Diagnostic accuracy of artificial intelligence for the screening of prostate cancer in biparametric magnetic resonance imaging: a systematic review

Cover Image

Cite item

Full Text

Abstract

BACKGROUND: Based on the latest published data, 40,137 new cases of prostate cancer were reported in Russia in 2021, ranking second after lung cancer in men.

Thus, prostate cancer is one of the most common malignant neoplasms in men. Accurate and timely detection of prostate cancer is important under the current conditions.

AIM: This systematic review aimed to assess the quality of prediction models designed to detect prostate cancer during initial presentation.

MATERIALS AND METHODS: A systematic search was performed in eLibrary.ru, PubMed, Google Scholar, Web of Science, and ResearchGate for relevant publications indexed from January 2019 to September 2023 in accordance with the PRISMA protocol. Two authors independently assessed the relevant studies for potential inclusion or exclusion.

RESULTS: This systematic review meta-analysis included 21 studies. In total, data from 3,630 patients were analyzed, of which 47% had prostate cancer and 53% had benign prostate neoplasms. The mean age of the patients was 67.1 (36–90) years. In addition, 81% of the studies were based on T2-weighted imaging, 57% on diffusion-weighted imaging, and 76% on apparent diffusion coefficient. Moreover, 43% and 33% of the studies were dedicated to transition zone and prostate peripheral zone neoplasms, respectively, and 52% of the authors examined the whole prostate gland, without dividing it into zones. The most common machine-learning algorithms applied by the investigators were as follows: multiple logistic regression (76%), support vector machine (38%), and random forest (24%). Based on the meta-analysis performed for the receiver operating characteristic-area under the curve (ROC–AUC) assessment with random-effect approach in 73 prediction models described in the publications, the final ROC–AUC was 0.793 [95% CI 0.768–0.818], I2 = 86.71%, p <0.001. The most accurate prediction models were based on the T2-weighted imaging + apparent diffusion coefficients imaging protocol: 0.860 [95% CI 0.813–0.907], and models created according to the “white box” principle (0.834 [95% CI 0.806–0.861]) were more accurate than the “black box” ones (0.733 [95% CI 0.695–0.771]). The models using radiomics and clinical features were slightly more accurate than those using the radiomics parameters alone (0.869 [95% CI 0.844–0.895] vs. 0.779 [95% CI 0.751–0.807]). Model accuracy was nearly identical across transitional and/or peripheral zone studies.

CONCLUSIONS: Artificial intelligence demonstrated promising results. However, the clinical applicability may require more intensive expert inspection in healthcare institutions and evaluation of efficacy in prospective studies.

About the authors

Oksana V. Kryuchkova

Central Clinical Hospital, Office of the President of the Russian Federation

Email: ovk16@bk.ru
ORCID iD: 0000-0001-6483-2074
SPIN-code: 2445-3370

MD Cand. Sci. (Medicine)

Russian Federation, Moscow

Elena V. Schepkina

Russian Presidential Academy of National Economy and Public Administration; Research and Practical Clinical Center for Diagnostics and Telemedical Technologies; Editorial of the Journal “Pediatria” named after G.N. Speransky

Author for correspondence.
Email: elenaschepkina@gmail.com
ORCID iD: 0000-0002-2079-1482
SPIN-code: 2347-9436
Scopus Author ID: 57211515165
ResearcherId: IAR-4060-2023

Cand. Sci. (Sociology)

Russian Federation, Moscow; Moscow; Moscow

Natalia A. Rubtsova

P.A. Herzen Moscow Oncology Research Institute, Branch National Medical Research Radiological Center

Email: rna17@ya.ru
ORCID iD: 0000-0001-8378-4338
SPIN-code: 9712-9091

MD, Dr. Sci. (Medicine)

Russian Federation, Moscow

Boris Y. Alekseev

P.A. Herzen Moscow Oncology Research Institute, Branch National Medical Research Radiological Center

Email: byalekseev@mail.ru
ORCID iD: 0000-0002-3398-4128
SPIN-code: 4692-5705

MD, Dr. Sci. (Medicine)

Russian Federation, Moscow

Anton I. Kuznetsov

Moscow Aviation Institute

Email: drednout5786@yandex.ru
ORCID iD: 0000-0003-2182-5792
SPIN-code: 8824-9080
Russian Federation, Moscow

