Noninvasive, radiological image-based detection and stratification of Gleason patterns can impact clinical outcomes, treatment selection, and the determination of disease status at diagnosis without subjecting patients to surgical biopsies. We present machine learning-based automatic classification of prostate cancer aggressiveness by combining apparent diffusion coefficient (ADC) and T2-weighted (T2-w) MRI-based texture features. Our approach achieved reasonably accurate classification of Gleason scores (GS) $6\left(3+3\right)$ vs. $\ge 7$ and $7\left(3+4\right)$ vs. $7\left(4+3\right)$ despite the presence of highly unbalanced samples by using two different sample augmentation techniques followed by feature selection-based classification. Our method distinguished between GS $6\left(3+3\right)$ and $\ge 7$ cancers with 93% accuracy for cancers occurring in both peripheral (PZ) and transition (TZ) zones and 92% for cancers occurring in the PZ alone. Our approach distinguished the GS $7\left(3+4\right)$ from GS $7\left(4+3\right)$ with 92% accuracy for cancers occurring in both the PZ and TZ and with 93% for cancers occurring in the PZ alone. In comparison, a classifier using only the ADC mean achieved a top accuracy of 58% for distinguishing GS $6\left(3+3\right)$ vs. GS $\ge 7$ for cancers occurring in PZ and TZ and 63% for cancers occurring in PZ alone. The same classifier achieved an accuracy of 59% for distinguishing GS $7\left(3+4\right)$ from GS $7\left(4+3\right)$ occurring in the PZ and TZ and 60% for cancers occurring in PZ alone. Separate analysis of the cancers occurring in TZ alone was not performed owing to the limited number of samples. Our results suggest that texture features derived from ADC and T2-w MRI together with sample augmentation can help to obtain reasonably accurate classification of Gleason patterns. Significance Gleason scores and ultimately the aggressiveness of prostate cancers determined using transrectal ultrasound (TRUS)-guided biopsy procedures could result in incorrect diagnosis in addition to patient discomfort. The Gleason scores determined from TRUS-guided biopsies often differ from immediate repeat biopsies and the biopsies determined following whole excision of the prostate. Our approach presents a highly accurate and automated method for differentiating between the high ≥7 and low Gleason score 6(3+3), as well as between 7(3+4) and 7(4+3) Gleason score cancers through multiparametric MRI combined with texture features computed on the same images. Noninvasive and accurate techniques such as ours can benefit patient care without subjecting them to unnecessary interventions.

Objective: To analyze patient outcome in the first 14 months of the German natural orifice translumenal endoscopic surgery (NOTES) registry (GNR). Summary Background Data: NOTES is a new surgical concept, which permits scarless intra-abdominal operations through natural orifices, such as the mouth, vagina, rectum, or urethra. The GNR was established as a nationwide outcome database to allow the monitoring and safe introduction of this technique in Germany. Methods: The GNR was designed as a voluntary database with online access. All surgeons in Germany who performed NOTES procedures were requested to participate in the registry. The GNR recorded demographical and therapy data as well as data on the postoperative course. Results: A total of 572 target organs were operated in 551 patients. Cholecystectomies accounted for 85.3% of all NOTES procedures. All procedures were performed in female patients using transvaginal hybrid technique. Complications occurred in 3.1% of all patients, conversions to laparoscopy or open surgery in 4.9%. In cholecystectomies, institutional case volume, obesity, and age had substantial effect on conversion rate, operation length, and length of hospital stay, but no effect on complications. Conclusions: Despite the fact that NOTES has just recently been introduced, the technique has already gained considerable clinical application. Transvaginal hybrid NOTES cholecystectomy is a practicable and safe alternative to laparoscopic resection even in obese or older patients.

The association of brown adipose tissue (BAT) and body fat distribution and their combined effects on metabolic health in humans remains unknown. Here, we retrospectively identify individuals with and without BAT on 18F-fluorodeoxyglucose (18F-FDG) positron emission tomography (PET)/computed tomography (CT) and assemble a propensity score-matched study cohort to compare body fat distribution and determine its role in mediating the benefits of brown fat. We find that BAT is associated with lower amounts of visceral adipose tissue and higher amounts of subcutaneous adipose tissue, resulting in less central obesity. In addition, BAT is independently associated with lower blood glucose and white blood cell count, improved lipids, lower prevalence of type 2 diabetes mellitus, and decreased liver fat accumulation. These observations are most prominent in individuals with central obesity. Our results support a role of BAT in protection from visceral adiposity and improved metabolic health.

CT, fluorine 18 (18F) fluorodeoxyglucose PET, and 18F 16β-fluoro-5-dihydrotestosterone PET provided clinically relevant prognostic information in patients with bone metastases from castration-resistant prostate cancer, and imaging features such as CT lesion morphologic analysis, total number of bone lesions, and degree of androgen receptor expression were significantly associated with patient survival. PurposeTo compare the features of bone metastases at computed tomography (CT) to tracer uptake at fluorine 18 fluorodeoxyglucose (FDG) positron emission tomography (PET) and fluorine 18 16β-fluoro-5-dihydrotestosterone (FDHT) PET and to determine associations between these imaging features and overall survival in men with castration-resistant prostate cancer.Materials and MethodsThis is a retrospective study of 38 patients with castration-resistant prostate cancer. Two readers independently evaluated CT, FDG PET, and FDHT PET features of bone metastases. Associations between imaging findings and overall survival were determined by using univariate Cox proportional hazards regression.ResultsIn 38 patients, reader 1 detected 881 lesions and reader 2 detected 867 lesions. Attenuation coefficients at CT correlated inversely with FDG (reader 1: r = −0.3007; P < .001; reader 2: r = −0.3147; P < .001) and FDHT (reader 1: r = −0.2680; P = .001; reader 2: r = −0.3656; P < .001) uptake. The number of lesions on CT ...

The purpose of this article is to investigate the added value of second-opinion evaluation of prostate MRI by subspecialized genitourinary oncologic radiologists for the assessment of extracapsular extension (ECE) of prostate cancer. We performed a retrospective evaluation of initial and second-opinion radiology reports of 76 patients who underwent MRI of the prostate before prostatectomy for histologically proven prostate cancer. Initial outside reports and second-opinion reports were unpaired and reviewed in random order by a urologist who was blinded to patients' clinical details and histopathologic data. Histopathologic analysis of the prostatectomy specimen served as the reference standard. Among cases with diagnostic-quality images available (71/76; 93%), disagreement between the initial report and the second-opinion report was observed in 30% of cases (21/71; κ = 0.35); in 18 of these 21 cases (86%), histopathologic analysis proved that the second-opinion report was correct. The second-opinion interpretations had statistically significantly higher sensitivity (66% vs 24%; p < 0.0001) than did the initial reports, whereas there was no statistically significant difference in specificity (87% vs 93%; p = 0.317). On ROC curve analysis, the second-opinion reports yielded a statistically significantly higher AUC for the detection of ECE (0.80 vs 0.65; p = 0.004). The reinterpretation of prostate MRI examinations by subspecialized genitourinary oncologic radiologists improved the detection of ECE of prostate cancer.