Publications by authors named "H Huisman"
Purpose To validate a deep learning (DL) model for predicting the risk of prostate cancer (PCa) progression based on MRI and clinical parameters and compare it with established models. Materials and Methods This retrospective study included 1607 MRI scans of 1143 male patients (median age, 64 years; IQR, 59-68 years) undergoing MRI for suspicion of clinically significant PCa (csPCa) (International Society of Urological Pathology grade > 1) between January 2012 and May 2022 who were negative for csPCa at baseline MRI. A DL model was developed using baseline MRI and clinical parameters (age, prostate-specific antigen [PSA] level, PSA density, and prostate volume) to predict the time to PCa progression (defined as csPCa diagnosis at follow-up).
View Article and Find Full Text PDFArticle Synopsis
- Biparametric MRI (bpMRI) may serve as a valid alternative to multiparametric MRI (mpMRI) for diagnosing clinically significant prostate cancer (csPCa), as assessed in a large international observer study.
- The study involved 400 mpMRI examinations from four different European centers, where readers evaluated both bpMRI and mpMRI for their ability to accurately diagnose csPCa, finding them to be similarly effective.
- Key findings indicated that bpMRI and mpMRI had comparable diagnostic accuracy (AUROC values) and sensitivity, with bpMRI showing a noninferior performance, though both methods had similar specificity when distinguishing csPCa.
Purpose To determine whether the unsupervised domain adaptation (UDA) method with generated images improves the performance of a supervised learning (SL) model for prostate cancer (PCa) detection using multisite biparametric (bp) MRI datasets. Materials and Methods This retrospective study included data from 5150 patients (14 191 samples) collected across nine different imaging centers. A novel UDA method using a unified generative model was developed for PCa detection using multisite bpMRI datasets.
View Article and Find Full Text PDFArticle Synopsis
- This study investigates the potential for improving the diagnostic accuracy of detecting clinically significant prostate cancer (csPCa) on MRI by incorporating clinical parameters like prostate-specific antigen, prostate volume, and age into deep learning models.
- A total of 932 biparametric MRI exams were analyzed, and various AI models were tested, combining MRI-based deep learning results with the clinical parameters through different methods of data fusion.
- The results showed that the best model, which combined deep learning suspicion levels with clinical features, outperformed other models and had performance comparable to radiologist assessments in identifying csPCa.
Objective: To review the components of past and present active surveillance (AS) protocols, provide an overview of the current studies employing artificial intelligence (AI) in AS of prostate cancer, discuss the current challenges of AI in AS, and offer recommendations for future research.
Methods: Research studies on the topic of MRI-based AI were reviewed to summarize current possibilities and diagnostic accuracies for AI methods in the context of AS. Established guidelines were used to identify possibilities for future refinement using AI.