Svetlana V. Epifanova

Central Clinical Hospital, Office of the President of the Russian Federation; Research and Practical Clinical Center for Diagnostics and Telemedical Technologies

Email: svepifanova@yandex.ru
ORCID iD: 0000-0002-7591-5120
SPIN-code: 9067-5033

MD, Cand. Sci. (Medicine)

Russian Federation, Moscow; Moscow

Elena V. Zarya

Central Clinical Hospital, Office of the President of the Russian Federation

Email: zaryya@yandex.ru
ORCID iD: 0009-0001-4444-8881
SPIN-code: 9800-8219
Russian Federation, Moscow

Ali E. Talyshinskii

Saint Petersburg State University

Email: ali-ma@mail.ru
ORCID iD: 0000-0002-3521-8937
SPIN-code: 7747-0117

MD, Dr. Sci. (Medicine)

Russian Federation, Saint Petersburg

References

  1. Mottet N, van den Bergh RCN, 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. European urology. 2021;79(2):243–262. doi: 10.1016/j.eururo.2020.09.042
  2. Zdravookhranenie v Rossii, 2021: statisticheskii sbornik. Moscow: Rosstat; 2021.
  3. Verma S, Rajesh A. A Clinically Relevant Approach to Imaging Prostate Cancer: review. American Journal of Roentgenology. 2011;196(3 Suppl):S1–10 Quiz S11–4. doi: 10.2214/AJR.09.7196
  4. Girometti R, Giannarini G, Panebianco V, et al. Comparison of different thresholds of PSA density for risk stratification of PI-RADSv2.1 categories on prostate MRI. The British Journal of Radiology. 2022;95(1131):20210886. doi: 10.1259/bjr.20210886
  5. Niaf E, Lartizien C, Bratan F, et al. Prostate Focal Peripheral Zone Lesions: Characterization at Multiparametric MR Imaging–Influence of a Computer-aided Diagnosis System. Radiology. 2014;271(3):761–769. doi: 10.1148/radiol.14130448
  6. Drost FJH, Osses DF, Nieboer D, et al. Prostate MRI, with or without MRI-targeted biopsy, and systematic biopsy for detecting prostate cancer. Cochrane Database of Systematic Reviews. 2019;4(4):CD012663. doi: 10.1002/14651858.CD012663.pub2
  7. Goldenberg SL, Nir G, Salcudean SE. A new era: artificial intelligence and machine learning in prostate cancer. Nature Reviews Urology. 2019;16(7):391–403. doi: 10.1038/s41585-019-0193-3
  8. Cuocolo R, Cipullo MB, Stanzione A, et al. Machine learning applications in prostate cancer magnetic resonance imaging. European Radiology Experimental. 2019;3(1):35. doi: 10.1186/s41747-019-0109-2
  9. Ghezzo S, Bezzi C, Presotto L, et al. State of the art of radiomic analysis in the clinical management of prostate cancer: A systematic review. Critical Reviews in Oncology/Hematology. 2022;169:103544. doi: 10.1016/j.critrevonc.2021.103544
  10. Gelezhe PB, Blokhin IA, Semenov SS, Caruso D. Magnetic resonance imaging radiomics in prostate cancer radiology: what is currently known? Digital Diagnostics. 2021;2(4):441–452. doi: 10.17816/DD70170
  11. Ferro M, de Cobelli O, Vartolomei MD, et al. Prostate Cancer Radiogenomics–From Imaging to Molecular Characterization. International Journal of Molecular Sciences. 2021;22(18):9971. doi: 10.3390/ijms22189971
  12. Steyerberg EW, Vickers AJ, Cook NR, et al. Assessing the Performance of Prediction Models. Epidemiology. 2010;21(1):128–138. doi: 10.1097/EDE.0b013e3181c30fb2
