ABSTRACT
PURPOSE: To compare the image quality between a deep learning-based image reconstruction algorithm (DLIR) and an adaptive statistical iterative reconstruction algorithm (ASiR-V) in noncontrast trauma head CT. METHODS: Head CT scans from 94 consecutive trauma patients were included. Images were reconstructed with ASiR-V 50% and the DLIR strengths: low (DLIR-L), medium (DLIR-M), and high (DLIR-H). The image quality was assessed quantitatively and qualitatively and compared between the different reconstruction algorithms. Inter-reader agreement was assessed by weighted kappa. RESULTS: DLIR-M and DLIR-H demonstrated lower image noise (p < 0.001 for all pairwise comparisons), higher SNR of up to 82.9% (p < 0.001), and higher CNR of up to 53.3% (p < 0.001) compared to ASiR-V. DLIR-H outperformed other DLIR strengths (p ranging from < 0.001 to 0.016). DLIR-M outperformed DLIR-L (p < 0.001) and ASiR-V (p < 0.001). The distribution of reader scores for DLIR-M and DLIR-H shifted towards higher scores compared to DLIR-L and ASiR-V. There was a tendency towards higher scores with increasing DLIR strengths. There were fewer non-diagnostic CT series for DLIR-M and DLIR-H compared to ASiR-V and DLIR-L. No images were graded as non-diagnostic for DLIR-H regarding intracranial hemorrhage. The inter-reader agreement was fair-good between the second most and the less experienced reader, poor-moderate between the most and the less experienced reader, and poor-fair between the most and the second most experienced reader. CONCLUSION: The image quality of trauma head CT series reconstructed with DLIR outperformed those reconstructed with ASiR-V. In particular, DLIR-M and DLIR-H demonstrated significantly improved image quality and fewer non-diagnostic images. The improvement in qualitative image quality was greater for the second most and the less experienced readers compared to the most experienced reader.
Subject(s)
Deep Learning , Algorithms , Humans , Image Processing, Computer-Assisted , Radiation Dosage , Radiographic Image Interpretation, Computer-Assisted/methods , Tomography, X-Ray Computed/methodsABSTRACT
Black smoke lung disease - a new disease in Sweden We describe two elderly female patients, immigrants to Sweden from Afghanistan, with intensive longtime exposure to smoke from biomass, and who presented with bronchial stenosis and severe bronchial obstruction. CT and X-ray showed bizarre perihilar infiltrates in the lungs. Bronchoscopy revealed black narrow bronchi with a middle lobe stenosis in one of the patients. These findings indicate the diagnosis bronchial anthracofibrosis (BAF). The here described findings are seen mainly in elderly never-smoking women from developing countries who have spent years cooking food in poorly ventilated kitchens. With increased immigration from these countries such cases will be seen in industrialized countries as well. Active tuberculosis must always be excluded but otherwise no more active investigations such as biopsies are warranted. We suggest that this disease should be termed ¼black smoke disease« to differentiate it from coal workers' pneumoconiosis, silicosis, and other classical occupational diseases which can have similar clinical and radiological pictures. This term is easily understood even by non-medical persons and illustratess both the etiology and the black bronchi.
Subject(s)
Anthracosis , Smoke/adverse effects , Afghanistan/ethnology , Anthracosis/diagnosis , Anthracosis/diagnostic imaging , Anthracosis/etiology , Anthracosis/pathology , Biomass , Bronchoscopy , Construction Materials/adverse effects , Female , Humans , Iran/ethnology , Middle Aged , Occupational Exposure/adverse effects , Radiography , Sweden , Tomography, X-Ray ComputedABSTRACT
BACKGROUND: Core biopsies are valuable in obtaining sufficient tissue to ensure diagnosis of diseases in the thorax. OBJECTIVE: To evaluate the complication rate and the diagnostic yield in computer tomography (CT)-guided core biopsies performed in a county hospital in Sweden. METHODS: Medical journals, spirometry results, pathology reports and CT scans were reviewed in 463 consecutive cases, where a transthoracic core biopsy was performed between January 2005 and December 2010. Of these 380 (82%) were lung lesions, 48 (10%) were mediastinal lesions and 35 (8%) were pleural lesions. RESULTS: All patients underwent a chest X-ray 4 hours post-biopsy and pneumothorax was seen in 156/463 (34%) patients: 137 after lung biopsy and 17 after mediastinal biopsy. Chest tube insertion was required for 27 (17%) of these patients (6% of all core biopsies). Small intraparenchymal hemorrhages and hemoptysis were observed with subjective difficulty in one case. The diagnostic yield for the 463 patients was 212 (46%) cases of lung cancer, 188 (41%) benign lesions and 39 (8%) pulmonary metastases. CONCLUSIONS: A transthoracic core biopsy ensures diagnosis with a low complication rate and is suitable as an outpatient procedure. An increased risk for pneumothorax was observed when the biopsied lesion was small or when emphysema was in the path of the biopsy needle. Reduced lung function pre-biopsy or emphysema in the path of the biopsy needle increased the need for chest tube treatment of pneumothorax. A CT-guided core biopsy is safe and applicable in a county hospital.
