Abbreviated Protocols <i>versus</i> Multiparametric MRI for Assessment of Extraprostatic Extension in Prostatic Carcinoma: A Multireader Study

Stanzione, Arnaldo; Ponsiglione, Andrea; Cuocolo, Renato; Cocozza, Sirio; Picchi, Stefano Giusto; Stilo, Salvatore; Persico, Francesco; Creta, Massimiliano; Longo, Nicola; Imbriaco, Massimo

doi:10.21873/anticanres.13617

Cited by 23 publications

(12 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Regarding the first, biparametric prostate MRI protocols without the use of DCE are becoming more and more common, also to accommodate the increasing demand for MRI exams due to its growing role in current guidelines [ 5 , 32 ]. Protocols without DCE have also shown a similar performance to full mpMRI for EPE detection [ 33 ]. Finally, DCE has a high temporal resolution, with the degree and speed of lesion enhancement influenced both by technical and physiological factors, together with lesion nature.…”

Section: Discussionmentioning

confidence: 99%

MRI index lesion radiomics and machine learning for detection of extraprostatic extension of disease: a multicenter study

et al. 2021

Self Cite

View full text Add to dashboard Cite

Objectives To build a machine learning (ML) model to detect extraprostatic extension (EPE) of prostate cancer (PCa), based on radiomics features extracted from prostate MRI index lesions. Methods Consecutive MRI exams of patients undergoing radical prostatectomy for PCa were retrospectively collected from three institutions. Axial T2-weighted and apparent diffusion coefficient map images were annotated to obtain index lesion volumes of interest for radiomics feature extraction. Data from one institution was used for training, feature selection (using reproducibility, variance and pairwise correlation analyses, and a correlation-based subset evaluator), and tuning of a support vector machine (SVM) algorithm, with stratified 10-fold cross-validation. The model was tested on the two remaining institutions’ data and compared with a baseline reference and expert radiologist assessment of EPE. Results In total, 193 patients were included. From an initial dataset of 2436 features, 2287 were excluded due to either poor stability, low variance, or high collinearity. Among the remaining, 14 features were used to train the ML model, which reached an overall accuracy of 83% in the training set. In the two external test sets, the SVM achieved an accuracy of 79% and 74% respectively, not statistically different from that of the radiologist (81–83%, p = 0.39–1) and outperforming the baseline reference (p = 0.001–0.02). Conclusions A ML model solely based on radiomics features demonstrated high accuracy for EPE detection and good generalizability in a multicenter setting. Paired to qualitative EPE assessment, this approach could aid radiologists in this challenging task. Key Points • Predicting the presence of EPE in prostate cancer patients is a challenging task for radiologists. • A support vector machine algorithm achieved high diagnostic accuracy for EPE detection, with good generalizability when tested on multiple external datasets. • The performance of the algorithm was not significantly different from that of an experienced radiologist.

show abstract

Section: Discussionmentioning

confidence: 99%

MRI index lesion radiomics and machine learning for detection of extraprostatic extension of disease: a multicenter study

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…Multiparametric MRI is still preferred in men, where the balance between under-diagnosis and overdiagnosis favors the clinical priority of not missing significant cancer [21]. These patients include men with prior negative biopsies with unexplained raised e920252-3…”

Section: The Role Of Multiparametric Mri In Active Surveillance Of Prostate Cancermentioning

confidence: 99%

“…Water molecules, which are the main source of protons in the body, move freely in the normal tissue. Tumors, included prostate cancer, consist of densely packed cells and an abundance of cell membranes with restricted diffusion of water [20,21].…”

Section: The Role Of Multiparametric Mri In Active Surveillance Of Prostate Cancermentioning

confidence: 99%

Active Surveillance of Prostate Cancer Using Multiparametric Magnetic Resonance Imaging: A Review of the Current Role and Future Perspectives

