Стандартизированный алгоритм построения радиомических моделей МРТ для диагностики рака предстательной железы Grade Group ≥ 1 и ≥ 3: рекомендации на основе систематического обзора, метаанализа и оценки методологического качества (RQS/METRICS)

Цель исследования. На основе синтеза данных систематического обзора в рамках типовой методологии проведения метаанализов оценить текущее состояние разработки радиомических моделей, проанализировать источники методологической неоднородности и представить стандартизированный, доказательно обоснованный алгоритм для повышения качества и воспроизводимости будущих исследований.

Материалы и методы. Проведен систематический поиск в базах PubMed/MEDLINE, Embase, Scopus, Web of Science и Cochrane Library за период 01.2020–12.2025. Использовались ключевые слова, связанные с радиомикой, МРТ и раком поджелудочной железы (РПЖ). По критериям PICOS было отобрано 27 исследований (n = 5945 пациентов). Диагностическая эффективность оценена с помощью метаанализа (модель случайных эффектов), методологическое качество – по шкалам RQS и METRICS двумя независимыми рецензентами.

Результаты. Включено 27 исследований. Объединенная диагностическая эффективность радиомических моделей высокая (AUC = 0.847), однако отмечена существенная гетерогенность (I² = 70.32 %). Среднее качество по RQS составило 15,2 ± 3,4 (42,3 % от максимума), по METRICS – 67,5 ± 9,0 %. Выявлены системные методологические слабости: ретроспективный дизайн (96,3 %), отсутствие внешней валидации (77,8 %), анализа клинической полезности (70 %) и описания обработки пропущенных данных (100 %). Мета-регрессия показала, что высокий риск смещения приводит к завышению AUC (p = 0,009).

Заключение. Текущие высокие показатели эффективности радиомики РПЖ требуют осторожной интерпретации из-за методологических ограничений. Разработанный стандартизированный алгоритм, включающий рекомендации по проспективному дизайну, валидации, обработке данных и построению модели, представляет собой практическое методологическое руководство. Его внедрение может стать ключом к повышению методологической строгости, воспроизводимости и клинической трансляционной ценности будущих исследований в данной области.

1. Bray F, Laversanne M, Sung H, Ferlay J, Siegel RL, Soerjomataram I, Jemal A. Global cancer statistics 2022: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J Clin. 2024 May-Jun;74(3):229-263. https://doi.org/10.3322/caac.21834

2. Hamdy FC, Donovan JL, Lane JA, Mason M, Metcalfe C, Holding P, et al.; ProtecT Study Group. 10-Year Outcomes after Monitoring, Surgery, or Radiotherapy for Localized Prostate Cancer. N Engl J Med. 2016 Oct 13;375(15):1415-1424. https://doi.org/10.1056/nejmoa1606220

3. Klotz L, Zhang L, Lam A, Nam R, Mamedov A, Loblaw A. Clinical results of long-term follow-up of a large, active surveillance cohort with localized prostate cancer. J Clin Oncol. 2010 Jan 1;28(1):126-31. https://doi.org/10.1200/jco.2009.24.2180

4. Alessandrino F, Taghipour M, Hassanzadeh E, Ziaei A, Vangel M, Fedorov A, Tempany CM, Fennessy FM. Predictive role of PI-RADSv2 and ADC parameters in differentiating Gleason pattern 3 + 4 and 4 + 3 prostate cancer. Abdom Radiol (NY). 2019 Jan;44(1):279-285. https://doi.org/10.1007/s00261-018-1718-6

5. Westphalen AC, McCulloch CE, Anaokar JM, Arora S, Barashi NS, Barentsz JO, et al. Variability of the Positive Predictive Value of PI-RADS for Prostate MRI across 26 Centers: Experience of the Society of Abdominal Radiology Prostate Cancer Disease-focused Panel. Radiology. 2020 Jul;296(1):76-84. https://doi.org/10.1148/radiol.2020190646

6. Gillies RJ, Kinahan PE, Hricak H. Radiomics: Images Are More than Pictures, They Are Data. Radiology. 2016 Feb;278(2):563-77. https://doi.org/10.1148/radiol.2015151169

7. Aerts HJ, Velazquez ER, Leijenaar RT, Parmar C, Grossmann P, Carvalho S, et al. Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach. Nat Commun. 2014 Jun 3;5:4006. https://doi.org/10.1038/ncomms5006 Erratum in: Nat Commun. 2014;5:4644. Cavalho, Sara [corrected to Carvalho, Sara].

