eur Urol 1999; 35(3):185-191.

[15] Liu YF, Shu X, Qiao XF, et al. Radiomics-based machine learning models for predicting P504s/P63 immunohistochemical expression: A noninvasive diagnostic tool for prostate cancer. Front Oncol 2022;12:911426.

[16] Mühlbauer J, Egen L, Kowalewski KF, et al. Radiomics in renal cell carcinoma—A systematic review and meta-analysis. Cancers (Basel) 2021; 13(6):1348.

[17] Kozikowski M, Suarez-Ibarrola R, Osiecki R, et al. Role of radiomics in the prediction of muscle-invasive bladder cancer: A systematic review and meta-analysis. Eur Urol Focus 2022; 8(3):728-738.

[18] Lim EJ, Castellani D, So WZ, et al. Radiomics in urolithiasis: Systematic review of current applications, limitations, and future directions. J Clin Med 2022; 11(17):5151.

[19] Siroky MB, Olsson CA, Krane RJ. The flow rate nomogram: II. Clinical correlation. J Urol 1980; 123(2):208-210.

[20] Reynard JM, Yang Q, Donovan JL, et al. The ICS-'BPH' study: Uroflowmetry, lower urinary tract symptoms and bladder outlet obstruction. Br J Urol 1998; 82(5):619-623.

[21] Siroky MB, Olsson CA, Krane RJ. The flow rate nomogram: I. Development. J Urol 1979; 122(5):665-668.

[22] McNeal JE. Normal histology of the prostate. Am J Surg Pathol 1988; 12(8):619-633.

[23] McNeal JE, Redwine EA, Freiha FS, Stamey TA. Zonal distribution of prostatic adenocarcinoma. Correlation with histologic pattern and direction of spread. Am J Surg Pathol 1988; 12(12):897-906.

[24] Greene DR, Egawa S, Hellerstein DK, Scardino PT. Sonographic measurements of transition zone of prostate in men with and without benign prostatic hyperplasia. Urology 1990; 36(4):293-299.

[25] Roehrborn CG. Pathology of benign prostatic hyperplasia. Int J Impot Res 2008; 20(Suppl 3):S11-S18.

[26] Devlin CM, Simms MS, Maitland NJ. Benign prostatic hyperplasia — What do we know? BJU Int 2021; 127(4):389-399.

[27] Hamm CA, Baumgärtner GL, Biessmann F, et al. Interactive explainable deep learning model informs prostate cancer diagnosis at MRI. Radiology 2023; 307(4):e222276.

[28] Pandolfo SD, Del Giudice F, Chung BI, et al. Robotic assisted simple prostatectomy versus other treatment modalities for large benign prostatic hyperplasia: A systematic review and meta-analysis of over 6500 cases. Prostate Cancer Prostatic Dis 2023; 26(3):495-510.

[29] Autorino R, Amparore D, Loizzo D, Pandolfo SD, Checcucci E, Porpiglia F. Robot-assisted simple prostatectomy is better than endoscopic enucleation of the prostate. Eur Urol Focus 2022; 8(2):368-370.

[30] Ming Y, Qu H, Bertini E. RuleMatrix: Visualizing and understanding classifiers with rules. IEEE Trans Vis Comput Graph 2019; 25(1):342-352.

[31] Selvaraju RR, Cogswell M, Das A, et al. Grad-CAM: Visual explanations from deep networks via gradient-based localization. 2017 IEEE International Conference on Computer Vision (ICCV). Venice, Italy, October 22-29, 2017. pp. 618-626.