Dataset Information

Detection of prostate cancer with multiparametric MRI utilizing the anatomic structure of the prostate.

ABSTRACT: Multiparametric magnetic resonance imaging (mpMRI), which combines traditional anatomic and newer quantitative MRI methods, has been shown to result in improved voxel-wise classification of prostate cancer as compared with any single MRI parameter. While these results are promising, substantial heterogeneity in the mpMRI parameter values and voxel-wise prostate cancer risk has been observed both between and within regions of the prostate. This suggests that classification of prostate cancer can potentially be improved by incorporating structural information into the classifier. In this paper, we propose a novel voxel-wise classifier of prostate cancer that accounts for the anatomic structure of the prostate by Bayesian hierarchical modeling, which can be combined with post hoc spatial Gaussian kernel smoothing to account for residual spatial correlation. Our proposed classifier results in significantly improved area under the ROC curve (0.822 vs 0.729, P < .001) and sensitivity corresponding to 90% specificity (0.599 vs 0.429, P < .001), compared with a baseline model that does not account for the anatomic structure of the prostate. Furthermore, the classifier can also be applied on voxels with missing mpMRI parameters, resulting in similar performance, which is an important practical consideration that cannot be easily accommodated using regression-based classifiers. In addition, our classifier achieved high computational efficiency with a closed-form solution for the posterior predictive cancer probability.

SUBMITTER: Jin J

PROVIDER: S-EPMC6123293 | biostudies-literature | 2018 Sep

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Detection of prostate cancer with multiparametric MRI utilizing the anatomic structure of the prostate.

Jin Jin J Zhang Lin L Leng Ethan E Metzger Gregory J GJ Koopmeiners Joseph S JS

Statistics in medicine 20180619 22

Multiparametric magnetic resonance imaging (mpMRI), which combines traditional anatomic and newer quantitative MRI methods, has been shown to result in improved voxel-wise classification of prostate cancer as compared with any single MRI parameter. While these results are promising, substantial heterogeneity in the mpMRI parameter values and voxel-wise prostate cancer risk has been observed both between and within regions of the prostate. This suggests that classification of prostate cancer can ...[more]

PMID: 29923345

Similar Datasets

Project description:Purpose To compare the diagnostic accuracy of gallium 68 (68Ga)-labeled prostate-specific membrane antigen (PSMA)-11 PET/MRI with that of multiparametric MRI in the detection of prostate cancer. Materials and Methods The authors performed a retrospective study of men with biopsy-proven prostate cancer who underwent simultaneous 68Ga-PSMA-11 PET/MRI before radical prostatectomy between December 2015 and June 2017. The reference standard was whole-mount pathologic examination. Readers were blinded to radiologic and pathologic findings. Tumor localization was based on 30 anatomic regions. Region-specific sensitivity and specificity were calculated for PET/MRI and multiparametric MRI by using raw stringent and alternative neighboring approaches. Maximum standardized uptake value (SUVmax) in the tumor and Prostate Imaging Reporting and Data System (PI-RADS) version 2 grade were compared with tumor Gleason score. Generalized estimating equations were used to estimate population-averaged sensitivity and specificity and to determine the association between tumor characteristics and SUVmax or PI-RADS score. Results Thirty-two men (median age, 68 years; interquartile range: 62-71 years) were imaged. The region-specific sensitivities of PET/MRI and multiparametric MRI were 74% (95% confidence interval [CI]: 70%, 77%) and 50% (95% CI: 45%, 0.54%), respectively, with the alternative neighboring approach (P < .001 for both) and 73% (95% CI: 68%, 79%) and 69% (95% CI: 62%, 75%), respectively, with the population-averaged generalized estimating equation (P = .04). Region-specific specificity of PET/MRI was similar to that of multiparametric MRI with the alternative neighboring approach (88% [95% CI: 85%, 91%] vs 90% [95% CI: 87%, 92%], P = .99) and in population-averaged estimates (70% [95% CI: 64%, 76%] vs 70% [95% CI: 64%, 75%], P = .99). SUVmax was associated with a Gleason score of 7 and higher (odds ratio: 1.71 [95% CI: 1.27, 2.31], P < .001). Conclusion The sensitivity of gallium 68-labeled prostate-specific membrane antigen-11 PET/MRI in the detection of prostate cancer is better than that of multiparametric MRI. © RSNA, 2018 See also the editorial by Civelek in this issue.