8. Tyan AS, Kаrmаzаnovsky GG, Karelskaya NA, Kondratyev EV, Gritskevich AА, Kalinin DV, et al. Category PI-RADS 3: the role of texture analysis in prostate cancer risk stratification (a systematic review). Digital Diagnostics. 2025;6(1):33-45. https://doi.org/10.17816/dd633500

9. Russo L, Bottazzi S, Kocak B, Zormpas-Petridis K, Gui B, Stanzione A, et al. Evaluating the quality of radiomics-based studies for endometrial cancer using RQS and METRICS tools. Eur Radiol. 2025 Jan;35(1):202-214. https://doi.org/10.1007/s00330-024-10947-6

10. Brancato V, Cerrone M, Garbino N, Salvatore M, Cavaliere C. Current status of magnetic resonance imaging radiomics in hepatocellular carcinoma: A quantitative review with Radiomics Quality Score. World J Gastroenterol. 2024 Jan 28;30(4):381-417. https://doi.org/10.3748/wjg.v30.i4.381

11. Lambin P, Leijenaar RTH, Deist TM, Peerlings J, de Jong EEC, van Timmeren J, et al. Radiomics: the bridge between medical imaging and personalized medicine. Nat Rev Clin Oncol. 2017 Dec;14(12):749-762. https://doi.org/10.1038/nrclinonc.2017.141

12. Kocak B, Akinci D'Antonoli T, Mercaldo N, Alberich-Bayarri A, Baessler B, Ambrosini I, et al. METhodological RadiomICs Score (METRICS): a quality scoring tool for radiomics research endorsed by EuSoMII. Insights Imaging. 2024 Jan 17;15(1):8. https://doi.org/10.1186/s13244-023-01572-w

13. Moher D, Liberati A, Tetzlaff J, Altman DG; PRISMA Group. Preferred reporting items for systematic reviews and meta-analyses: the PRISMA statement. BMJ. 2009 Jul 21;339:b2535. https://doi.org/10.1136/bmj.b2535

14. Woźnicki P, Westhoff N, Huber T, Riffel P, Froelich MF, Gresser E, et al. Multiparametric MRI for Prostate Cancer Characterization: Combined Use of Radiomics Model with PI-RADS and Clinical Parameters. Cancers (Basel). 2020 Jul 2;12(7):1767. https://doi.org/10.3390/cancers12071767

15. Li M, Yang L, Yue Y, Xu J, Huang C, Song B. Use of Radiomics to Improve Diagnostic Performance of PI-RADS v2.1 in Prostate Cancer. Front Oncol. 2021 Feb 17;10:631831. https://doi.org/10.3389/fonc.2020.631831

16. Hu L, Zhou DW, Fu CX, Benkert T, Jiang CY, Li RT, et al. Advanced zoomed diffusion-weighted imaging vs. full-field-of-view diffusion-weighted imaging in prostate cancer detection: a radiomic features study. Eur Radiol. 2021 Mar;31(3):1760-1769. https://doi.org/10.1007/s00330-020-07227-4

17. He D, Wang X, Fu C, Wei X, Bao J, Ji X, et al. MRI-based radiomics models to assess prostate cancer, extracapsular extension and positive surgical margins. Cancer Imaging. 2021 Jul 5;21(1):46. https://doi.org/10.1186/s40644-021-00414-6

18. Ji X, Zhang J, Shi W, He D, Bao J, Wei X, et al. Bi-parametric magnetic resonance imaging based radiomics for the identification of benign and malignant prostate lesions: cross-vendor validation. Phys Eng Sci Med. 2021 Sep;44(3):745-754. https://doi.org/10.1007/s13246-021-01022-1

19. Ayyad SM, Badawy MA, Shehata M, Alksas A, Mahmoud A, Abou El-Ghar M, et al. A New Framework for Precise Identification of Prostatic Adenocarcinoma. Sensors (Basel). 2022 Feb 26;22(5):1848. https://doi.org/10.3390/s22051848

