Nodal metastasis (N1) is a strong prognostic parameter in prostate cancer; however, lymph node evaluation is always incomplete.To study the prognostic value of lymphatic invasion (L1) and whether it might complement or even replace lymph node analysis in clinical practice.Retrospective analysis of pathological and clinical data from 14 528 consecutive patients.Radical prostatectomy.The impact of L1 and N1 on patient prognosis was measured with time to biochemical recurrence as the primary endpoint.Nodal metastases were found in 1602 (12%) of 13 070 patients with lymph node dissection. L1 was seen in 2027 of 14 528 patients (14%) for whom lymphatic vessels had been visualized by immunohistochemistry. N1 and L1 continuously increased with unfavorable Gleason grade, advanced pT stage, and preoperative prostate-specific antigen (PSA) values (p<0.0001 each). N1 was found in 4.3% of 12 501 L0 and in 41% of 2027 L1 carcinomas (p<0.0001). L1 was seen in 11% of 9868 N0 and in 61% of 1360 N1 carcinomas (p<0.0001). Both N1 and L1 were linked to PSA recurrence (p<0.0001 each). This was also true for 17 patients with isolated tumor cells (ie, <200 unequivocal cancer cells without invasive growth) and 193 metastases ≤1mm. Combined analysis of N and L status showed that L1 had no prognostic effect in N1 patients but L1 was strikingly linked to PSA recurrence in N0 patients. N0L1 patients showed a similar outcome as N1 patients.Analysis of lymphatic invasion provides comparable prognostic information than lymph node analysis. Even minimal involvement of the lymphatic system has pivotal prognostic impact in prostate cancer. Thus, a thorough search for lymphatic involvement helps to identify more patients with an increased risk for disease recurrence.Already minimal amounts of tumor cells inside the lymph nodes or intraprostatic lymphatic vessels have a severe impact on patient prognosis.Copyright © 2018 European Association of Urology. Published by Elsevier B.V. All rights reserved.

To assess the role of preoperative multiparametric MRI (mpMRI) of the prostate in the prediction of nodal metastases in patients treated with radical prostatectomy (RP) and extended pelvic lymph node dissection (ePLND).We retrospectively analyzed 101 patients who underwent both preoperative mpMRI of the prostate and RP with ePLND at our institution. For each patient, complete preoperative clinical data and tumour characteristics at mpMRI were recorded. Final histopathologic stage was considered the standard of reference. Univariate and multivariate logistic regression analyses were performed.Nodal metastases were found in 23/101 (22.8%) patients. At univariate analyses, all clinical and radiological parameters were significantly associated to nodal invasion (all p<0.03); tumour volume at MRI (mrV), tumour ADC and tumour T-stage at MRI (mrT) were the most accurate predictors (AUC = 0.93, 0.86 and 0.84, respectively). A multivariate model including PSA levels, primary Gleason grade, mrT and mrV showed high predictive accuracy (AUC = 0.956). Observed prevalence of nodal metastases was very low among tumours with mrT2 stage and mrV<1cc (1.8%).Preoperative mpMRI of the prostate can predict nodal metastases in prostate cancer patients, potentially allowing a better selection of candidates to ePLND.• Multiparametric-MRI of the prostate can predict nodal metastases in prostate cancer • Tumour volume and stage at MRI are the most accurate predictors • Prevalence of nodal metastases is low for T2-stage and <1cc tumours • Preoperative mpMRI may allow a better selection of candidates to lymphadenectomy.

The oncological benefit of pelvic lymph node dissection (PLND) for prostate cancer (PCa) remains unclear. The therapeutic effect of PLND on the elimination of microscopic metastases during radical prostatectomy (RP) for PCa was examined in the current study. A total of 348 Japanese patients with high- or intermediate-risk PCa without lymph node metastasis, who underwent antegrade RP at the Kyushu Cancer Center (Fukuoka, Japan) between August 1998 and May 2013 were retrospectively analyzed. The patients were divided into the standard (obturator + internal iliac nodes) group and the expanded (standard + additional nodes) group according to the extent of PLND. Preoperative and postoperative characteristics were also analyzed to determine the factors associated with prostate-specific antigen (PSA) failure. Standard and expanded PLND were performed in 70.9% (247/348) and 29.1% (101/348) of cases, respectively. The results revealed that preoperative PSA levels were the only marked difference between the two groups. No differences were observed in the other preoperative and postoperative characteristics. Furthermore, the rate of PSA recurrence in each group did not differ to a statistically significant extent (P=0.3622). Reducing the area of dissection from expanded PLND to standard PLND significantly reduced the number of dissected lymph nodes (P<0.0001). Additionally, the PSA level, clinical tumor stage, Gleason score of the biopsy specimen, pathological tumor stage and extent of PLND were all associated with PSA recurrence, as determined via multivariate Cox hazards regression analysis (P=0.0177, P=0.0023, P=0.0027, P<0.0001 and P=0.0164, respectively). In high- and intermediate-risk patients without lymph node metastasis, a greater number of lymph nodes were dissected when the extent of dissection was greater. Furthermore, the extent of PLND was a significantly associated with PSA failure. The results indicated that PLND exerted a therapeutic effect by eliminating microscopic pelvic lymph node metastases that were not detected by routine pathological examinations.Copyright: © Furubayashi et al.

