Retrospective analysis and prospective validation of an AI-based software for intracranial haemorrhage detection at a high-volume trauma centre.

Rapid detection of intracranial haemorrhage (ICH) is crucial for assessing patients with neurological symptoms. Prioritising these urgent scans for reporting presents a challenge for radiologists. Artificial intelligence (AI) offers a solution to enable radiologists to triage urgent scans and reduce reporting errors. This study aims to evaluate the accuracy of an ICH-detection AI software and whether it benefits a high-volume trauma centre in terms of triage and reducing diagnostic errors. A peer review of head CT scans performed prior to the implementation of the AI was conducted to identify the department's current miss-rate. Once implemented, the AI software was validated using CT scans performed over one month, and was reviewed by a neuroradiologist. The turn-around-time was calculated as the time taken from scan completion to report finalisation. 2916 head CT scans and reports were reviewed as part of the audit. The AI software flagged 20 cases that were negative-by-report. Two of these were true-misses that had no follow-up imaging. Both patients were followed up and exhibited no long-term neurological sequelae. For ICH-positive scans, there was an increase in TAT in the total sample (35.6%), and a statistically insignificant decrease in TAT in the emergency (- 5.1%) and outpatient (- 14.2%) cohorts. The AI software was tested on a sample of real-world data from a high-volume Australian centre. The diagnostic accuracy was comparable to that reported in literature. The study demonstrated the institution's low miss-rate and short reporting time, therefore any improvements from the use of AI would be marginal and challenging to measure.

Utility of computed tomography angiography in traumatic lower limb injury: Review of clinical impact in level 1 trauma centre.

INTRODUCTION: CT angiography (CTA) is efficient and accurate in detecting lower limb vascular injury in the setting of trauma (1-6). Less clear is the in-practice correlation between appropriate indications for these examinations and subsequent clinical impacts. MATERIALS AND METHODS: All CT leg angiography acquired from January 2016 through April 2019 were reviewed via retrospective search. Studies not acquired for trauma were excluded. Imaging and reports were reviewed to assess for vascular injury. Electronic medical records were reviewed to assess the presence or absence of classical 'hard' or 'soft' signs of vascular injury and whether vascular intervention was undertaken. RESULTS: A total of 347 lower limb injuries were identified in 273 men and 74 women. Mean age was 41.5 years ranging from 15-95 years. 268 cases were fractures with 177 open injuries. 301 of injuries were secondary to blunt trauma, 31 penetrating injury occurred and 15 cases were ascribed to blast/gunshot injury. 74 (21.3%) studies were deemed to have a positive finding of vascular injury, 249 (71.8%) were reported as negative and 24 (6.9%) were indeterminate. Of the cases with positive findings, 26 underwent intervention (7.4% of all patients undergoing CTA). No patients with negative CTA required intervention, while three (3, 0.8% of total) with indeterminate findings required intervention. Where there were no clinical signs (absence of any hard or soft signs) 249 CTA's were performed and none required any form of intervention. CONCLUSION: In the absence of clinical signs of vessel injury, CT angiography is unlikely to demonstrate vascular injury requiring intervention in the setting of lower limb trauma.

Weight-Adjusted Contrast Administration in the Computed Tomography Evaluation of Pulmonary Embolism.

INTRODUCTION: Computed tomography pulmonary angiogram (CTPA) is widely considered the gold standard for diagnosis of pulmonary embolism (PE) with previous studies demonstrating high sensitivity and specificity. Despite this, nondiagnostic and indeterminate CTPA rates of 5%-26% remain a concern. As part of a continuing quality assurance program, a new weight-adjusted contrast dose and increased administration rate CTPA protocol was studied with an aim to improve diagnostic accuracy of PE evaluation. METHODS: A total of 2,398 CTPA examinations were reviewed to assess pulmonary arterial enhancement and PE yield in this retrospective study. Between 1 August 2014 and 1 August 2015, 1,133 patients received a fixed-volume (60 mL) contrast dose technique at 4 mL/s (protocol A). A new protocol was then implemented as part of a continuing quality assurance program. Between 15 September 2015 and 15 September 2016, 1,265 patients received a weight-adjusted contrast dose (1 mL/kg) and increased administration rate (5 mL/s) CTPA technique (protocol B). Studies were classed into categories based on quality of study; diagnostic: HU > 211, nondiagnostic: HU < 211 and PE yield; positive, negative, and indeterminate. These variables were compared with cross-sectional surface area to assess the relationship between patient habitus, CTPA diagnostic quality, and PE yield. RESULTS: A weight-adjusted contrast dose and increased administration rate CTPA protocol (protocol B) resulted in a significant increase in mean PA enhancement (P < .0001), 55.23% decrease in nondiagnostic studies and 43.04% decrease in indeterminate studies. Protocol B demonstrated increased positive and negative CTPA rates with decreased indeterminate rates from 12.38% to 7.04%. Comparison with cross-sectional area demonstrated significant increase in proportion of diagnostic studies and reduction in nondiagnostic and indeterminate CTPAs using protocol B in obese patients. CONCLUSIONS: A weight-adjusted contrast dose and increased administration rate CTPA protocol can significantly increase PA enhancement, especially in obese patients, resulting in greater high-quality and fewer nondiagnostic and indeterminate CTPA examinations. A CTPA protocol with a higher rate of conclusive examinations can provide greater confidence in PE evaluation for reporting radiologists and accurate clinical decision-making pathways for referring physicians.