20. Lu Y, Li B, Huang H, Leng Q, Wang Q, Zhong R, et al. Biparametric MRI-based radiomics classifiers for the detection of prostate cancer in patients with PSA serum levels of 4∼10 ng/mL. Front Oncol. 2022 Dec 5;12:1020317. https://doi.org/10.3389/fonc.2022.1020317

21. Gui S, Lan M, Wang C, Nie S, Fan B. Application Value of Radiomic Nomogram in the Differential Diagnosis of Prostate Cancer and Hyperplasia. Front Oncol. 2022 Apr 14;12:859625. https://doi.org/10.3389/fonc.2022.859625

22. Grajales Lopera DO, Picot F, Shams R, Dallaire F, Sheehy G, Alley S, et al. Image-guided Raman spectroscopy navigation system to improve transperineal prostate cancer detection. Part 2: in-vivo tumor-targeting using a classification model combining spectral and MRI-radiomics features. J Biomed Opt. 2022 Sep;27(9):095004. https://doi.org/10.1117/1.jbo.27.9.095004

23. Ma L, Zhou Q, Yin H, Ang X, Li Y, Xie G, Li G. Texture analysis based on PI-RADS 4/5-scored magnetic resonance images combined with machine learning to distinguish benign lesions from prostate cancer. Transl Cancer Res. 2022 May;11(5):1146-1161. https://doi.org/10.21037/tcr-21-2271

24. Jin P, Shen J, Yang L, Zhang J, Shen A, Bao J, Wang X. Machine learning-based radiomics model to predict benign and malignant PIRADS v2.1 category 3 lesions: a retrospective multi-center study. BMC Med Imaging. 2023 Mar 29;23(1):47. https://doi.org/10.1186/s12880-023-01002-9

25. Li C, Jin Z, Wei C, Dai G, Tu J, Shen J. Comparison in prostate cancer diagnosis with PSA 4-10 ng/mL: radiomics-based model VS. PIRADS v2.1. BMC Urol. 2024 Oct 23;24(1):233. https://doi.org/10.1186/s12894-024-01625-2

26. Zhou H, Xie M, Shi H, Shou C, Tang M, Zhang Y, et al. Integrating multimodal imaging and peritumoral features for enhanced prostate cancer diagnosis: A machine learning approach. PLoS One. 2025 May 15;20(5):e0323752. https://doi.org/10.1371/journal.pone.0323752

27. Jin L, Ma Z, Gao F, Li M, Li H, Geng D. Automated machine learning for prostate cancer detection and Gleason score prediction using T2WI: a diagnostic multi-center study. BMC Cancer. 2025 Oct 1;25(1):1483. https://doi.org/10.1186/s12885-025-14917-z

28. Lu Y, Yuan R, Su Y, Liang Z, Huang H, Leng Q, et al. Biparametric MRI-based radiomics for noninvastive discrimination of benign prostatic hyperplasia nodules (BPH) and prostate cancer nodules: a bio-centric retrospective cohort study. Sci Rep. 2025 Jan 3;15(1):654. https://doi.org/10.1038/s41598-024-84908-w

29. Zhang C, Wang Z, Shang P, Zhou Y, Zhu J, Xu L, Chen Z, Yu M, Zang Y. Combining multi-parametric MRI radiomics features with tumor abnormal protein to construct a machine learning-based predictive model for prostate cancer. Sci Rep. 2025 Jul 2;15(1):22816. https://doi.org/10.1038/s41598-025-05718-2

30. Chen Z, Xue Y, Zhang Z, Li W, Wen M, Zhao Y, et al. The performance of intravoxel-incoherent motion diffusion-weighted imaging derived hypoxia for the risk stratification of prostate cancer in peripheral zone. Eur J Radiol. 2020 Apr;125:108865. https://doi.org/10.1016/j.ejrad.2020.108865

31. Gugliandolo SG, Pepa M, Isaksson LJ, Marvaso G, Raimondi S, Botta F, et al. MRI-based radiomics signature for localized prostate cancer: a new clinical tool for cancer aggressiveness prediction? Sub-study of prospective phase II trial on ultra-hypofractionated radiotherapy (AIRC IG-13218). Eur Radiol. 2021 Feb;31(2):716-728. https://doi.org/10.1007/s00330-020-07105-z

