Purpose This study aimed to develop deep learning (DL) models based on multicentre biparametric magnetic resonance imaging (bpMRI) for the diagnosis of clinically significant prostate cancer (csPCa) and compare the performance of these models with that of the Prostate Imaging and Reporting and Data System (PI-RADS) assessment by expert radiologists based on multiparametric MRI (mpMRI). Methods We included 1861 consecutive male patients who underwent radical prostatectomy or biopsy at seven hospitals with mpMRI. These patients were divided into the training (1216 patients in three hospitals) and external validation cohorts (645 patients in four hospitals). PI-RADS assessment was performed by expert radiologists. We developed DL models for the classification between benign and malignant lesions (DL-BM) and that between csPCa and non-csPCa (DL-CS). An integrated model combining PI-RADS and the DL-CS model, abbreviated as PIDL-CS, was developed. The performances of the DL models and PIDL-CS were compared with that of PI-RADS. Results In each external validation cohort, the area under the receiver operating characteristic curve (AUC) values of the DL-BM and DL-CS models were not significantly different from that of PI-RADS (P > 0.05), whereas the AUC of PIDL-CS was superior to that of PI-RADS (P < 0.05), except for one external validation cohort (P > 0.05). The specificity of PIDL-CS for the detection of csPCa was much higher than that of PI-RADS (P < 0.05). Conclusion Our proposed DL models can be a potential non-invasive auxiliary tool for predicting csPCa. Furthermore, PIDL-CS greatly increased the specificity of csPCa detection compared with PI-RADS assessment by expert radiologists, greatly reducing unnecessary biopsies and helping radiologists achieve a precise diagnosis of csPCa.
PurposeTo determine the predictive performance of the integrated model based on clinical factors and radiomic features for the accurate identification of clinically significant prostate cancer (csPCa) among Prostate Imaging Reporting and Data System (PI-RADS) 3 lesions.Materials and MethodsA retrospective study of 103 patients with PI-RADS 3 lesions who underwent pre-operative 3.0-T MRI was performed. Patients were randomly divided into the training set and the testing set at a ratio of 7:3. Radiomic features were extracted from axial T2WI, diffusion-weighted imaging (DWI), and apparent diffusion coefficient (ADC) images of each patient. The minimum redundancy maximum relevance (mRMR) and least absolute shrinkage and selection operator (LASSO) feature selection methods were used to identify the radiomic features and construct a radiomic model for csPCa identification. Moreover, multivariable logistic regression analysis was used to integrate the clinical factors with radiomic feature model to further improve the accuracy of csPCa identification, and the two are presented in the form of normogram. The performance of the integrated model was compared with radiomic model and clinical model on testing set.ResultsA total of four radiomic features were selected and used for radiomic model construction producing a radiomic score (Radscore). Radscore was significantly different between the csPCa and the non-csPCa patients (training set: p < 0.001; testing set: p = 0.035). Multivariable logistic regression analysis showed that age and PSA could be used as independent predictors for csPCa identification. The clinical–radiomic model produced the receiver operating characteristic (ROC) curve (AUC) in the testing set was 0.88 (95%CI, 0.75–1.00), which was similar to clinical model (AUC = 0.85; 95%CI, 0.52–0.90) (p = 0.048) and higher than the radiomic model (AUC = 0.71; 95%CI, 0.68–1.00) (p < 0.001). The decision curve analysis implies that the clinical–radiomic model could be beneficial in identifying csPCa among PI-RADS 3 lesions.ConclusionThe clinical–radiomic model could effectively identify csPCa among biparametric PI-RADS 3 lesions and thus could help avoid unnecessary biopsy and improve the life quality of patients.
Background The Gleason Grade Group (GG) is essential in assessing the malignancy of prostate cancer (PCa) and is typically obtained by invasive biopsy procedures in which sampling errors could lead to inaccurately scored GGs. With the gradually recognized value of bi‐parametric magnetic resonance imaging (bpMRI) in PCa, it is beneficial to noninvasively predict GGs from bpMRI for early diagnosis and treatment planning of PCa. However, it is challenging to establish the connection between bpMRI features and GGs. Purpose In this study, we propose a dual attention‐guided multiscale neural network (DAMS‐Net) to predict the 5‐scored GG from bpMRI and design a training curriculum to further improve the prediction performance. Methods The proposed DAMS‐Net incorporates a feature pyramid network (FPN) to fully extract the multiscale features for lesions of varying sizes and a dual attention module to focus on lesion and surrounding regions while avoiding the influence of irrelevant ones. Furthermore, to enhance the differential ability for lesions with the inter‐grade similarity and intra‐grade variation in bpMRI, the training process employs a specially designed curriculum based on the differences between the radiological evaluations and the ground truth GGs. Results Extensive experiments were conducted on a private dataset of 382 patients and the public PROSTATEx‐2 dataset. For the private dataset, the experimental results showed that the proposed network performed better than the plain baseline model for GG prediction, achieving a mean quadratic weighted Kappa (Kw) of 0.4902 and a mean positive predictive value of 0.9098 for predicting clinically significant cancer (PPVGG>1). With the application of curriculum learning, the mean Kw and PPVGG>1 further increased to 0.5144 and 0.9118, respectively. For the public dataset, the proposed method achieved state‐of‐the‐art results of 0.5413 Kw and 0.9747 PPVGG>1. Conclusion The proposed DAMS‐Net trained with curriculum learning can effectively predict GGs from bpMRI, which may assist clinicians in early diagnosis and treatment planning for PCa patients.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.