Effects of a comprehensive brain computed tomography deep learning model on radiologist detection accuracy.

OBJECTIVES: Non-contrast computed tomography of the brain (NCCTB) is commonly used to detect intracranial pathology but is subject to interpretation errors. Machine learning can augment clinical decision-making and improve NCCTB scan interpretation. This retrospective detection accuracy study assessed the performance of radiologists assisted by a deep learning model and compared the standalone performance of the model with that of unassisted radiologists. METHODS: A deep learning model was trained on 212,484 NCCTB scans drawn from a private radiology group in Australia. Scans from inpatient, outpatient, and emergency settings were included. Scan inclusion criteria were age ≥ 18 years and series slice thickness ≤ 1.5 mm. Thirty-two radiologists reviewed 2848 scans with and without the assistance of the deep learning system and rated their confidence in the presence of each finding using a 7-point scale. Differences in AUC and Matthews correlation coefficient (MCC) were calculated using a ground-truth gold standard. RESULTS: The model demonstrated an average area under the receiver operating characteristic curve (AUC) of 0.93 across 144 NCCTB findings and significantly improved radiologist interpretation performance. Assisted and unassisted radiologists demonstrated an average AUC of 0.79 and 0.73 across 22 grouped parent findings and 0.72 and 0.68 across 189 child findings, respectively. When assisted by the model, radiologist AUC was significantly improved for 91 findings (158 findings were non-inferior), and reading time was significantly reduced. CONCLUSIONS: The assistance of a comprehensive deep learning model significantly improved radiologist detection accuracy across a wide range of clinical findings and demonstrated the potential to improve NCCTB interpretation. CLINICAL RELEVANCE STATEMENT: This study evaluated a comprehensive CT brain deep learning model, which performed strongly, improved the performance of radiologists, and reduced interpretation time. The model may reduce errors, improve efficiency, facilitate triage, and better enable the delivery of timely patient care. KEY POINTS: • This study demonstrated that the use of a comprehensive deep learning system assisted radiologists in the detection of a wide range of abnormalities on non-contrast brain computed tomography scans. • The deep learning model demonstrated an average area under the receiver operating characteristic curve of 0.93 across 144 findings and significantly improved radiologist interpretation performance. • The assistance of the comprehensive deep learning model significantly reduced the time required for radiologists to interpret computed tomography scans of the brain.

Charting the potential of brain computed tomography deep learning systems.

Brain computed tomography (CTB) scans are widely used to evaluate intracranial pathology. The implementation and adoption of CTB has led to clinical improvements. However, interpretation errors occur and may have substantial morbidity and mortality implications for patients. Deep learning has shown promise for facilitating improved diagnostic accuracy and triage. This research charts the potential of deep learning applied to the analysis of CTB scans. It draws on the experience of practicing clinicians and technologists involved in development and implementation of deep learning-based clinical decision support systems. We consider the past, present and future of the CTB, along with limitations of existing systems as well as untapped beneficial use cases. Implementing deep learning CTB interpretation systems and effectively navigating development and implementation risks can deliver many benefits to clinicians and patients, ultimately improving efficiency and safety in healthcare.

Nontuberculous Mycobacterial Infection Predisposing to Chronic Cavitary Pulmonary Aspergillosis.

Aspergillus is a large group of spore-forming fungi in the phylum Ascomycota. Aspergillus infections more frequently occur in individuals with pre-existing lung conditions such as cystic fibrosis and asthma and immunosuppressed individuals, and less frequently in the immunocompetent population. Pulmonary aspergillosis can be subdivided into three categories: allergic bronchopulmonary aspergillosis, chronic pulmonary aspergillosis, and invasive pulmonary aspergillosis. We present a rare case of a 57-year-old male with a previously known diagnosis of pancreatic adenocarcinoma on chemotherapy who was found to have a co-infection of the respiratory tract by Aspergillus flavus and Mycobacterium avium intracellulare.

MRI findings in an atypical case of Kearns-Sayre syndrome: a case report.

MR imaging features of mitochondrial encephalomyopathies, lactic acidosis, and stroke-like episodes, Kearns-Sayre/Pearson syndrome have been described in the literature. We describe extensive white matter changes with abnormal signal intensity lesions involving the deep gray nuclei and myelinated white matter tracts in an 18-year-old female with a large-scale 7.4 kb mitochondrial DNA deletion and a atypical presentation of Kearns-Sayre syndrome. Restricted diffusion due to status spongiosus at the involved sites is also discussed.

The rare phakomatoses.

This article outlines the clinical, central nervous system, and neuropathologic features,pathogenesis, genetics, molecular biology, and neuroimaging characteristics of the rare vascular phakomatoses, melanophakomatoses, and organoid phakomatoses.

Using CT to localize side and level of vocal cord paralysis.

OBJECTIVE: The purpose of our study was to assess the relative accuracy of imaging findings related to peripheral recurrent nerve paralysis on axial CT studies of the neck. Also assessed were imaging findings of a central vagal neuropathy. MATERIALS AND METHODS: We retrospectively identified 40 patients who had clinically diagnosed vocal cord paralysis and had undergone CT. Eight imaging signs of vocal cord paralysis were assessed, and an imaging distinction between a central or peripheral vagal neuropathy was made by evaluating asymmetric dilatation of the oropharynx with thinning of the constrictor muscles. In two patients, we studied the use of reformatted coronal images from a multidetector CT scanner. RESULTS: For unilateral vocal cord paralysis, the most sensitive imaging findings were ipsilateral pyriform sinus dilatation, medial positioning and thickening of the ipsilateral aryepiglottic fold, and ipsilateral laryngeal ventricle dilatation. In two patients, coronal reformatted images aided the diagnosis by better showing flattening of the subglottic arch. Imaging findings allowed localization of a central vagal neuropathy in four patients. CONCLUSION: Three reliable imaging findings associated with vocal cord paralysis were identified on routine axial CT studies: ipsilateral pyriform sinus dilatation, medial positioning and thickening of the ipsilateral aryepiglottic fold, and ipsilateral laryngeal ventricle dilatation. Coronal reformatted images of the larynx may be helpful, but they are not necessary in 95% of patients. Ipsilateral pharyngeal constrictor muscle atrophy is a helpful imaging finding to localize a more central vagal neuropathy. Our findings can aid radiologists in identifying peripheral and central vagal neuropathy in patients who present for CT of the neck who have a normal voice and are without a history suggestive of a vagal problem.