2020

View full text Add to dashboard Cite

Departmental sourcesClinically, active surveillance involves continuous monitoring of patients who may be at risk for disease. Patients with low-grade and early-stage prostate cancer may benefit from active surveillance, rather than undergoing surgical and medical treatments that are associated with side effects. In these cases, the role of active surveillance is to ensure that there is no progression of the disease. However, active surveillance may be associated with a risk of under-diagnosis. Previously, the assignment of risk categories and patient monitoring were based on digital rectal examination, transrectal prostate biopsy, and monitoring of serum levels of prostatespecific antigen (PSA). Multiparametric magnetic resonance imaging (MRI) of the prostate gland has an estimated negative predictive value of 95% for the detection of prostate cancer, which makes this an effective imaging method for targeting biopsies and for monitoring patients over time. Also, multiparametric MRI-guided biopsy at the initial stage of the risk stratification for patients who are newly diagnosed with prostate cancer may reduce the number of underdiagnosed patients, improve long-term patient prognosis, and reduce the number of patients who are overtreated, which may reduce healthcare costs and reduce treatment morbidity. For these reasons, multiparametric MRI has become an accepted monitoring tool in patients who are enrolled in active surveillance programs. This review aims to present the current status of the use of multiparametric MRI in active surveillance of prostate cancer and to discuss future perspectives, supported by recent literature.

show abstract

“…Stanzione et al. (20) compared the diagnostic accuracy of three MRI protocols for detecting EPE in a small retrospective multi-reader study of 35 cases with and 15 cases without PCa. Dual-pulse MRI (DWI + tT2W), bpMRI, and mpMRI evaluated by two experienced radiologists and two radiology residents were compared.…”

Section: Discussionmentioning

confidence: 99%

Accuracy of abbreviated multiparametric MRI-derived protocols in predicting local staging of prostate cancer in men undergoing radical prostatectomy

et al. 2020

View full text Add to dashboard Cite

Background Abbreviated magnetic resonance imaging (aMRI) protocols have emerged as an alternative to multiparametric MRI (mpMRI) to reduce examination time and costs. Purpose To compare multiple aMRI protocols for predicting pathological stage ≥T3 (≥pT3) prostate cancer (PCa). Material and Methods One hundred and eight men undergoing staging mpMRI before radical prostatectomy (RP) were retrospectively evaluated. 3.0-T imaging was performed with a 32-channel surface coil and a protocol including diffusion-weighted imaging (DWI), transverse T2-weighted (tT2W) imaging, coronal T2W (cT2W) imaging, sagittal T2W (sT2) imaging, and dynamic contrast-enhanced (DCE) imaging. Two readers independently assessed whether any MRI observation showed stage ≥T3 on each sequence (reading order: DWI, cT2W, tT2W, sT2W, DCE). Final stage was assessed by matching readers’ assignments to pathology, and combining them into eight protocols: DWI + tT2W, DWI + cT2W + tT2W, DWI + tT2W + sT2W, DWI + cT2W + tT2W + sT2W, DWI + tT2W + DCE, DWI + cT2W + tT2W + DCE, DWI + tT2W + sT2W + DCE, and mpMRI. Diagnostic accuracy and inter-reader agreement for aMRI protocols were calculated. Results Prevalence of ≥pT3 PCa was 31.5%. Sensitivity, specificity, positive (PPV) and negative predictive value (NPV) of aMRI protocols were comparable to mpMRI for R1. Sensitivity was 74.3% (95% confidence interval [CI] 64.8–72.0) to 77.1% (95% CI 67.9–84.4), and NPV 86.8% (95% CI 78.6–92.3) to 88.1% (95% CI 80.1–93.3). All accuracy measures of the various aMRI protocols were similar to mpMRI also for R2, albeit all slightly lower compared to R1. On a per-protocol basis, there was substantial inter-reader agreement in predicting stage ≥pT3 (k 0.63–0.67). Conclusion When comparing the diagnostic accuracy of multiple aMRI protocols against mpMRI for predicting stage ≥pT3 PCa, the protocol with the fewest sequences (DWI + tT2W) is apparently equivalent to standard mpMRI.

show abstract

Abbreviated Protocols versus Multiparametric MRI for Assessment of Extraprostatic Extension in Prostatic Carcinoma: A Multireader Study

Abstract: Patients and MethodsThis observational, retrospective study was approved by the Institutional Review Board (Protocol number: 60/19) and the need for informed consent was waived.

Cited by 23 publications

References 29 publications

MRI index lesion radiomics and machine learning for detection of extraprostatic extension of disease: a multicenter study

MRI index lesion radiomics and machine learning for detection of extraprostatic extension of disease: a multicenter study

Active Surveillance of Prostate Cancer Using Multiparametric Magnetic Resonance Imaging: A Review of the Current Role and Future Perspectives

Accuracy of abbreviated multiparametric MRI-derived protocols in predicting local staging of prostate cancer in men undergoing radical prostatectomy

Contact Info

Product

Resources

About