Extramural venous invasion: a novel magnetic resonance imaging biomarker for adverse pathology in bladder cancer.

Extramural venous invasion (EMVI) recognized on magnetic resonance imaging (MRI) is an unequivocal biomarker for detecting adverse outcomes in rectal cancer: however it has not yet been explored in the area of bladder cancer. In this study, we assessed the feasibility of identifying EMVI findings on MRI in patients with bladder cancer and its avail in identifying adverse pathology. In this single-institution retrospective study, the MRI findings inclusive of EMVI was described in patients with bladder cancer that had available imaging between January 2018 and June 2020. Patient demographic and clinical information were retrieved from our electronic medical records system. Histopathologic features frequently associated with poor outcomes including lymphovascular invasion (LVI), variant histology, muscle invasive bladder cancer (MIBC), and extravesical disease (EV) were compared to MRI-EMVI. A total of 38 patients were enrolled in the study, with a median age of 73 years (range 50-101), 76% were male and 23% were females. EMVI was identified in 23 (62%) patients. There was a significant association between EMVI and MIBC (OR = 5.30, CI = 1.11-25.36; P = 0.036), and extravesical disease (OR = 17.77, CI = 2.37-133; P = 0.005). We found a higher probability of presence of LVI and histologic variant in patients with EMVI. EMVI had a sensitivity, specificity, negative predictive value (NPV) and positive predictive value (PPV) of 90%, 73%, 94% and 63% respectively in detecting extravesical disease. Our study suggests, EMVI may be a useful biomarker in bladder cancer imaging, is associated with adverse pathology, and could be potentially integrated in the standard of care with regards to MRI reporting systems. A larger study sample size is further warranted to assess feasibility and applicability.

MRI and CT bladder segmentation from classical to deep learning based approaches: Current limitations and lessons.

Precise determination and assessment of bladder cancer (BC) extent of muscle invasion involvement guides proper risk stratification and personalized therapy selection. In this context, segmentation of both bladder walls and cancer are of pivotal importance, as it provides invaluable information to stage the primary tumor. Hence, multiregion segmentation on patients presenting with symptoms of bladder tumors using deep learning heralds a new level of staging accuracy and prediction of the biologic behavior of the tumor. Nevertheless, despite the success of these models in other medical problems, progress in multiregion bladder segmentation, particularly in MRI and CT modalities, is still at a nascent stage, with just a handful of works tackling a multiregion scenario. Furthermore, most existing approaches systematically follow prior literature in other clinical problems, without casting a doubt on the validity of these methods on bladder segmentation, which may present different challenges. Inspired by this, we provide an in-depth look at bladder cancer segmentation using deep learning models. The critical determinants for accurate differentiation of muscle invasive disease, current status of deep learning based bladder segmentation, lessons and limitations of prior work are highlighted.