A User Interface for Optimizing Radiologist Engagement in Image Data Curation for Artificial Intelligence.

PURPOSE: To delineate image data curation needs and describe a locally designed graphical user interface (GUI) to aid radiologists in image annotation for artificial intelligence (AI) applications in medical imaging. MATERIALS AND METHODS: GUI components support image analysis toolboxes, picture archiving and communication system integration, third-party applications, processing of scripting languages, and integration of deep learning libraries. For clinical AI applications, GUI components included two-dimensional segmentation and classification; three-dimensional segmentation and quantification; and three-dimensional segmentation, quantification, and classification. To assess radiologist engagement and performance efficiency associated with GUI-related capabilities, image annotation rate (studies per day) and speed (minutes per case) were evaluated in two clinical scenarios of varying complexity: hip fracture detection and coronary atherosclerotic plaque demarcation and stenosis grading. RESULTS: For hip fracture, 1050 radiographs were annotated over 7 days (150 studies per day; median speed: 10 seconds per study [interquartile range, 3-21 seconds per study]). A total of 294 coronary CT angiographic studies with 1843 arteries and branches were annotated for atherosclerotic plaque over 23 days (15.2 studies [80.1 vessels] per day; median speed: 6.08 minutes per study [interquartile range, 2.8-10.6 minutes per study] and 73 seconds per vessel [interquartile range, 20.9-155 seconds per vessel]). CONCLUSION: GUI-component compatibility with common image analysis tools facilitates radiologist engagement in image data curation, including image annotation, supporting AI application development and evolution for medical imaging. When complemented by other GUI elements, a continuous integrated workflow supporting formation of an agile deep neural network life cycle results.Supplemental material is available for this article.© RSNA, 2019.

Calcaneal Avulsion Fractures: An Often Forgotten Diagnosis.

OBJECTIVE: The calcaneus is the primary weight bearing bone in the heel, and its many surface contours render it a relatively difficult bone to visualize in its entirety. The stabilizing ligaments that hold the calcaneus in place occupy very specific locations, and the Achilles tendon enthesis is in a relatively constant location; therefore, avulsion fractures occur in reproducible locations. CONCLUSION: The mechanisms of injuries include overuse and neuropathic conditions, although most cases are related to trauma.

Pitfalls in diagnosis: skeletal holes, clefts, and notches.

Radiographs often depict unusually appearing variations in the skeleton that have the appearance of holes, clefts, and prominent notches. Although certain variants are recognizable, others may not be as familiar. Knowledge of characteristic locations of nutrient foramina is also important. The aim of this pictorial essay are to review the anatomic variants in the trunk of the skeleton that manifest as holes, cleft, or notches in the bone and to specify the differentiating features of these variants from those that constitute true pathologic conditions.

MRI of isolated cuboid stress fractures in adults.

OBJECTIVE: Isolated cuboid stress fractures are rare. The purpose of this study was to evaluate the MRI appearance of this condition. MATERIALS AND METHODS: A retrospective search for patients with the diagnosis of a cuboid stress fracture was performed for a 19-year period. All patients underwent an initial three-view radiographic foot series for pain. MRI was performed because symptoms persisted beyond 4 weeks. RESULTS: Ten patients, nine of whom were women, were diagnosed with isolated cuboid stress fractures. These patients were divided into an athletic group (mean age, 36.3 years) and nonathletic group (mean age, 55.0 years). In the athletic group, there were five runners, one ballet dancer, and one gymnast, and in the nonathletic group, there was one with osteoporosis, one with a plantar fascia rupture, and one who recently underwent a fasciotomy. Eight stress fractures were linear and two were stellate and all were surrounded by marrow edema. Six fractures were located inferolaterally, one superolaterally, one laterally, one medially, and one was subchondral in location. All but one involved the peroneal sulcus and cuboid crest region. Nine of 10 feet showed pathology in the plantar fascia, seven in the peroneal tendons, and four in the posterior tibial tendon. CONCLUSION: An isolated stress fracture of the cuboid is most likely to occur in the lateral aspect of the cuboid. The cause is likely multifactorial and may include compressive and tensile forces, but plantar fascia dysfunction and age-related bone loss, which are more prevalent in women, may be additional contributing factors.