32. Han C, Ma S, Liu X, Liu Y, Li C, Zhang Y, Zhang X, Wang X. Radiomics Models Based on Apparent Diffusion Coefficient Maps for the Prediction of High-Grade Prostate Cancer at Radical Prostatectomy: Comparison With Preoperative Biopsy. J Magn Reson Imaging. 2021 Dec;54(6):1892-1901. https://doi.org/10.1002/jmri.27565

33. Kang Z, Xu A, Wang L. Predictive role of T2WI and ADC-derived texture parameters in differentiating Gleason score 3+4 and 4+3 prostate cancer. J Xray Sci Technol. 2021;29(2):307-315. https://doi.org/10.3233/xst-200785

34. Bertelli E, Mercatelli L, Marzi C, Pachetti E, Baccini M, Barucci A, et al. Machine and Deep Learning Prediction Of Prostate Cancer Aggressiveness Using Multiparametric MRI. Front Oncol. 2022 Jan 13;11:802964. https://doi.org/10.3389/fonc.2021.802964

35. Urakami A, Arimura H, Takayama Y, Kinoshita F, Ninomiya K, Imada K, et al. Stratification of prostate cancer patients into low- and high-grade groups using multiparametric magnetic resonance radiomics with dynamic contrast-enhanced image joint histograms. Prostate. 2022 Feb;82(3):330-344. https://doi.org/10.1002/pros.24278

36. Zhuang H, Chatterjee A, Fan X, Qi S, Qian W, He D. A radiomics based method for prediction of prostate cancer Gleason score using enlarged region of interest. BMC Med Imaging. 2023 Dec 8;23(1):205. https://doi.org/10.1186/s12880-023-01167-3

37. Gao Z, Xu X, Sun H, Li T, Ding W, Duan Y, Tang L, Gu Y. The value of synthetic magnetic resonance imaging in the diagnosis and assessment of prostate cancer aggressiveness. Quant Imaging Med Surg. 2024 Aug 1;14(8):5473-5489. https://doi.org/10.21037/qims-24-291

38. Nicoletti G, Mazzetti S, Maimone G, Cignini V, Cuocolo R, Faletti R, et al. Development and Validation of an Explainable Radiomics Model to Predict High-Aggressive Prostate Cancer: A Multicenter Radiomics Study Based on Biparametric MRI. Cancers (Basel). 2024 Jan 1;16(1):203. https://doi.org/10.3390/cancers16010203

39. Wang K, Luo N, Sun Z, Zhao X, She L, Xing Z, et al. Evaluating the feasibility of AI-predicted bpMRI image features for predicting prostate cancer aggressiveness: a multi-center study. Insights Imaging. 2025 Jan 15;16(1):20. https://doi.org/10.1186/s13244-024-01865-8

40. Shibayama Y, Arimura H, Takayama Y, Kinoshita F, Takamatsu D, Nishie A, et al. Explainable radiomics based on association of histopathological cell density and multiparametric MR radiomic features for high-risk stratification of prostate cancer patients. MAGMA. 2025 Oct;38(5):803-815. https://doi.org/10.1007/s10334-025-01250-6

41. Aghakhanyan G, Filidei T, Febi M, Fanni SC, Marciano A, Francischello R, et al. Advancing Pediatric Sarcomas through Radiomics: A Systematic Review and Prospective Assessment Using Radiomics Quality Score (RQS) and Methodological Radiomics Score (METRICS). Diagnostics (Basel). 2024 Apr 17;14(8):832. https://doi.org/10.3390/diagnostics14080832

42. Gitto S, Cuocolo R, Klontzas ME, Albano D, Messina C, Sconfienza LM. Quality appraisal of radiomics-based studies on chondrosarcoma using METhodological RadiomICs Score (METRICS) and Radiomics Quality Score (RQS). Insights Imaging. 2025 Jun 18;16(1):129. https://doi.org/10.1186/s13244-025-02016-3

43. Kocak B, Mese I, Ates Kus E. Radiomics for differentiating radiation-induced brain injury from recurrence in gliomas: systematic review, meta-analysis, and methodological quality evaluation using METRICS and RQS. Eur Radiol. 2025 Aug;35(8):4490-4505. https://doi.org/10.1007/s00330-025-11401-x