Validation of AI-driven measurements for hip morphology assessment.

Rationale And Objectives: Accurate assessment of hip morphology is crucial for the diagnosis and management of hip pathologies. Traditional manual measurements are prone to mistakes and inter- and intra-reader variability. Artificial intelligence (AI) could mitigate such issues by providing accurate and reproducible measurements.

Evaluation of a deep learning software for automated measurements on full-leg standing radiographs.

Background: Precise lower limb measurements are crucial for assessing musculoskeletal health; fully automated solutions have the potential to enhance standardization and reproducibility of these measurements. This study compared the measurements performed by BoneMetrics (Gleamer, Paris, France), a commercial artificial intelligence (AI)-based software, to expert manual measurements on anteroposterior full-leg standing radiographs.

Methods: A retrospective analysis was conducted on a dataset comprising consecutive anteroposterior full-leg standing radiographs obtained from four imaging institutions.

Automated weight-bearing foot measurements using an artificial intelligence-based software.

Objective: To assess the accuracy of an artificial intelligence (AI) software (BoneMetrics, Gleamer) in performing automated measurements on weight-bearing forefoot and lateral foot radiographs.

Methods: Consecutive forefoot and lateral foot radiographs were retrospectively collected from three imaging institutions. Two senior musculoskeletal radiologists independently annotated key points to measure the hallux valgus, first-second metatarsal, and first-fifth metatarsal angles on forefoot radiographs and the talus-first metatarsal, medial arch, and calcaneus inclination angles on lateral foot radiographs.

Predictive Factors for Recurrent Hemoptysis after Bronchial Artery Embolization in Patients with Lung Cancer.

Purpose: To identify clinical, radiological, and angiographic characteristics associated with recurrent hemoptysis after bronchial artery embolization (BAE) in patients with lung cancer and severe hemoptysis admitted to the intensive care unit (ICU).

Materials And Methods: A total of 144 consecutive patients with lung cancer who underwent BAE for life-threatening hemoptysis admitted in the ICU between 2014 and 2022 were retrospectively included. Demographics, laboratory values, clinical course, and radiological/angiographic features were compared between those with and without recurrent hemoptysis within 1 month after embolization.

Using AI to Improve Radiologist Performance in Detection of Abnormalities on Chest Radiographs.

Background Chest radiography remains the most common radiologic examination, and interpretation of its results can be difficult. Purpose To explore the potential benefit of artificial intelligence (AI) assistance in the detection of thoracic abnormalities on chest radiographs by evaluating the performance of radiologists with different levels of expertise, with and without AI assistance. Materials and Methods Patients who underwent both chest radiography and thoracic CT within 72 hours between January 2010 and December 2020 in a French public hospital were screened retrospectively.

Virtual Injection Software Reduces Radiation Exposure and Procedural Time of Prostatic Artery Embolization Performed with Cone-Beam CT.

Purpose: To evaluate the impact of virtual injection software (VIS) use during cone-beam computed tomography (CT)-guided prostatic artery embolization (PAE) on both patient radiation exposure and procedural time.

Materials And Methods: This institutional review board (IRB)-approved comparative retrospective study analyzed the treatment at a single institution of 131 consecutive patients from January 2020 to May 2022. Cone-beam CT was used with (Group 1, 77/131; 58.

Performance of Sonoelastography for predicting malignancy in soft tissue.

Background: Separating benign from malignant soft-tissue masses often requires a biopsy. The objective of this study was to assess whether shear-wave elastography (SWE) helped to separate benign from malignant soft-tissue masses.

Methods: In 2015-2016, we prospectively included patients with soft-tissue masses deemed by our multidisciplinary sarcoma board to require a diagnostic biopsy.

Assessment of performances of a deep learning algorithm for the detection of limbs and pelvic fractures, dislocations, focal bone lesions, and elbow effusions on trauma X-rays.

Purpose: To appraise the performances of an AI trained to detect and localize skeletal lesions and compare them to the routine radiological interpretation.

Methods: We retrospectively collected all radiographic examinations with the associated radiologists' reports performed after a traumatic injury of the limbs and pelvis during 3 consecutive months (January to March 2017) in a private imaging group of 14 centers. Each examination was analyzed by an AI (BoneView, Gleamer) and its results were compared to those of the radiologists' reports.

Deep learning to detect anterior cruciate ligament tear on knee MRI: multi-continental external validation.

Objectives: To develop a deep-learning algorithm for anterior cruciate ligament (ACL) tear detection and to compare its accuracy using two external datasets.

