Quantitative Analysis of Diffusion Weighted Imaging May Improve Risk Stratification of Prostatic Transition Zone Lesions

Engel, Hannes; Oerther, Benedict; Reisert, Marco; Kellner, Elias; Sigle, August; Gratzke, Christian; Bronsert, Peter; Krauß, Tobias; Bamberg, Fabian; Benndorf, Matthias

doi:10.21873/invivo.12963

Cited by 5 publications

(4 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our data also supported the use of quantitative ADC measurements for decision-making in PI-RADS 3 lesions, with AUC of 0.856 (0.782-0.923) and 0.788 (0.628-0.920) in the training and testing cohorts, respectively. Efficient at discerning the microenvironment of neoplastic tissues, ADC can identify alterations in compartmental volumes, such as stroma, epithelium, and lumen space, and cellularity (32), It currently serves as best parameter for prostate MRI assessment (4,33). Moreover, ADC has been consistently proven to be inversely correlated with factors like tumor grade, tumor aggressiveness, and pathological stage (34)(35)(36).…”

Section: Discussionmentioning

confidence: 99%

“…By 2040, global prostate cancer incidences are projected to rise to nearly 2.3 million new cases and 740 000 deaths (3). Multi-Magnetic resonance imaging (mpMRI) of the prostate, which helps improve the detection, localization, and staging of prostate cancer (PCa), has been established as the de facto standard for the imaging assessment of suspected PCa (4). A large-sample study demonstrated that utilizing MRI for initial screening before biopsy can minimize needless biopsies by approximately half for cases with a PI-RADS score of 3 or higher, and prevent the overdiagnosis of clinically insignificant lesions (5).…”

Section: Introductionmentioning

confidence: 99%

“…Recent studies suggest exploiting radiomic features and mean apparent diffusion coefficient (ADC) values to quantitively evaluate MRI enhances diagnostic accuracy for TZ lesions over mere qualitative PI-RADS assessment (13)(14)(15). Engel et al reported that the risk stratification for prostatic TZ lesions could be improved through a quantitative diffusion-weighted imaging (DWI) analysis (4). Another study demonstrated an achievable specificity and sensitivity through downgrading PI-RADS lesions at or above 4 based on mean ADC values or machine learning algorithms (15).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Magnetic resonance imaging radiomics-based prediction of clinically significant prostate cancer in equivocal PI-RADS 3 lesions in the transitional zone

Zhao,

Xiong,

Liu

et al. 2023

Front. Oncol.

View full text Add to dashboard Cite

PurposeThis bi-institutional study aimed to establish a robust model for predicting clinically significant prostate cancer (csPCa) (pathological grade group ≥ 2) in PI-RADS 3 lesions in the transition zone by comparing the performance of combination models.Materials and methodsThis study included 243 consecutive men who underwent 3-Tesla magnetic resonance imaging (MRI) and ultrasound-guided transrectal biopsy from January 2020 and April 2022 which is divided into a training cohort of 170 patients and a separate testing cohort of 73 patients. T2WI and DWI images were manually segmented for PI-RADS 3 lesions for the mean ADC and radiomic analysis. Predictive clinical factors were identified using both univariate and multivariate logistic models. The least absolute shrinkage and selection operator (LASSO) regression models were deployed for feature selection and for constructing radiomic signatures. We developed nine models utilizing clinical factors, radiological features, and radiomics, leveraging logistic and XGboost methods. The performances of these models was subsequently compared using Receiver Operating Characteristic (ROC) analysis and the Delong test.ResultsOut of the 243 participants with a median age of 70 years, 30 were diagnosed with csPCa, leaving 213 without a csPCa diagnosis. Prostate-specific antigen density (PSAD) stood out as the only significant clinical factor (odds ratio [OR], 1.068; 95% confidence interval [CI], 1.029–1.115), discovered through the univariate and multivariate logistic models. Seven radiomic features correlated with csPCa prediction. Notably, the XGboost model outperformed eight other models (AUC of the training cohort: 0.949, and validation cohort: 0.913). However, it did not surpass the PSAD+MADC model (P > 0.05) in the training and testing cohorts (AUC, 0.949 vs. 0.888 and 0.913 vs. 0.854, respectively).ConclusionThe machine learning XGboost model presented the best performance in predicting csPCa in PI-RADS 3 lesions within the transitional zone. However, the addition of radiomic classifiers did not display any significant enhancement over the compound model of clinical and radiological findings. The most exemplary and generalized option for quantitative prostate evaluation was Mean ADC+PSAD.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Magnetic resonance imaging radiomics-based prediction of clinically significant prostate cancer in equivocal PI-RADS 3 lesions in the transitional zone

Zhao,

Xiong,

Liu

et al. 2023

Front. Oncol.