Preoperative pelvic lymph node metastasis (PLNM) prediction can help clinicians determine whether to perform pelvic lymph node dissection (PLND). The purpose of this research is to explore the feasibility of diffusion-weighted imaging (DWI)-based radiomics for preoperative PLNM prediction in PCa patients at the nodal level.The preoperative MR images of 1116 pathologically confirmed lymph nodes (LNs) from 84 PCa patients were enrolled. The subjects were divided into a primary cohort (67 patients with 192 positive and 716 negative LNs) and a held-out cohort (17 patients with 43 positive and 165 negative LNs) at a 4:1 ratio. Two preoperative pelvic lymph node metastasis (PLNM) prediction models were constructed based on automatic LN segmentation with quantitative radiological LN features alone (Model 1) and combining radiological and radiomics features (Model 2) via multiple logistic regression. The visual assessments of junior (Model 3) and senior (Model 4) radiologists were compared.No significant difference was found between the area under the curve (AUCs) of Models 1 and 2 (0.89 vs. 0.90; P = 0.573) in the held-out cohort. Model 2 showed the highest AUC (0.83, 95% CI 0.76, 0.89) for PLNM prediction in the LN subgroup with a short diameter ≤ 10 mm compared with Model 1 (0.78, 95% CI 0.70, 0.84), Model 3 (0.66, 95% CI 0.52, 0.77), and Model 4 (0.74, 95% CI 0.66, 0.88). The nomograms of Models 1 and 2 yielded C-index values of 0.804 and 0.910, respectively, in the held-out cohort. The C-index of the nomogram analysis (0.91) and decision curve analysis (DCA) curves confirmed the clinical usefulness and benefit of Model 2.A DWI-based radiomics nomogram incorporating the LN radiomics signature with quantitative radiological features is promising for PLNM prediction in PCa patients, particularly for normal-sized LNM.© 2022. The Author(s).

To identify which patient with prostate cancer (PCa) could safely avoid extended pelvic lymph node dissection (ePLND) by predicting lymph node invasion (LNI), via a radiomics-based machine learning approach.An integrative radiomics model (IRM) was proposed to predict LNI, confirmed by the histopathologic examination, integrating radiomics features, extracted from prostatic index lesion regions on MRI images, and clinical features via SVM. The study cohort comprised 244 PCa patients with MRI and followed by radical prostatectomy (RP) and ePLND within 6 months between 2010 and 2019. The proposed IRM was trained in training/validation set and evaluated in an internal independent testing set. The model's performance was measured by area under the curve (AUC), sensitivity, specificity, negative predictive value (NPV), and positive predictive value (PPV). AUCs were compared via Delong test with 95% confidence interval (CI), and the rest measurements were compared via chi-squared test or Fisher's exact test.Overall, 17 (10.6%) and 14 (16.7%) patients with LNI were included in training/validation set and testing set, respectively. Shape and first-order radiomics features showed usefulness in building the IRM. The proposed IRM achieved an AUC of 0.915 (95% CI: 0.846-0.984) in the testing set, superior to pre-existing nomograms whose AUCs were from 0.698 to 0.724 (p < 0.05).The proposed IRM could be potentially feasible to predict the risk of having LNI for patients with PCa. With the improved predictability, it could be utilized to assess which patients with PCa could safely avoid ePLND, thus reduce the number of unnecessary ePLND.• The combination of MRI-based radiomics features with clinical information improved the prediction of lymph node invasion, compared with the model using only radiomics features or clinical features. • With improved prediction performance on predicting lymph node invasion, the number of extended pelvic lymph node dissection (ePLND) could be reduced by the proposed integrative radiomics model (IRM), compared with the existing nomograms.© 2022. The Author(s), under exclusive licence to European Society of Radiology.

Medical image registration is an important task in medical image processing. It refers to the process of aligning data sets, possibly from different modalities (e.g., magnetic resonance and computed tomography), different time points (e.g., follow-up scans), and/or different subjects (in case of population studies). A large number of methods for image registration are described in the literature. Unfortunately, there is not one method that works for all applications. We have therefore developed elastix, a publicly available computer program for intensity-based medical image registration. The software consists of a collection of algorithms that are commonly used to solve medical image registration problems. The modular design of elastix allows the user to quickly configure, test, and compare different registration methods for a specific application. The command-line interface enables automated processing of large numbers of data sets, by means of scripting. The usage of elastix for comparing different registration methods is illustrated with three example experiments, in which individual components of the registration method are varied.

Biomedical imaging is a driver of scientific discovery and a core component of medical care and is being stimulated by the field of deep learning. While semantic segmentation algorithms enable image analysis and quantification in many applications, the design of respective specialized solutions is non-trivial and highly dependent on dataset properties and hardware conditions. We developed nnU-Net, a deep learning-based segmentation method that automatically configures itself, including preprocessing, network architecture, training and post-processing for any new task. The key design choices in this process are modeled as a set of fixed parameters, interdependent rules and empirical decisions. Without manual intervention, nnU-Net surpasses most existing approaches, including highly specialized solutions on 23 public datasets used in international biomedical segmentation competitions. We make nnU-Net publicly available as an out-of-the-box tool, rendering state-of-the-art segmentation accessible to a broad audience by requiring neither expert knowledge nor computing resources beyond standard network training.