Prediction of clinically significant prostate cancer with a multimodal MRI-based radiomics nomogram

Abstract

ObjectiveTo develop and validate a multimodal MRI-based radiomics nomogram for predicting clinically significant prostate cancer (CS-PCa).MethodsPatients who underwent radical prostatectomy with pre-biopsy prostate MRI in three different centers were assessed retrospectively. Totally 141 and 60 cases were included in the training and test sets in cohort 1, respectively. Then, 66 and 122 cases were enrolled in cohorts 2 and 3, as external validation sets 1 and 2, respectively. Two different manual segmentation methods were established, including lesion segmentation and whole prostate segmentation on T2WI and DWI scans, respectively. Radiomics features were obtained from the different segmentation methods and selected to construct a radiomics signature. The final nomogram was employed for assessing CS-PCa, combining radiomics signature and PI-RADS. Diagnostic performance was determined by receiver operating characteristic (ROC) curve analysis, net reclassification improvement (NRI) and decision curve analysis (DCA).ResultsTen features associated with CS-PCa were selected from the model integrating whole prostate (T2WI) + lesion (DWI) for radiomics signature development. The nomogram that combined the radiomics signature with PI-RADS outperformed the subjective evaluation alone according to ROC analysis in all datasets (all p<0.05). NRI and DCA confirmed that the developed nomogram had an improved performance in predicting CS-PCa.ConclusionsThe established nomogram combining a biparametric MRI-based radiomics signature and PI-RADS could be utilized for noninvasive and accurate prediction of CS-PCa.

Biparametric MRI-based radiomics classifiers for the detection of prostate cancer in patients with PSA serum levels of 4∼10 ng/mL

“…( 9 ) compared the combination of lesion segmentation and whole prostate segmentation on T2WI and DWI to establish the optimal radiomic methodology. The results showed that the radiomic model based on whole prostate T2WI and lesion DWI achieved the best performance in predicting clinically significant PCa, which was superior to PI-RADS scores ( 9 ). However, Montoya et al.…”

“…Radiomics is a novel tool that involves extracting quantitative features from medical images using computational algorithms such as machine learning, which can identify new biomarkers and assess the heterogeneity of the disease (8). Recently, radiomics and its combination with machine learning techniques have shown its promise in MRI-based PCa diagnosis, which was superior to Prostate Imaging-Reporting and Data System (PI-RADS) category (9)(10)(11)(12)(13). mpMRI protocol suggested by PI-RADS v2.0 includes T2weighted imaging (T2WI), diffusion-weighted imaging (DWI) and the corresponding apparent-diffusion coefficient (ADC) maps, and dynamic contrast-enhanced (DCE) imaging (14).…”

Development and internal validation of a nomogram predicting significant prostate cancer: Is it clinically applicable in low prevalent prostate cancer countries? A multicenter study

“…Four recent studies that used MRI/PI‐RAD scores for the creation of prediction models have reached the same conclusion 28–31 . According to ROC analysis in all datasets, where it varied from 0.80 to 0.96, Jing et al 28 integrated radiomics signature and PI‐RADS to construct a radiomics nomogram with superior discriminatory capacity, predicting csPCa, which surpassed the subjective evaluation alone of PSA.…”

“…Four recent studies that used MRI/PI-RAD scores for the creation of prediction models have reached the same conclusion. [28][29][30][31] According to ROC analysis in all datasets, where it varied from 0.80 to 0.96, Jing et al 28 integrated radiomics signature and PI-RADS to construct a radiomics nomogram with superior discriminatory capacity, predicting csPCa, which surpassed the subjective evaluation alone of PSA. The use of multiparametric-MRI (mpMRI) based nomograms for predicting csPCa showed a slight but significant net benefit in Castellani's DCA compared to those excluding PI-RADS scores, and the AUC for the full model including PI-RADS scores was 0.77.…”

Normalization Strategies in Multi-Center Radiomics Abdominal MRI: Systematic Review and Meta-Analyses

“…All included papers have been published since 2015, with an increase from 2019. The most studied organs are the prostate [3] , [19] , [20] , [21] , [22] , [23] , [24] , [25] , [26] , [27] , [28] , [29] , [30] , [31] , [32] , [33] , [34] , [35] , [36] , [37] , [38] , [39] , [40] (S-Table I), female pelvis [4] , [41] , [42] , [43] , [44] , [45] , [46] , [47] , [48] , [49] , [50] , [51] , [52] (S-Table II), and rectum [5] , [53] , [54] , [55] , [56] , [57] , [58] , [59] , [60] , [61] , [62] , [63] , [64] , [65] , [66] , [67] , [68] , [69] (S-Table III), while a lower number of publications were related to the liver [6] , [70] , [71] , [72] , [73] , [74] , [75] (S-Table IV), and a miscellaneous group of organs including kidney [76] , [77] , …”