View full text Add to dashboard Cite

show abstract

“…This revision makes the risk stratification of TZ lesions more reasonable. Recent studies that had moderate to substantial interreader agreement have confirmed that quantitative apparent diffusion coefficient (ADC) measurement may be important for risk stratification 5–7 . However, the assessment of hyperintensity on high b -value DWI and hypointensity on ADC maps is still subjective, and it is not mentioned whether ADC value or ADC category can improve the diagnostic efficacy of prostatic transition zone cancer in PI-RADS v2.1.…”

mentioning

confidence: 99%

Comparison of the Utility of PI-RADS 2.1, ADC Values, and Combined Use of Both, for the Diagnosis of Transition Zone Prostate Cancers

Liu,

Xiong,

Zeng

et al. 2023

J Comput Assist Tomogr

View full text Add to dashboard Cite

Objective To assess the performance of apparent diffusion coefficient (ADC; values or category) alone, Prostate Imaging Reporting and Data System version 2.1 (PI-RADS v2.1) scoring alone, and the two in combination, to diagnose transition zone prostate cancers (PCas). Methods This retrospective study included 222 patients who underwent multiparametric magnetic resonance imaging of the prostate between May 2020 and December 2022 and who had pathologically confirmed PCa or benign prostatic hyperplasia (BPH). Prostate Imaging Reporting and Data System version 2.1 and ADC (values or category) were used in the assessment of suspicious findings identified in the transition zone. The interobserver agreements for region-of-interest measurements were calculated by intraclass correlation coefficients. Logistic regression analyses were used to determine the performance of PI-RADS v2.1 alone and in combination with ADC (values or category) to diagnose PCa. Receiver operating characteristic curve and DeLong test were used to evaluate the diagnostic performance of the quantitative parameters. Results A total of 152 patients had BPH, and 70 patients had PCa. For BPH versus PCa, the ADC values of PCa (0.64 × 10−3 ± 0.16 × 10−3 mm2/s) were significantly lower than BPH (1.06 ± 0.18 × 10−3 mm2/s; P < 0.001). The PI-RADS scores for PCa (5 [interquartile range, 5–5]) were significantly higher than BPH (2 [interquartile range, 2–3]; P < 0.001). For all patients who had PI-RADS 1–5, the combined use of ADC (values or category) together with PI-RADS v2.1 did not perform significantly better than the use of PI-RADS v2.1 alone. The receiver operating characteristic of ADC category in combination with PI-RADS v2.1 score, 0.756 (95% confidence interval, 0.646–0.846), was significantly higher than that for PI-RADS 2.1 alone, 0.631 (95% confidence interval, 0.514–0.738), in PI-RADS 3–4 lesions (P = 0.047). Conclusion The ADC category can help to improve the diagnostic performance of PI-RADS v2.1 category 3–4 lesions in diagnosing PCa.

show abstract

Prevalence and grade of malignancy differences with respect to the area of involvement in multiparametric resonance imaging of the prostate in the diagnosis of prostate cancer using the PI-RADS version 2 classification

Rodríguez-Cabello,

Méndez-Rubio,

Sanz-Miguelañez

et al. 2023

World J Urol

View full text Add to dashboard Cite

Quantitative Analysis of Diffusion Weighted Imaging May Improve Risk Stratification of Prostatic Transition Zone Lesions

Cited by 5 publications

References 26 publications

Magnetic resonance imaging radiomics-based prediction of clinically significant prostate cancer in equivocal PI-RADS 3 lesions in the transitional zone

Magnetic resonance imaging radiomics-based prediction of clinically significant prostate cancer in equivocal PI-RADS 3 lesions in the transitional zone

Comparison of the Utility of PI-RADS 2.1, ADC Values, and Combined Use of Both, for the Diagnosis of Transition Zone Prostate Cancers

Prevalence and grade of malignancy differences with respect to the area of involvement in multiparametric resonance imaging of the prostate in the diagnosis of prostate cancer using the PI-RADS version 2 classification

Contact Info

Product

Resources

About