Adequate detection of the histopathological extraprostatic extension (EPE) of prostate cancer (PCa) remains a challenge using conventional radiomics on 3 Tesla multiparametric magnetic resonance imaging (3T mpMRI). This study focuses on the assessment of artificial intelligence (AI)-driven models with innovative MRI radiomics in predicting EPE of prostate cancer (PCa) at a lesion-specific level. With a dataset encompassing 994 lesions from 794 PCa patients who underwent robot-assisted radical prostatectomy (RARP) at two Dutch hospitals, the study establishes and validates three classification models. The models were validated on an internal validation cohort of 162 lesions and an external validation cohort of 189 lesions in terms of discrimination, calibration, net benefit, and comparison to radiology reporting. Notably, the achieved AUCs ranged from 0.86 to 0.91 at the lesion-specific level, demonstrating the superior accuracy of the random forest model over conventional radiological reporting. At the external test cohort, the random forest model was the best-calibrated model and demonstrated a significantly higher accuracy compared to radiological reporting (83% vs. 67%, p = 0.02). In conclusion, an AI-powered model that includes both existing and novel MRI radiomics improves the detection of lesion-specific EPE in prostate cancer.

Manual contouring of neurovascular structures on prostate magnetic resonance imaging (MRI) is labor-intensive and prone to considerable interrater disagreement. Our aim is to contour neurovascular structures automatically on prostate MRI by deep learning (DL) to improve workflow and interrater agreement. Segmentation of neurovascular structures was performed on pre-treatment 3.0 T MRI data of 131 prostate cancer patients (training [n = 105] and testing [n = 26]). The neurovascular structures include the penile bulb (PB), corpora cavernosa (CCs), internal pudendal arteries (IPAs), and neurovascular bundles (NVBs). Two DL networks, nnU-Net and DeepMedic, were trained for auto-contouring on prostate MRI and evaluated using volumetric Dice similarity coefficient (DSC), mean surface distances (MSD), Hausdorff distances, and surface DSC. Three radiation oncologists evaluated the DL-generated contours and performed corrections when necessary. Interrater agreement was assessed and the time required for manual correction was recorded. nnU-Net achieved a median DSC of 0.92 (IQR: 0.90–0.93) for the PB, 0.90 (IQR: 0.86–0.92) for the CCs, 0.79 (IQR: 0.77–0.83) for the IPAs, and 0.77 (IQR: 0.72–0.81) for the NVBs, which outperformed DeepMedic for each structure (p < 0.03). nnU-Net showed a median MSD of 0.24 mm for the IPAs and 0.71 mm for the NVBs. The median interrater DSC ranged from 0.93 to 1.00, with the majority of cases (68.9%) requiring manual correction times under two minutes. DL enables reliable auto-contouring of neurovascular structures on pre-treatment MRI data, easing the clinical workflow in neurovascular-sparing MR-guided radiotherapy.

Background: Pelvic morphological parameters on magnetic resonance imaging (MRI), such as the membranous urethral length (MUL), can predict urinary incontinence after radical prostatectomy but are prone to interobserver disagreement. Our objective was to improve interobserver agreement among radiologists in measuring pelvic parameters using deep learning (DL)-based segmentation of pelvic structures on MRI scans. Methods: Preoperative MRI was collected from 167 prostate cancer patients undergoing radical prostatectomy within our regional multicentric cohort. Two DL networks (nnU-Net) were trained on coronal and sagittal scans and evaluated on a test cohort using an 80/20% train-test split. Pelvic parameters were manually measured by three abdominal radiologists on raw MRI images and with the use of DL-generated segmentations. Automated measurements were also performed for the pelvic parameters. Interobserver agreement was evaluated using the intraclass correlation coefficient (ICC) and the Bland–Altman plot. Results: The DL models achieved median Dice similarity coefficient (DSC) values of 0.85–0.97 for coronal structures and 0.87–0.98 for sagittal structures. When radiologists used DL-generated segmentations of pelvic structures, the interobserver agreement for sagittal MUL improved from 0.64 (95% confidence interval 0.28–0.83) to 0.91 (95% CI 0.84–0.95). Furthermore, there was an increase in ICC values for the obturator internus muscle from 0.74 (95% CI 0.42–0.87) to 0.86 (95% CI 0.75–0.92) and for the levator ani muscle from 0.40 (95% CI 0.05–0.66) to 0.61 (95% CI 0.31–0.78). Conclusions: DL-based automated segmentation of pelvic structures improved interobserver agreement in measuring pelvic parameters on preoperative MRI scans. Relevance statement: The implementation of deep learning segmentations allows for more consistent measurements of pelvic parameters by radiologists. Standardized measurements are crucial for incorporating these parameters into urinary continence prediction models. Key points: • DL-generated segmentations improve interobserver agreement for pelvic measurements among radiologists. • Membranous urethral length measurement improved from substantial to almost perfect agreement. • Artificial intelligence enhances objective pelvic parameter assessment for continence prediction models. Graphical

A sub-fractionation workflow enables a substantial reduction in planning target volume (PTV) margin in prostate cancer (PCa) patients by reducing systematic motion during magnetic resonance (MR)-guided radiotherapy. This study assessed geometric and reconstructed dose outcomes in patients treated with a tight-margin sub-fractionation workflow on a combined linear accelerator with a 1.5 T MRI scanner (MR-Linac). We evaluated the sub-fractionation workflow with tight margins (2–3 mm) on 128 PCa patients who completed treatment with 5 × 7.25 Gy (36.25 Gy total dose). A traffic light protocol was applied based on residual motions to detect patients with unexpectedly large motions. When ’red’ traffic light criteria were met, plans with larger margins (5 mm isotropic) were adopted for subsequent fractions. Intra- and inter-fraction dose accumulation was performed via an in-house developed deformable image registration algorithm. A total of 89 % (114/128) of patients completed treatment with the initial tight margins. The mean 3D intrafraction shifts were 1.0 mm (SD: 0.6 mm) in the group with the tight margins and 1.9 mm (SD: 1.5 mm) in the patient group who switched to large margins. The median accumulated D99% was 34.9 Gy (interquartile range: 34.0–35.3 Gy) for patients with prostate shifts who switched to larger margins. In 57 % (8/14) of these patients, the accumulated D99% was above the threshold of 34.4 Gy. Tight margins of 2–3 mm can be safely applied for at least 95 % (122/128) of the PCa patients undergoing a sub-fractionation workflow on a 1.5 T MR-linac.