Assessment of Ankle Fractures using Deep Learning Algorithms and Convolutional Neural Network

Early and accurate detection of ankle fractures is crucial for reducing future complications. Radiographs are the most abundant imaging techniques for assessing fractures. We believe deep learning (DL) methods, through adequately trained deep convolutional neural networks (DCNNs), can assess radiographic images fast and accurate without human intervention. Herein, we aimed to assess the performance of two different DCNNs in detecting ankle fractures using radiographs compared to the ground truth. In this retrospective study, our DCNNs were trained using radiographs obtained from 1050 patients with ankle fracture and the same number of individuals with otherwise healthy ankles. Inception V3 and Renet50 pretrained models were used in our algorithms. Danis-Weber classification method was used. Out of 1050, 72 individuals were labeled as occult fractures as they were not detected in the primary radiographic assessment. Using single-view radiographs was compared with 3-views (anteroposterior, mortise, lateral) for training the DCNNs. Our DCNNs showed a better performance using 3-views images versus single-view based on greater values for accuracy, F-score, and area under the curve (AUC). The sensitivity and specificity in detection of ankle fractures using 3-views were 97.5% and 93.9% using Resnet50 compared to 98.7% and 98.6 using inception V3, respectively. Resnet50 missed 3 occult fractures while Inception V3 missed only one case. Clinical Significance: The performance of our DCNNs showed a promising potential that can be considered in developing the currently used image interpretation programs or as a separate assistant to the clinicians to detect ankle fractures faster and more precisely.

Occult periprosthetic fractures of the acetabulum in THA using an elliptic cup design have no adverse impact on outcome

Occult periprosthetic fractures have been defined as a fracture only visible on postoperative CT scans but not on postoperative plain radiography after an uneventful surgery without intraoperative fracture. The fracture rate for hemispherical and peripheral self-locking cups has been described as 8.4%. We retrospectively analyzed postoperative CT scans after primary THA to clear the question whether such occult periprosthetic fractures of the acetabulum require particular treatment strategy. Between 2014 and 2018 we identified 115 CT scans of 114 patients after primary cementless THA with elliptical cups using a direct anterior approach. The CT scans were obtained as part of other investigations. Localization of the fracture, patients demographics, clinical (WOMAC, Harris Hip Score) and radiological outcome were analyzed. Fracture and non-Fracture group were compared with regard to demographics and short-term outcome after 1 year. Four occult fractures (3.5%) were identified. Three fractures involved the posterior wall. All patients had an uneventful routine postoperative rehabilitation. Patients with occult fractures showed similar post- operative HHS and WOMAC scores at 3 (HHS p = 0.576, WOMAC p = 0.128) and 12 (HHS p = 0.479, WOMAC p = 0.588) months. There were no cup loosening nor radiolucent lines at latest follow-up (mean FU 22 months, range 12-34 months). Clinical and radiological short-term outcome was not impaired by the occurrence of an occult periprosthetic fracture of the acetabulum. The incidental detection of an occult periprosthetic fracture of the acetabulum does not seem to oblige the surgeon to adapt the postoperative regime.

Clinical Analysis of Magnetic Nanoparticle Contrast Agent in the Diagnosis of Occult Fracture by Multislice Spiral CT and MRI

To investigate the differences in the diagnosis and treatment of occult fractures between multi-slice spiral CT (CT) and magnetic resonance imaging (MRI) using I/Fe3O4 nanometer contrast agent. This retrospective study analyzed the clinical data of 60 patients with occult fractures and compared the diagnosis results of multislice CT (observation group) and MRI (control group). All the contrast agents used were I/Fe3O4 nanometer contrast agents. In the control group, 55 cases (91.67%) were detected on T1-weighted imaging versus 58 cases (96.67) on T2-weighted imaging. In the observation group, 47 cases (78.33%) were diagnosed. The intergroup difference was significant (P < 0.05). Clinically, I/Fe3O4 nanometer contrast agent can be used to affect imaging. The detection rate of MRI is higher than that of CT, and the ability to obtain detailed data of occult fractures is better.

Absence of post-traumatic bone marrow edema in the setting of preeclampsia

Magnetic resonance imaging (MRI) is a powerful tool in the diagnosis of missed or occult fractures on radiographic and computed tomography (CT) imaging, through the detection of bone marrow edema. While radiologists often rely on bone marrow edema as a guide for diagnosing subtle underlying fractures, it is important to recognize its limitations as a diagnostic metric. We present a rare case demonstrating the absence of bone marrow edema after acute trauma and confirmed Lisfranc fracture in a patient with preeclampsia and propose an interesting physiologic mechanism to explain this manifestation.