Khosravi, Bardia

Background: Establishing imaging registries for large patient cohorts is challenging because manual labeling is tedious and relying solely on DICOM (digital imaging and communications in medicine) metadata can result in errors. We endeavored to establish an automated hip and pelvic radiography registry of total hip arthroplasty (THA) patients by utilizing deep-learning pipelines. The aims of the study were (1) to utilize these automated pipelines to identify all pelvic and hip radiographs with appropriate annotation of laterality and presence or absence of implants, and (2) to automatically measure acetabular component inclination and version for THA images. Methods: We retrospectively retrieved 846,988 hip and pelvic radiography DICOM files from 20,378 patients who underwent primary or revision THA performed at our institution from 2000 to 2020. Metadata for the files were screened followed by extraction of imaging data. Two deep-learning algorithms (an EfficientNetB3 classifier and a YOLOv5 object detector) were developed to automatically determine the radiographic appearance of all files. Additional deep-learning algorithms were utilized to automatically measure the acetabular angles on anteroposterior pelvic and lateral hip radiographs. Algorithm performance was compared with that of human annotators on a random test sample of 5,000 radiographs. Results: Deep-learning algorithms enabled appropriate exclusion of 209,332 DICOM files (24.7%) as misclassified non-hip/pelvic radiographs or having corrupted pixel data. The final registry was automatically curated and annotated in <8 hours and included 168,551 anteroposterior pelvic, 176,890 anteroposterior hip, 174,637 lateral hip, and 117,578 oblique hip radiographs. The algorithms achieved 99.9% accuracy, 99.6% precision, 99.5% recall, and a 99.6% F1 score in determining the radiograph appearance. Conclusions: We developed a highly accurate series of deep-learning algorithms to rapidly curate and annotate THA patient radiographs. This efficient pipeline can be utilized by other institutions or registries to construct radiography databases for patient care, longitudinal surveillance, and large-scale research. The stepwise approach for establishing a radiography registry can further be utilized as a workflow guide for other anatomic areas. Level of Evidence: Diagnostic Level IV . See Instructions for Authors for a complete description of levels of evidence.

Abstract Background Differentiating ulcerative colitis-associated “backwash” ileitis (BWI) from Crohn’s terminal ileitis (CTI) is a diagnostic challenge and highly affects patient’s management. This study aimed to investigate magnetic resonance enterography (MRE) features including ileocecal valve patency index (ICPI) in patients with BWI and CTI and distinguish these entities based on MRE findings. Methods After obtaining institutional review board approval, we reviewed 1654 MREs; 60 patients with pathologically proven BWI (n = 30) and CTI (n = 30) were enrolled. Two radiologists who were blinded to the clinical diagnosis analyzed MREs. We evaluated bowel wall thickness and enhancement pattern, ileocecal valve (ICV) diameter, and lip thickness. Ileocecal valve patency index-T and ICPI-C were calculated to normalize the ICV diameter with respect to terminal ileum (TI) and cecum, respectively. An additional group of non-BWI-UC patients (n = 30) was also included to validate indices. Results Circumferential mural thickening (90% vs 1%, P &lt; .001) and inner-wall enhancement (P &lt; .001) of TI were more frequent in BWI patients than CTI. Serosal irregularity (53% vs 13%, P = .002), higher mural thickness (5mm vs 3mm, P &lt; .001), and asymmetric hyperenhancement (P &lt; .001) of TI were more prevalent in CTI than BWI. Ileocecal valve patency and lip atrophy were significantly higher in BWI than CTI and non-BWI-UC groups (both P &lt; .001). Ileocecal valve patency indices-C and ICPI-T indices were able to accurately distinguish BWI from CTI (area under the ROC curve [AUC], 0.864 and 0.847 for ICPI-T and ICPI-C, respectively) and non-BWI-UC (AUC, 0.777 and 0.791 for ICPI-T and ICPI-C, respectively). Ileocecal valve patency indices-T ≥31.5% were 100% specific to distinguish BWI from CTI, but sensitivity was 63%. Conclusions Magnetic resonance enterography features of ICV and TI can accurately differentiate BWI from CTI. Two practical indices introduced in this study showed high specificity to distinguish BWI from CTI.