  13. Higgins JPT, Green S, editors. The Cochrane Collaboration. Cochrane Handbook for Systematic Reviews of Interventions [Internet]. England: John Wiley & Sons Ltd. [cited 19 Mar 2020]. Available from: https://training.cochrane.org/handbook
  14. Higgins JPT, Thompson SG, Deeks JJ, Altman DG. Measuring inconsistency in meta-analyses. BMJ. 2003;327(7414):557–560. doi: 10.1136/bmj.327.7414.557
  15. DerSimonian R, Laird N. Meta-analysis in clinical trials. Controlled Clinical Trials. 1986;7(3):177–188. doi: 10.1016/0197-2456(86)90046-2
  16. 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. Cancers (Basel). 2020;12(7):1767. doi: 10.3390/cancers12071767
  17. Li M, Yang L, Yue Y, et al. Use of Radiomics to Improve Diagnostic Performance of PI-RADS v2.1 in Prostate Cancer. Frontiers in Oncology. 2021;10:631831. doi: 10.3389/fonc.2020.631831
  18. Gui S, Lan M, Wang C, et al. Application Value of Radiomic Nomogram in the Differential Diagnosis of Prostate Cancer and Hyperplasia. Frontiers in Oncology. 2022;12:859625. doi: 10.3389/fonc.2022.859625
  19. Lu Y, Li B, Huang H, et al. Biparametric MRI-based radiomics classifiers for the detection of prostate cancer in patients with PSA serum levels of 4~10 ng/mL. Frontiers in Oncology. 2022;12:1020317. doi: 10.3389/fonc.2022.1020317
  20. Zhou B, Liu X, Gan H, et al. Differentiation of Prostate Cancer and Stromal Hyperplasia in the Transition Zone With Monoexponential, Stretched-Exponential Diffusion-Weighted Imaging and Diffusion Kurtosis Imaging in a Reduced Number of b Values: Correlation With Whole-Mount Pathology. Journal of Computer Assisted Tomography. 2022;46(4):545–550. doi: 10.1097/RCT.0000000000001314
  21. Wu M, Krishna S, Thornhill RE, et al. Transition zone prostate cancer: Logistic regression and machine-learning models of quantitative ADC, shape and texture features are highly accurate for diagnosis. Journal of Magnetic Resonance Imaging. 2019;50(3):940–950. doi: 10.1002/jmri.26674
  22. Zhong JG, Shi L, Liu J, et al. Predicting prostate cancer in men with PSA levels of 4–10 ng/mL: MRI-based radiomics can help junior radiologists improve the diagnostic performance // Scientific reports. 2023;13(1):4846. doi: 10.1038/s41598-023-31869-1
  23. Ou YC, Chang KH, Tung MC, et al. Building a Nomogram for Prediction of Prostate Cancer in Patients With Preoperatively Suspected Prostate Cancer. Anticancer Research. 2020;40(5):2995–3002. doi: 10.21873/anticanres.14280
  24. McGarry SD, Bukowy JD, Iczkowski KA, et al. Gleason Probability Maps: A Radiomics Tool for Mapping Prostate Cancer Likelihood in MRI Space. Tomography. 2019;5(1):127–134. doi: 10.18383/j.tom.2018.00033
  25. Hu L, Zhou DW, Fu CX, et al. Advanced zoomed diffusion-weighted imaging vs. full-field-of-view diffusion-weighted imaging in prostate cancer detection: a radiomic features study. European radiology. 2021;31(3):1760–1769. doi: 10.1007/s00330-020-07227-4
  26. Ji X, Zhang J, Shi W, et al. Bi-parametric magnetic resonance imaging based radiomics for the identification of benign and malignant prostate lesions: cross-vendor validation. Physical and Engineering Sciences in Medicine. 2021;44(3):745–754. doi: 10.1007/s13246-021-01022-1
  27. Jin P, Shen J, Yang L, et al. Machine learning-based radiomics model to predict benign and malignant PI-RADS v2.1 category 3 lesions: a retrospective multi-center study. BMC Medical Imaging. 2023;23(1):47. doi: 10.1186/s12880-023-01002-9