Project description:BACKGROUND:Multiparametric MRI (mpMRI) became recognised in investigating those with suspected prostate cancer between 2010 and 2012; in the USA, the preventative task force moratorium on PSA screening was a strong catalyst. In a few short years, it has been adopted into daily urological and oncological practice. The pace of clinical uptake, born along by countless papers proclaiming high accuracy in detecting clinically significant prostate cancer, has sparked much debate about the timing of mpMRI within the traditional biopsy-driven clinical pathways. There are strongly held opposing views on using mpMRI as a triage test regarding the need for biopsy and/or guiding the biopsy pattern. OBJECTIVE:To review the evidence base and present a position paper on the role of mpMRI in the diagnosis and management of prostate cancer. METHODS:A subgroup of experts from the ESUR Prostate MRI Working Group conducted literature review and face to face and electronic exchanges to draw up a position statement. RESULTS:This paper considers diagnostic strategies for clinically significant prostate cancer; current national and international guidance; the impact of pre-biopsy mpMRI in detection of clinically significant and clinically insignificant neoplasms; the impact of pre-biopsy mpMRI on biopsy strategies and targeting; the notion of mpMRI within a wider risk evaluation on a patient by patient basis; the problems that beset mpMRI including inter-observer variability. CONCLUSIONS:The paper concludes with a set of suggestions for using mpMRI to influence who to biopsy and who not to biopsy at diagnosis. KEY POINTS:• Adopt mpMRI as the first, and primary, investigation in the workup of men with suspected prostate cancer. • PI-RADS assessment categories 1 and 2 have a high negative predictive value in excluding significant disease, and systematic biopsy may be postponed, especially in men with low-risk of disease following additional risk stratification. • PI-RADS assessment category lesions 4 and 5 should be targeted; PI-RADS assessment category lesion 3 may be biopsied as a target, as part of systematic biopsies or may be observed depending on risk stratification.

Project description:Prostate cancer (PCa) is the most frequent male malignancy and the assessment of PCa aggressiveness, for which a biopsy is required, is fundamental for patient management. Currently, multiparametric (mp) MRI is strongly recommended before biopsy. Quantitative assessment of mpMRI might provide the radiologist with an objective and noninvasive tool for supporting the decision-making in clinical practice and decreasing intra- and inter-reader variability. In this view, high dimensional radiomics features and Machine Learning (ML) techniques, along with Deep Learning (DL) methods working on raw images directly, could assist the radiologist in the clinical workflow. The aim of this study was to develop and validate ML/DL frameworks on mpMRI data to characterize PCas according to their aggressiveness. We optimized several ML/DL frameworks on T2w, ADC and T2w+ADC data, using a patient-based nested validation scheme. The dataset was composed of 112 patients (132 peripheral lesions with Prostate Imaging Reporting and Data System (PI-RADS) score ≥ 3) acquired following both PI-RADS 2.0 and 2.1 guidelines. Firstly, ML/DL frameworks trained and validated on PI-RADS 2.0 data were tested on both PI-RADS 2.0 and 2.1 data. Then, we trained, validated and tested ML/DL frameworks on a multi PI-RADS dataset. We reported the performances in terms of Area Under the Receiver Operating curve (AUROC), specificity and sensitivity. The ML/DL frameworks trained on T2w data achieved the overall best performance. Notably, ML and DL frameworks trained and validated on PI-RADS 2.0 data obtained median AUROC values equal to 0.750 and 0.875, respectively, on unseen PI-RADS 2.0 test set. Similarly, ML/DL frameworks trained and validated on multi PI-RADS T2w data showed median AUROC values equal to 0.795 and 0.750, respectively, on unseen multi PI-RADS test set. Conversely, all the ML/DL frameworks trained and validated on PI-RADS 2.0 data, achieved AUROC values no better than the chance level when tested on PI-RADS 2.1 data. Both ML/DL techniques applied on mpMRI seem to be a valid aid in predicting PCa aggressiveness. In particular, ML/DL frameworks fed with T2w images data (objective, fast and non-invasive) show good performances and might support decision-making in patient diagnostic and therapeutic management, reducing intra- and inter-reader variability.

Dataset Information

Detection of prostate cancer with multiparametric MRI utilizing the anatomic structure of the prostate.

Publications

Detection of prostate cancer with multiparametric MRI utilizing the anatomic structure of the prostate.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets