Epidural Hematoma

Value Proposition

Epidural hematomas are typically post-traumatic, resulting from direct blunt trauma to the skull. They are frequently associated with overlying skull fractures. They can occur in patients of any demographic but are more common in the young. They can compress the adjacent brain, causing midline shift and central downward brain herniation, leading to increased intracranial pressure (ICP), brainstem compression and death if untreated. Epidural hematomas are critical to identify and manage as quickly as possible, since they are typically associated with injury to a dural artery and can quickly increase in size. Identifying them as soon as possible can significantly improve patient outcomes. In emergency situations, automated identification and classification of epidural hematomas would assist case prioritization and interpretation. In busy private practices, outpatient CT scans that potentially demonstrate epidural hematomas may not be reviewed for days after completion, delaying management and potentially leading to poor patient outcomes. Automated identification and classification would also provide value to non-specialists, especially those who read images in emergency situations.

Narrative

A 17-year-old male is skiing without a helmet and catches an edge on the icy slope. He falls and lands on his side, hitting his head against the hard ice. He feels dazed and a bit dizzy but does not lose consciousness. The ski patrol takes him to the nearest care station where he is assessed. He still feels a bit dizzy and has a severe headache. A large subcutaneous hematoma is noted along his right temple. He is sent to the nearest community hospital for evaluation, where a CT scan is ordered.

Workflow Description

Patient receives a CT of their head; the clinical indication will usually be head trauma. Algorithm receives entire CT dataset. If the algorithm can determine a result, return: size, location (R/L; frontal/parietal/temporal/occipital/parafalcine/cerebellar), density of the epidural hematoma. A reliability metric, assessing the accuracy of the size measurement, would also be helpful. An alert should notify the user.
Additional considerations are as follows: Algorithm executes after exam is verified on PACS in the backend. Algorithm optimally integrates on PACS and dictation or reporting software. The user is able to automatically populate the report or manually input the results. Indicator image may save to PACS as part of the medical record.

Inputs

DICOM Study

Primary Outputs

Hematoma Shape/Configuration

Hematoma Laterality

Hematoma Location

Hematoma Width

Hematoma Volume

Hematoma Density 

Hematoma Septations