  28. Li S, Zheng T, Fan Z, et al. A dynamic-static combination model based on radiomics features for prostate cancer using multiparametric MRI. Physics in Medicine & Biology. 2023;68(1):015008. doi: 10.1088/1361-6560/aca954
  29. Ayyad SM, Badawy MA, Shehata M, et al. A New Framework for Precise Identification of Prostatic Adenocarcinoma. Sensors. 2022;22(5):1848. doi: 10.3390/s22051848
  30. Han L, He G, Mei Y, et al. Combining Magnetic Resonance Diffusion-Weighted Imaging with Prostate-Specific Antigen to Differentiate Between Malignant and Benign Prostate Lesions. Medical Science Monitor. 2022;28:e935307. doi: 10.12659/MSM.935307
  31. Chen T, Li M, Gu Y, et al. Prostate Cancer Differentiation and Aggressiveness: Assessment With a Radiomic-Based Model vs. PI-RADS v2. Journal of Magnetic Resonance Imaging. 2019;49(3):875–884. doi: 10.1002/jmri.26243
  32. He D, Wang X, Fu C, et al. MRI-based radiomics models to assess prostate cancer, extracapsular extension and positive surgical margins. Cancer Imaging. 2021;21(1):46. doi: 10.1186/s40644-021-00414-6
  33. Jamshidi G, Abbasian Ardakani A, Ghafoori M, et al. Radiomics-based machine-learning method to diagnose prostate cancer using mp-MRI: a comparison between conventional and fused models. Magnetic Resonance Materials in Physics, Biology and Medicine. 2022;36(1):55–64. doi: 10.1007/s10334-022-01037-z
  34. Aussavavirojekul P, Hoonlor A, Srinualnad S. Optimization of clinical risk-factor interpretation and radiological findings with machine learning for PIRADS category 3 patients. Prostate. 2022;82(2):235–244. doi: 10.1002/pros.24266
  35. Giambelluca D, Cannella R, Vernuccio F, et al. PI-RADS 3 Lesions: Role of Prostate MRI Texture Analysis in the Identification of Prostate Cancer. Current Problems in Diagnostic Radiology. 2021;50(2):175–185. doi: 10.1067/j.cpradiol.2019.10.009
  36. Viswanath SE, Chirra PV, Yim MC, et al. Comparing radiomic classifiers and classifier ensembles for detection of peripheral zone prostate tumors on T2-weighted MRI: a multi-site study. BMC Medical Imaging. 2019;19(1):22. doi: 10.1186/s12880-019-0308-6
  37. Chawla NV, Bowyer KW, Hall LO, Kegelmeyer WP. SMOTE: Synthetic Minority Over-sampling Technique. Journal of Artificial Intelligence Research. 2002;16(1):321–357.
  38. Dai JC, Morgan TN, Goueli R, et al. MRI Features Associated with Histology of Benign Prostatic Hyperplasia Nodules: Generation of a Predictive Model. Journal of Endourology. 2022;36(3):381–386. doi: 10.1089/end.2021.0397
  39. Liu 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. Scientific reports. 2020;10(1):5157. doi: 10.1038/s41598-020-62015-w
  40. Zhang L, Tang M, Chen S, et al. A meta-analysis of use of Prostate Imaging Reporting and Data System Version 2 (PI-RADS V2) with multiparametric MR imaging for the detection of prostate cancer. European radiology. 2017;27(12):5204–5214. doi: 10.1007/s00330-017-4843-7
  41. Zhen L, Liu X, Yegang C, et al. Accuracy of multiparametric magnetic resonance imaging for diagnosing prostate Cancer: a systematic review and meta-analysis. BMC Cancer. 2019;19(1):1244. doi: 10.1186/s12885-019-6434-2

