Automated pelvic MRI measurements associated with urinary incontinence for prostate cancer patients undergoing radical prostatectomy.

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.

Comparison of MRI Activity Scoring Systems and Features for the Terminal Ileum in Patients With Crohn Disease.

OBJECTIVE: The purpose of this study was to evaluate four previously validated MRI activity scoring systems for diagnosis and grading of Crohn disease (CD) in the terminal ileum against an endoscopic and histopathologic reference standard. SUBJECTS AND METHODS: Ethics approval and written informed consent were obtained. Subjects with known or suspected CD were prospectively recruited between December 2011 and August 2014. Each patient underwent MRI and ileocolonoscopy with terminal ileum biopsies. Four MRI scoring systems (Magnetic Resonance Index of Activity [MaRIA], Clermont score, London score, and Crohn disease MRI Index) and component features were applied by two observers and correlated to the Crohn disease endoscopic index of severity (CDEIS, 0-44) and histopathologic endoscopic acute inflammation score (0-6). Interobserver agreement (weighted kappa and intraclass correlation coefficient [ICC]) and diagnostic accuracy for active and ulcerating endoscopic or histopathologic disease were evaluated. RESULTS: Ninety-eight patients (median age, 32 years old; 55 women, 43 men) were included. All four scoring systems showed good interobserver agreement (ICC = 0.70-0.78), moderate-to-strong correlation to CDEIS (r = 0.57-0.67) and weak-to-moderate correlation to endoscopic acute inflammation score (r = 0.38-0.49). Scoring systems' diagnostic accuracy for active and ulcerating endoscopic disease ranged from 73% to 78% and 71% to 76%, respectively, whereas for active histopathologic disease accuracy ranged from 65% to 72%. Between the scoring systems, no significant differences were found for both observers regarding interobserver agreement, correlation coefficients, and diagnostic accuracy. CONCLUSION: All scoring systems were comparable in terms of interobserver agreement, correlation to the endoscopic and histopathologic reference standard, and diagnostic accuracy. The London score, MaRIA, and Clermont score have the additional benefit of having validated cutoff values for both active and ulcerating endoscopic disease.

Acute appendagitis of the ligamentum teres hepatis: clinical, ultrasound, and computed tomographic findings.

PURPOSE: To describe the clinical, ultrasound (US), and CT findings in three patients with acute appendagitis of the ligamentum teres hepatis. METHODS: A retrospective search of cases over a 4-year period was performed and yielded three patients with acute appendagitis of the ligamentum teres hepatis. The diagnosis was confirmed by US, CT, and clinical follow-up in all three cases. We retrospectively noted the laboratory data, clinical findings, and presumptive clinical diagnosis and describe the US and CT findings. RESULTS: All three patients presented with severe, circumscribed epigastric pain without other symptoms. The complex reactive protein was not elevated or only mildly elevated. At the spot of maximum pain, US and CT showed all signs of an acute appendagitis; however, the pain was not close to colon, but close to the teres ligament. Symptoms resolved within 1 to 2 weeks without therapy. CONCLUSIONS: Acute appendagitis of the teres ligament is not as rare as previously assumed. Familiarity with the US and CT features enables a reliable diagnosis and prevents unnecessary medical or operative treatment.