Computational Detection of Extraprostatic Extension of Prostate Cancer on Multiparametric MRI Using Deep Learning.

The localization of extraprostatic extension (EPE), i.e., local spread of prostate cancer beyond the prostate capsular boundary, is important for risk stratification and surgical planning. However, the sensitivity of EPE detection by radiologists on MRI is low (57% on average). In this paper, we propose a method for computational detection of EPE on multiparametric MRI using deep learning. Ground truth labels of cancers and EPE were obtained in 123 patients (38 with EPE) by registering pre-surgical MRI with whole-mount digital histopathology images from radical prostatectomy. Our approach has two stages. First, we trained deep learning models using the MRI as input to generate cancer probability maps both inside and outside the prostate. Second, we built an image post-processing pipeline that generates predictions for EPE location based on the cancer probability maps and clinical knowledge. We used five-fold cross-validation to train our approach using data from 74 patients and tested it using data from an independent set of 49 patients. We compared two deep learning models for cancer detection: (i) UNet and (ii) the Correlated Signature Network for Indolent and Aggressive prostate cancer detection (CorrSigNIA). The best end-to-end model for EPE detection, which we call EPENet, was based on the CorrSigNIA cancer detection model. EPENet was successful at detecting cancers with extraprostatic extension, achieving a mean area under the receiver operator characteristic curve of 0.72 at the patient-level. On the test set, EPENet had 80.0% sensitivity and 28.2% specificity at the patient-level compared to 50.0% sensitivity and 76.9% specificity for the radiologists. To account for spatial location of predictions during evaluation, we also computed results at the sextant-level, where the prostate was divided into sextants according to standard systematic 12-core biopsy procedure. At the sextant-level, EPENet achieved mean sensitivity 61.1% and mean specificity 58.3%. Our approach has the potential to provide the location of extraprostatic extension using MRI alone, thus serving as an independent diagnostic aid to radiologists and facilitating treatment planning.

Renal Forniceal Rupture in the Setting of Obstructing Ureteral Stones: An Analysis of Stone Characterization and Urologic Intervention Pattern.

Introduction and Objective: Forniceal rupture due to obstructing ureterolithiasis (FROU) is a seldom encountered radiographic finding, but the impact of this diagnosis and influence on stone management has not been well studied in the literature. The purpose of the study is to examine stone characteristics and intervention patterns of patients with radiographic evidence of FROU. Materials and Methods: A retrospective analysis of all patients with radiographic evidence of FROU was compared with patients with obstructing ureteral stones without forniceal ruptures (noFROU). All patients presented to our Emergency Department from January 2015 until December 2018. Data analyzed included patient demographics, clinical presentation, stone characteristics, and management pattern. Primary outcome was need for hospital admission and surgical intervention. Results: Thirty-two patients with FROU (mean age = 45) were compared with 50 patients with noFROU (mean age = 57). Univariate analysis revealed that age, history of diabetes mellitus, history of hypertension, days of symptoms, degree of hydronephrosis, and degree of perinephric stranding were associated with forniceal rupture (p ≤ 0.05). On multivariate analysis, only degree of perinephric stranding remained significant (p ≤ 0.05). Average maximum axial stone diameter in the FROU group was 5.1 mm vs 4.7 mm in the noFROU group (p = 0.66). Overall, 68.8% of stones were located within the distal ureter in the FROU group vs 48.8% in the noFROU group (p = 0.09). There was no difference in hospital admission (FROU 37.5% vs noFROU 44%, p = 0.56) and need for surgical intervention (FROU 50% vs noFROU 48%, p = 0.86). There were no 30-day complications in patients with FROU. Conclusions: Ureteral stone location and size does not seem to impact the presence of FROU. FROU may be an alarming reported finding but its presence does not appear to impact clinical outcomes or affect urological management, including admission or need for urologic intervention.

Effect of the experience of surgical chairpersons on departmental National Institutes of Health funding.

BACKGROUND: Experience and application of recruitment packages can be critical in leadership efforts of surgical chairpersons in promoting research, although attrition of these efforts can happen over time due to lack of new resources. We aimed to examine the impact of experience of surgical chairpersons on departmental National Institutes of Health (NIH) funding. METHODS: Experience as a chairperson defined as the number of years spent as an interim or permanent chair was abstracted from the department Web site (US medical schools only). The NIH funding (US dollars) of the departments were obtained from the Blue Ridge Medical Institute (www.brimr.org). The change in NIH funding from the immediate previous financial year (2010-2009 and 2011-2010) was used to classify chairpersons into four groups: group 1 (-/-), group 2 (-/+), group 3 (+/+), and group 4 (+/-) for analysis. RESULTS: Median NIH funding were $1.9 (0.7-6) million, $1.8 (0.6-5) million, and $1.7 (0.7-5) million for 2009, 2010, and 2011, respectively, and the median experience as a surgical chairperson was 6 y (3-10). Recent chairpersons (<1 y) inherited departments that usually lost NIH funding (62%) and were frequently unable to develop a positive trend for growth over the next fiscal year ([-/-] n = 4 and [+/-] n = 2, 75%). Chairpersons who held their positions for 4-6 y were most likely to be associated with trends of positive funding growth, whereas chairpersons >10 y were most likely to have lost funding (66%, P = 0.07). CONCLUSIONS: Provision of new development dollars later in their tenure and retention of chairpersons might lead to more positive trends in increase in NIH funding.

Role of laparoscopy in patients with peritoneal metastases considered for cytoreductive surgery and hyperthermic intraperitoneal chemotherapy (HIPEC).

BACKGROUND: We hypothesized that diagnostic laparoscopy (DL) was feasible for the evaluation of patients with peritoneal carcinomatosis (PC) undergoing cytoreductive surgery and hyperthermic intraperitoneal chemotherapy (CRS + HIPEC). METHODS: A retrospective review of PC patients treated from January 2010 to April 2013 was conducted. Data on tumor characteristics, treatment details and survival outcomes were extracted and analyzed. RESULTS: Of the 101 PC patients (mean age 52.9 ± 14.1 years), 73 diagnostic laparoscopies DL (61 concurrent with CRS + HIPEC) were performed in 70 patients whereas 31 patients underwent direct exploratory laparotomy (EL). Complete laparoscopic assessment was possible in 63 cases (86.3%), resulting in 18 exclusions (27.7%) while 10 cases were converted to open due to inadequate laparoscopic visualization. Subsequently, CRS + HIPEC was performed in 85.4% (of 55 selected for HIPEC, DL) versus 74.2% (EL, P value = 0.20). Among those excluded from HIPEC at the initial operation, delayed HIPEC after conversion chemotherapy was achieved in 6 (of 11 with extensive disease, DL). The incidence of grade 3 to 5 complications was 0% DL versus 10% EL (P value = 0.2). There were no port site recurrences at mean follow up of 9.1 ± 8 months. CONCLUSIONS: Laparoscopy is a feasible technique for selecting patients with PC for CRS + HIPEC, and can help select patients for conversion chemotherapy in the setting of high peritoneal carcinomatosis index (PCI) score.