Evaluating the Feasibility of AI-predicted BpMRI Image Features for Predicting Prostate Cancer Aggressiveness: a Multi-center Study

Overview

Journal Insights Imaging

Publisher Springer

Date 2025 Jan 15

PMID 39812752

Authors

Kexin Wang

Ning Luo

Zhaonan Sun

Xiangpeng Zhao

Lilan She

Zhangli Xing

Yuntian Chen

Chunlei He

Pengsheng Wu

Xiangpeng Wang

ZiXuan Kong

Affiliations

Soon will be listed here.

Abstract

Objective: To evaluate the feasibility of utilizing artificial intelligence (AI)-predicted biparametric MRI (bpMRI) image features for predicting the aggressiveness of prostate cancer (PCa).

Materials And Methods: A total of 878 PCa patients from 4 hospitals were retrospectively collected, all of whom had pathological results after radical prostatectomy (RP). A pre-trained AI algorithm was used to select suspected PCa lesions and extract lesion features for model development. The study evaluated five prediction methods, including (1) A clinical-imaging model of clinical features and image features of suspected PCa lesions selected by AI algorithm, (2) the PIRADS category, (3) a conventional radiomics model, (4) a deep-learning bases radiomics model, and (5) biopsy pathology.

Results: In the externally validated dataset, the deep learning-based radiomics model showed the highest area under the curve (AUC 0.700 to 0.791). It exceeded the clinical-imaging model (AUC 0.597 to 0.718), conventional radiomic model (AUC 0.566 to 0.632), PIRADS score (AUC 0.554 to 0.613), and biopsy pathology (AUC 0.537 to 0.578). The AUC predicted by the model did not show a statistically significant difference among the three externally verified hospitals (p > 0.05).

Conclusion: Deep-learning radiomics models utilizing AI-extracted image features from bpMRI images can potentially be used to predict PCa aggressiveness, demonstrating a generalized ability for external validation.

Critical Relevance Statement: Predicting the aggressiveness of prostate cancer (PCa) is important for formulating the best treatment plan for patients. The radiomic model based on deep learning is expected to provide an objective and non-invasive method for evaluating the aggressiveness of PCa.

Key Points: Predicting the aggressiveness of PCa is important for patients to obtain the best treatment options. The deep learning-based radiomics model can predict the aggressiveness of PCa with high accuracy. The model has good universality when tested on multiple external datasets.

References

Nketiah G, Elschot M, Scheenen T, Maas M, Bathen T, Selnaes K . Utility of T-weighted MRI texture analysis in assessment of peripheral zone prostate cancer aggressiveness: a single-arm, multicenter study. Sci Rep. 2021; 11(1):2085. PMC: 7822867. DOI: 10.1038/s41598-021-81272-x. View

Felker E, Margolis D, Nassiri N, Marks L . Prostate cancer risk stratification with magnetic resonance imaging. Urol Oncol. 2016; 34(7):311-9. PMC: 6042510. DOI: 10.1016/j.urolonc.2016.03.001. View

Matoso A, Epstein J . Defining clinically significant prostate cancer on the basis of pathological findings. Histopathology. 2018; 74(1):135-145. DOI: 10.1111/his.13712. View

Gnep K, Fargeas A, Gutierrez-Carvajal R, Commandeur F, Mathieu R, Ospina J . Haralick textural features on T -weighted MRI are associated with biochemical recurrence following radiotherapy for peripheral zone prostate cancer. J Magn Reson Imaging. 2016; 45(1):103-117. DOI: 10.1002/jmri.25335. View

Hambrock T, Hoeks C, Hulsbergen-van de Kaa C, Scheenen T, Futterer J, Bouwense S . Prospective assessment of prostate cancer aggressiveness using 3-T diffusion-weighted magnetic resonance imaging-guided biopsies versus a systematic 10-core transrectal ultrasound prostate biopsy cohort. Eur Urol. 2011; 61(1):177-84. DOI: 10.1016/j.eururo.2011.08.042. View

Khosravi P, Lysandrou M, Eljalby M, Li Q, Kazemi E, Zisimopoulos P . A Deep Learning Approach to Diagnostic Classification of Prostate Cancer Using Pathology-Radiology Fusion. J Magn Reson Imaging. 2021; 54(2):462-471. PMC: 8360022. DOI: 10.1002/jmri.27599. View

Aldoj N, Lukas S, Dewey M, Penzkofer T . Semi-automatic classification of prostate cancer on multi-parametric MR imaging using a multi-channel 3D convolutional neural network. Eur Radiol. 2019; 30(2):1243-1253. DOI: 10.1007/s00330-019-06417-z. View

Castaldo R, Cavaliere C, Soricelli A, Salvatore M, Pecchia L, Franzese M . Radiomic and Genomic Machine Learning Method Performance for Prostate Cancer Diagnosis: Systematic Literature Review. J Med Internet Res. 2021; 23(4):e22394. PMC: 8050752. DOI: 10.2196/22394. View

Boorjian S, Karnes R, Crispen P, Rangel L, Bergstralh E, Sebo T . The impact of discordance between biopsy and pathological Gleason scores on survival after radical prostatectomy. J Urol. 2008; 181(1):95-104. DOI: 10.1016/j.juro.2008.09.016. View

10.

Chen T, Zhang Z, Tan S, Zhang Y, Wei C, Wang S . MRI Based Radiomics Compared With the PI-RADS V2.1 in the Prediction of Clinically Significant Prostate Cancer: Biparametric vs Multiparametric MRI. Front Oncol. 2022; 11:792456. PMC: 8810653. DOI: 10.3389/fonc.2021.792456. View

11.

Chaddad A, Kucharczyk M, Niazi T . Multimodal Radiomic Features for the Predicting Gleason Score of Prostate Cancer. Cancers (Basel). 2018; 10(8). PMC: 6116195. DOI: 10.3390/cancers10080249. View

12.

Peerlings J, Woodruff H, Winfield J, Ibrahim A, Van Beers B, Heerschap A . Stability of radiomics features in apparent diffusion coefficient maps from a multi-centre test-retest trial. Sci Rep. 2019; 9(1):4800. PMC: 6423042. DOI: 10.1038/s41598-019-41344-5. View

13.

Hectors S, Chen C, Chen J, Wang J, Gordon S, Yu M . Magnetic Resonance Imaging Radiomics-Based Machine Learning Prediction of Clinically Significant Prostate Cancer in Equivocal PI-RADS 3 Lesions. J Magn Reson Imaging. 2021; 54(5):1466-1473. DOI: 10.1002/jmri.27692. View

14.

Ginsburg S, Algohary A, Pahwa S, Gulani V, Ponsky L, Aronen H . Radiomic features for prostate cancer detection on MRI differ between the transition and peripheral zones: Preliminary findings from a multi-institutional study. J Magn Reson Imaging. 2016; 46(1):184-193. PMC: 5464994. DOI: 10.1002/jmri.25562. View

15.

Algohary A, Shiradkar R, Pahwa S, Purysko A, Verma S, Moses D . Combination of Peri-Tumoral and Intra-Tumoral Radiomic Features on Bi-Parametric MRI Accurately Stratifies Prostate Cancer Risk: A Multi-Site Study. Cancers (Basel). 2020; 12(8). PMC: 7465024. DOI: 10.3390/cancers12082200. View

16.

Donati O, Mazaheri Y, Afaq A, Vargas H, Zheng J, Moskowitz C . Prostate cancer aggressiveness: assessment with whole-lesion histogram analysis of the apparent diffusion coefficient. Radiology. 2014; 271(1):143-52. DOI: 10.1148/radiol.13130973. View

17.

Turkbey B, Pinto P, Mani H, Bernardo M, Pang Y, McKinney Y . Prostate cancer: value of multiparametric MR imaging at 3 T for detection--histopathologic correlation. Radiology. 2010; 255(1):89-99. PMC: 2843833. DOI: 10.1148/radiol.09090475. View

18.

Caulfield S, Menezes G, Marignol L, Poole C . Nomograms are key decision-making tools in prostate cancer radiation therapy. Urol Oncol. 2018; 36(6):283-292. DOI: 10.1016/j.urolonc.2018.03.017. View

19.

Bonekamp D, Kohl S, Wiesenfarth M, Schelb P, Radtke J, Gotz M . Radiomic Machine Learning for Characterization of Prostate Lesions with MRI: Comparison to ADC Values. Radiology. 2018; 289(1):128-137. DOI: 10.1148/radiol.2018173064. View

20.

Donisi L, Cesarelli G, Castaldo A, De Lucia D, Nessuno F, Spadarella G . A Combined Radiomics and Machine Learning Approach to Distinguish Clinically Significant Prostate Lesions on a Publicly Available MRI Dataset. J Imaging. 2021; 7(10). PMC: 8540196. DOI: 10.3390/jimaging7100215. View