Thoracic Inlet in Cervical Spine CT of Blunt Trauma Patients: Prevalence of Pathologies and Importance of CT Interpretation.

BACKGROUND: The thoracic inlet of blunt trauma patients may have pathologies that can be diagnosed on cervical spine computed tomography (CT) but that are not evident on concurrent portable chest radiography (pCXR). This retrospective investigation aimed to identify the prevalence of thoracic inlet pathologies on cervical spine CT and their importance by measuring the diagnostic performance of pCXR and the predictive factors of such abnormalities. METHODS: This investigation was performed at a level-1 trauma center and included CT and concurrent pCXR of 385 consecutive adult patients (280 men, mean age of 47.6 years) who presented with suspected cervical spine injury. CT and pCXR findings were independently re-reviewed, and CT was considered the reference standard. RESULTS: Traumatic, significant nontraumatic and nonsignificant pathologies were present at 23.4%, 23.6% and 58.2%, respectively. The most common traumatic diagnoses were pneumothorax (12.7%) and pulmonary contusion (10.4%). The most common significant nontraumatic findings were pulmonary nodules (8.1%), micronodules (6.8%) and septal thickening (4.2%). The prevalence of active tuberculosis was 3.4%. The sensitivity and positive predictive value of pCXR was 56.67% and 49.51% in diagnosing traumatic and 8.89% and 50% in significant nontraumatic pathologies. No demographic or pre-admission clinical factors could predict these abnormalities. CONCLUSIONS: Several significant pathologies of the thoracic inlet were visualized on trauma cervical spine CT. Since a concurrent pCXR was not sensitive and no demographic or clinical factors could predict these abnormalities, a liberal use of chest CT is suggested, particularly among those experiencing high-energy trauma with significant injuries of the thoracic inlet. If chest CT is not available, a meticulous evaluation of the thoracic inlet in the cervical spine CT of blunt trauma patients is important.

A clinical evaluation study of cardiothoracic ratio measurement using artificial intelligence.

BACKGROUND: Artificial intelligence, particularly the deep learning (DL) model, can provide reliable results for automated cardiothoracic ratio (CTR) measurement on chest X-ray (CXR) images. In everyday clinical use, however, this technology is usually implemented in a non-automated (AI-assisted) capacity because it still requires approval from radiologists. We investigated the performance and efficiency of our recently proposed models for the AI-assisted method intended for clinical practice. METHODS: We validated four proposed DL models (AlbuNet, SegNet, VGG-11, and VGG-16) to find the best model for clinical implementation using a dataset of 7517 CXR images from manual operations. These models were investigated in single-model and combined-model modes to find the model with the highest percentage of results where the user could accept the results without further interaction (excellent grade), and with measurement variation within ± 1.8% of the human-operating range. The best model from the validation study was then tested on an evaluation dataset of 9386 CXR images using the AI-assisted method with two radiologists to measure the yield of excellent grade results, observer variation, and operating time. A Bland-Altman plot with coefficient of variation (CV) was employed to evaluate agreement between measurements. RESULTS: The VGG-16 gave the highest excellent grade result (68.9%) of any single-model mode with a CV comparable to manual operation (2.12% vs 2.13%). No DL model produced a failure-grade result. The combined-model mode of AlbuNet + VGG-11 model yielded excellent grades in 82.7% of images and a CV of 1.36%. Using the evaluation dataset, the AlbuNet + VGG-11 model produced excellent grade results in 77.8% of images, a CV of 1.55%, and reduced CTR measurement time by almost ten-fold (1.07 ± 2.62 s vs 10.6 ± 1.5 s) compared with manual operation. CONCLUSION: Due to its excellent accuracy and speed, the AlbuNet + VGG-11 model could be clinically implemented to assist radiologists with CTR measurement.