Supplementary files

Supplementary Files
Action
1. JATS XML
Download
2. Fig. 1. Flow chart of the publication review and study selection process. PCa – prostate cancer; MO – machine learning; MRI – magnetic resonance imaging; DCE (Dynamic Contrast Enhanced) – dynamic contrast enhancement; ROC-AUC – area under the ROC curve.

Download (329KB)
Indexing metadata
3. Fig. 2. The share of machine learning algorithms used in studies. MLR — Multiple Logistic Regression; SVM — Support Vector Machine; RF — Random Forest; LDA — Linear Discriminant Analysis; DT — Decision Tree; NB — Naive Bayesian; KNN — K Nearest Neighbors; CNN — Convolutional Neural Network; XGB — eXtreme Gradient Boosting; QAD — Quadratic Discriminant Analysis.

Download (108KB)
Indexing metadata
4. Fig. 3. Blobogram of individual prognostic models for the pooled area under the curve (ROC-AUC) and 95% confidence interval of the prostate cancer characteristic. Horizontal lines represent the 95% confidence interval of the point estimates. Each solid rectangle represents the ROC-AUC value of individual models, and the size of the rectangle indicates the study weight. The diamond represents the pooled ROC-AUC value of all 73 models in 21 studies. The dotted line represents the mean ROC-AUC value. TZ, transition zone; PZ, peripheral zone, PZ-TZ, peripheral and transition zones.

Download (1MB)
Indexing metadata
5. Fig. 4. Blobogram of individual prognostic models for pooled area under the curve (ROC-AUC) and 95% confidence interval of prostate cancer performance. Horizontal lines represent 95% confidence interval of point estimates. Each solid rectangle represents the ROC-AUC value of individual models, and the size of the rectangle indicates the study weight. Diamond represents the pooled ROC-AUC value of all 73 models in 21 studies. Dashed line represents the mean ROC-AUC value. TZ, transition zone; PZ, peripheral zone, PZ-TZ 0151 peripheral and transition zones. T2WI, T2-weighted images, DWI, diffusion-weighted images, ADC, measured diffusion coefficients.

Download (871KB)
Indexing metadata

Copyright (c) 2024 Eco-Vector

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Согласие на обработку персональных данных с помощью сервиса «Яндекс.Метрика»

1. Я (далее – «Пользователь» или «Субъект персональных данных»), осуществляя использование сайта https://journals.rcsi.science/ (далее – «Сайт»), подтверждая свою полную дееспособность даю согласие на обработку персональных данных с использованием средств автоматизации Оператору - федеральному государственному бюджетному учреждению «Российский центр научной информации» (РЦНИ), далее – «Оператор», расположенному по адресу: 119991, г. Москва, Ленинский просп., д.32А, со следующими условиями.

2. Категории обрабатываемых данных: файлы «cookies» (куки-файлы). Файлы «cookie» – это небольшой текстовый файл, который веб-сервер может хранить в браузере Пользователя. Данные файлы веб-сервер загружает на устройство Пользователя при посещении им Сайта. При каждом следующем посещении Пользователем Сайта «cookie» файлы отправляются на Сайт Оператора. Данные файлы позволяют Сайту распознавать устройство Пользователя. Содержимое такого файла может как относиться, так и не относиться к персональным данным, в зависимости от того, содержит ли такой файл персональные данные или содержит обезличенные технические данные.

3. Цель обработки персональных данных: анализ пользовательской активности с помощью сервиса «Яндекс.Метрика».

4. Категории субъектов персональных данных: все Пользователи Сайта, которые дали согласие на обработку файлов «cookie».

5. Способы обработки: сбор, запись, систематизация, накопление, хранение, уточнение (обновление, изменение), извлечение, использование, передача (доступ, предоставление), блокирование, удаление, уничтожение персональных данных.

6. Срок обработки и хранения: до получения от Субъекта персональных данных требования о прекращении обработки/отзыва согласия.

7. Способ отзыва: заявление об отзыве в письменном виде путём его направления на адрес электронной почты Оператора: info@rcsi.science или путем письменного обращения по юридическому адресу: 119991, г. Москва, Ленинский просп., д.32А

8. Субъект персональных данных вправе запретить своему оборудованию прием этих данных или ограничить прием этих данных. При отказе от получения таких данных или при ограничении приема данных некоторые функции Сайта могут работать некорректно. Субъект персональных данных обязуется сам настроить свое оборудование таким способом, чтобы оно обеспечивало адекватный его желаниям режим работы и уровень защиты данных файлов «cookie», Оператор не предоставляет технологических и правовых консультаций на темы подобного характера.

9. Порядок уничтожения персональных данных при достижении цели их обработки или при наступлении иных законных оснований определяется Оператором в соответствии с законодательством Российской Федерации.

10. Я согласен/согласна квалифицировать в качестве своей простой электронной подписи под настоящим Согласием и под Политикой обработки персональных данных выполнение мною следующего действия на сайте: https://journals.rcsi.science/ нажатие мною на интерфейсе с текстом: «Сайт использует сервис «Яндекс.Метрика» (который использует файлы «cookie») на элемент с текстом «Принять и продолжить».