Methods: A database of 19,765 knee MRI scans (17,738 patients) issued from different manufacturers and magnetic fields was used to build a deep learning-based ACL tear detector. Fifteen percent showed partial or complete ACL rupture.

Clinical guidelines and care pathway for management of low back pain with or without radicular pain.

Objective: To develop guidelines for low back pain management according to previous international guidelines and the updated literature.

Methods: A report was compiled from a review of systematic reviews of guidelines published between 2013 and 2018 and meta-analysis of the management of low back pain published between 2015 and 2018. This report summarized the state-of-the-art scientific knowledge for each predefined area of the guidelines from a critical review of selected literature.

Can T2-weighted Dixon fat-only images replace T1-weighted images in degenerative disc disease with Modic changes on lumbar spine MRI?

Objectives: To evaluate the diagnostic performance and interobserver agreement of a magnetic resonance imaging (MRI) protocol that only includes sagittal T2-weighted Dixon fat and water images as an alternative to a standard protocol that includes both sagittal T1-weighted sequence and T2-weighted Dixon water images as reference standard in lumbar degenerative disc disease with Modic changes.

Methods: From February 2017 to March 2019, 114 patients who underwent lumbar spine MRI for low back pain were included in this retrospective study. All MRI showed Modic changes at least at one vertebral level.

Assessment of an AI Aid in Detection of Adult Appendicular Skeletal Fractures by Emergency Physicians and Radiologists: A Multicenter Cross-sectional Diagnostic Study.

Background The interpretation of radiographs suffers from an ever-increasing workload in emergency and radiology departments, while missed fractures represent up to 80% of diagnostic errors in the emergency department. Purpose To assess the performance of an artificial intelligence (AI) system designed to aid radiologists and emergency physicians in the detection and localization of appendicular skeletal fractures. Materials and Methods The AI system was previously trained on 60 170 radiographs obtained in patients with trauma.

Limiting radiation exposure during prostatic arteries embolization: influence of patient characteristics, anatomical conditions, and technical factors.

Objective: To assess the influence of patient characteristics, anatomical conditions, and technical factors on radiation exposure during prostatic arteries embolization (PAE) performed for benign prostatic hyperplasia.

Materials And Methods: Patient characteristics (age, body mass index (BMI)), anatomical conditions (number of prostatic arteries, anastomosis), and technical factors (use of cone beam computed tomography (CBCT), large display monitor (LDM), and magnification) were recorded as well as total air kerma (AK), dose area product (DAP), fluoroscopy time (FT), and number of acquisitions (NAcq). Associations between potential dose-influencing factors and AK using univariate analysis and a multiple linear regression model were assessed.

Predictors of favorable outcome after mechanical thrombectomy for anterior circulation acute ischemic stroke in octogenarians.

Introduction: Mechanical thrombectomy for anterior circulation large vessel occlusion (LVO) improves functional outcome at three months. This therapeutic approach is the new gold standard, with a benefit being also observed in elderly patients. However, data are limited in this heterogeneous and fragile population.

Therapeutic outcome of CT-guided radiofrequency ablation in patients with osteoid osteoma.

Objective: To assess the long-term outcome of computed tomography-guided radiofrequency ablation (CT-guided RFA) in patients with suspected osteoid osteoma (OO).

Materials And Methods: Single-center retrospective study. Patients with clinical suspicion and imaging diagnosis of osteoid osteoma were treated by CT-guided RFA using the same device with either a 7- or 10-mm active tip electrode.

ASPECTS (Alberta Stroke Program Early CT Score) Assessment of the Perfusion-Diffusion Mismatch.

Background And Purpose: Rapid and reliable assessment of the perfusion-weighted imaging (PWI)/diffusion-weighted imaging (DWI) mismatch is required to promote its wider application in both acute stroke clinical routine and trials. We tested whether an evaluation based on the Alberta Stroke Program Early CT Score (ASPECTS) reliably identifies the PWI/DWI mismatch.

Methods: A total of 232 consecutive patients with acute middle cerebral artery stroke who underwent pretreatment magnetic resonance imaging (PWI and DWI) were retrospectively evaluated.

Progressive development of renal cysts in glycogen storage disease type I.

Glycogen storage disease type I (GSDI) is a rare metabolic disease due to glucose-6 phosphatase deficiency, characterized by fasting hypoglycemia. Patients also develop chronic kidney disease whose mechanisms are poorly understood. To decipher the process, we generated mice with a kidney-specific knockout of glucose-6 phosphatase (K.