Download This Paper
Preprints with The Lancet is a collaboration between The Lancet Group of journals and SSRN to facilitate the open sharing of preprints for early engagement, community comment, and collaboration. Preprints available here are not Lancet publications or necessarily under review with a Lancet journal. These preprints are early-stage research papers that have not been peer-reviewed. The usual SSRN checks and a Lancet-specific check for appropriateness and transparency have been applied. The findings should not be used for clinical or public health decision-making or presented without highlighting these facts. For more information, please see the FAQs.
A Radiomics Machine Learning Based Redefining Score Robustly Identifies Clinically Significant Prostate Cancer in Equivocal PI-RADS Score 3 Lesions
41 Pages Posted: 13 Jul 2020
More...Abstract
Background: PI-RADS score 3 lesions are recognized as equivocal likelihood of clinically significant prostate cancer (csPCa) occurrence, the optimal management of which remains controversial.
Methods: We developed a radiomics machine learning (RML) based redefining score to screen out csPCa in equivocal PI-RADS score 3 category in 263 patients with the dominant index lesion scored PI-RADS 3 who underwent biopsy and/or follow-up. One-step RML ( RML-i ) model integrated radiomic features of T2WI, DWI and ADC images all together, and two-step RML (RML-ii) model integrated the three independent radiomic signatures from T2WI images(T2WIRS), DWI images(DWIRS) and ADC images(ADCRS) separately into a regression model. The two RML models, as well as T2WIRS, DWIRS and ADCRS, were compared using the receiver operating characteristic-derived area under the curve (AUC), calibration plot and decision-curve analysis (DCA). Two radiologists were asked to give a subjective binary assessment, Cohen’s kappa statistics were calculated.
Findings: A total of 59/263 (22.4%) csPCa were identified. Inter-reader agreement was moderate (Kappa =0.435). The AUC of RML-i (0.89; 95% CI: 0.88-0.90) is significantly (p = 0.003) higher than that of RML-ii (0.87; 95% CI: 0.86-0.88). The DCA demonstrated that the RML-i and RML-ii significantly improved risk prediction at threshold probabilities of csPCa at 20% to 80% compared with doing-none or doing-all by PI-RADS score 3 or stratifying by separated DWI RS , ADC RS or T2WI RS .
Interpretation: Our RML models have the potential to predict csPCa in PI-RADS 3 lesions, thus informing the decision making process of biopsy.
Funding: None.
Declaration of Interests: The author declares no conflict of interest.
Ethics Approval Statement: This study was approved by the Independent Research Ethics Boards of the First Affiliated Hospital of Nanjing Medical University (protocol 2016-SRFA-093) on Dec 2016, before data analysis was conducted. Informed consent was waived and all procedures performed in studies involving human participants were in accordance with the 1964 Helsinki declaration and its later amendments.
Keywords: clinically significant prostate cancer; radiomics; machine learning; PI-RADS score 3
Suggested Citation: Suggested Citation