Prediction of Pathological Upgrading at Radical Prostatectomy in Prostate Cancer Eligible for Active Surveillance: A Texture Features and Machine Learning-Based Analysis of Apparent Diffusion Coefficient Maps

Xie, Jinke; Li, Basen; Min, Xiangde; Zhang, Peipei; Fan, Chanyuan; Li, Qiubai; Wang, Liang

doi:10.3389/fonc.2020.604266

Cited by 13 publications

(10 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Various ML algorithms previously used for GG upgrade prediction are logistic regression 18 , LASSO regression 18 , 46 , SVM 18 , 47 , k-Nearest Neighbours (kNN) 46 , decision trees 46 , and random forests 18 , 46 . Due to the lack of large datasets, medical problems pose a particular challenge for ML models.…”

Section: Discussionmentioning

confidence: 99%

Machine learning prediction of Gleason grade group upgrade between in-bore biopsy and radical prostatectomy pathology

Ozbozduman,

Loc,

Durmaz

et al. 2024

Sci Rep

View full text Add to dashboard Cite

This study aimed to enhance the accuracy of Gleason grade group (GG) upgrade prediction in prostate cancer (PCa) patients who underwent MRI-guided in-bore biopsy (MRGB) and radical prostatectomy (RP) through a combined analysis of prebiopsy and MRGB clinical data. A retrospective analysis of 95 patients with prostate cancer diagnosed by MRGB was conducted where all patients had undergone RP. Among the patients, 64.2% had consistent GG results between in-bore biopsies and RP, whereas 28.4% had upgraded and 7.4% had downgraded results. GG1 biopsy results, lower biopsy core count, and fewer positive cores were correlated with upgrades in the entire patient group. In patients with $$\hbox {GG}>1$$ GG > 1 , larger tumor sizes and fewer biopsy cores were associated with upgrades. By integrating MRGB data with prebiopsy clinical data, machine learning (ML) models achieved 85.6% accuracy in predicting upgrades, surpassing the 64.2% baseline from MRGB alone. ML analysis also highlighted the value of the minimum apparent diffusion coefficient ($$\hbox {ADC}_{\text{min}}$$ ADC min ) for $$\hbox {GG}>1$$ GG > 1 patients. Incorporation of MRGB results with tumor size, $$\hbox {ADC}_{\text{min}}$$ ADC min value, number of biopsy cores, positive core count, and Gleason grade can be useful to predict GG upgrade at final pathology and guide patient selection for active surveillance.

show abstract

Section: Discussionmentioning

confidence: 99%

Machine learning prediction of Gleason grade group upgrade between in-bore biopsy and radical prostatectomy pathology

Ozbozduman,

Loc,

Durmaz

et al. 2024

Sci Rep

View full text Add to dashboard Cite

show abstract

“…However, they noticed incremental benefit with the addition of clinical parameters. Another study by Xie et al investigated the role of radiomics from ADC maps to predict upgrading in Gleason score from TRUS-guided biopsies to radical prostatectomy (34). While Xie et al's study (34) did not directly address progression on repeat biopsy, they demonstrated that radiomic features from screening MRI can differentiate clinically significant and insignificant PCa.…”

Section: Discussionmentioning

confidence: 99%

Delta radiomic patterns on serial bi-parametric MRI are associated with pathologic upgrading in prostate cancer patients on active surveillance: preliminary findings

Midya,

Hiremath,

Huber

et al. 2023

Front. Oncol.

View full text Add to dashboard Cite

ObjectiveThe aim of this study was to quantify radiomic changes in prostate cancer (PCa) progression on serial MRI among patients on active surveillance (AS) and evaluate their association with pathologic progression on biopsy.MethodsThis retrospective study comprised N = 121 biopsy-proven PCa patients on AS at a single institution, of whom N = 50 at baseline conformed to the inclusion criteria. ISUP Gleason Grade Groups (GGG) were obtained from 12-core TRUS-guided systematic biopsies at baseline and follow-up. A biopsy upgrade (AS+) was defined as an increase in GGG (or in number of positive cores) and no upgrade (AS−) was defined when GGG remained the same during a median period of 18 months. Of N = 50 patients at baseline, N = 30 had MRI scans available at follow-up (median interval = 18 months) and were included for delta radiomic analysis. A total of 252 radiomic features were extracted from the PCa region of interest identified by board-certified radiologists on 3T bi-parametric MRI [T2-weighted (T2W) and apparent diffusion coefficient (ADC)]. Delta radiomic features were computed as the difference of radiomic feature between baseline and follow-up scans. The association of AS+ with age, prostate-specific antigen (PSA), Prostate Imaging Reporting and Data System (PIRADS v2.1) score, and tumor size was evaluated at baseline and follow-up. Various prediction models were built using random forest (RF) classifier within a threefold cross-validation framework leveraging baseline radiomics (Cbr), baseline radiomics + baseline clinical (Cbrbcl), delta radiomics (CΔr), delta radiomics + baseline clinical (CΔrbcl), and delta radiomics + delta clinical (CΔrΔcl).ResultsAn AUC of 0.64 ± 0.09 was obtained for Cbr, which increased to 0.70 ± 0.18 with the integration of clinical variables (Cbrbcl). CΔr yielded an AUC of 0.74 ± 0.15. Integrating delta radiomics with baseline clinical variables yielded an AUC of 0.77 ± 0.23. CΔrΔclresulted in the best AUC of 0.84 ± 0.20 (p < 0.05) among all combinations.ConclusionOur preliminary findings suggest that delta radiomics were more strongly associated with upgrade events compared to PIRADS and other clinical variables. Delta radiomics on serial MRI in combination with changes in clinical variables (PSA and tumor volume) between baseline and follow-up showed the strongest association with biopsy upgrade in PCa patients on AS. Further independent multi-site validation of these preliminary findings is warranted.

show abstract

“…Specifically, studies of Nordström et al and Moore et al demonstrated that the inclusion of MRI in longitudinal PCa biopsy and diagnostic pathways lead to a clear decrease of unnecessary re-biopsies and a higher yield of the clinical significant PCa ( 24 , 25 ). Those pathways are likely to further improve if combined with deep learning-based analyses of imaging features, such as apparent diffusion coefficient (ADC) maps ( 26 ).…”

Section: Discussionmentioning

confidence: 99%

The Dilemma of Misclassification Rates in Senior Patients With Prostate Cancer, Who Were Treated With Robot-Assisted Radical Prostatectomy: Implications for Patient Counseling and Diagnostics

et al. 2022

View full text Add to dashboard Cite

ObjectivesThere is a recent paradigm shift to extend robot-assisted radical prostatectomy (RARP) to very senior prostate cancer (PCa) patients based on biological fitness, comorbidities, and clinical PCa assessment that approximates the true risk of progression. Thus, we aimed to assess misclassification rates between clinical vs. pathological PCa burden.Materials and MethodsWe compared senior patients with PCa ≥75 y (n = 847), who were propensity score matched with younger patients <75 y (n = 3,388) in a 1:4 ratio. Matching was based on the number of biopsy cores, prostate volume, and preoperative Cancer of the Prostate Risk Assessment (CAPRA) risk groups score. Multivariable logistic regression models (LRMs) predicted surgical CAPRA (CAPRA-S) upgrade, which was defined as a higher risk of the CAPRA-S in the presence of lower-risk preoperative CAPRA score. LRM incorporated the same variables as propensity score matching. Moreover, patients were categorized as low-, intermediate-, and high-risk, preoperative and according to their CAPRA and CAPRA-S scores.ResultsSurgical CAPRA risk strata significantly differed between the groups. Greater proportions of unfavorable intermediate risk (39 vs. 32%) or high risk (30 vs. 28%; p < 0.001) were observed. These proportions are driven by greater proportions of International Society of Urological Pathology (ISUP) Gleason Grade Group 4 or 5 (33 vs. 26%; p = 0.001) and pathological tumor stage (≥T3a 54 vs. 45%; p < 0.001). Increasing age was identified as an independent predictor of CAPRA-S-based upgrade (age odds ratio [OR] 1.028 95% CI 1.02–1.037; p < 0.001).ConclusionApproximately every second senior patient has a misclassification in (i.e., any up or downgrade) and each 4.5th senior patient specifically has an upgrade in his final pathology that directly translates to an unfavorable PCa prognosis. It is imperative to take such substantial misclassification rates into account for this sensitive PCa demographic of senior men. Future prospective studies are warranted to further optimize PCa workflow and diagnostics, such as to incorporate modern imaging, molecular profiling and implement these into biopsy strategies to identify true PCa burden.

show abstract

Prediction of Pathological Upgrading at Radical Prostatectomy in Prostate Cancer Eligible for Active Surveillance: A Texture Features and Machine Learning-Based Analysis of Apparent Diffusion Coefficient Maps

Cited by 13 publications

References 46 publications

Machine learning prediction of Gleason grade group upgrade between in-bore biopsy and radical prostatectomy pathology

Machine learning prediction of Gleason grade group upgrade between in-bore biopsy and radical prostatectomy pathology

Delta radiomic patterns on serial bi-parametric MRI are associated with pathologic upgrading in prostate cancer patients on active surveillance: preliminary findings

The Dilemma of Misclassification Rates in Senior Patients With Prostate Cancer, Who Were Treated With Robot-Assisted Radical Prostatectomy: Implications for Patient Counseling and Diagnostics

Contact Info

Product

Resources

About