Automatic chest computed tomography image noise quantification using deep learning.

PURPOSE: This study aimed to develop a deep learning (DL) method for noise quantification for clinical chest computed tomography (CT) images without the need for repeated scanning or homogeneous tissue regions. METHODS: A comprehensive phantom CT dataset (three dose levels, six reconstruction methods, amounting to 9240 slices) was acquired and used to train a convolutional neural network (CNN) to output an estimate of local image noise standard deviations (SD) from a single CT scan input. The CNN model consisting of seven convolutional layers was trained on the phantom image dataset representing a range of scan parameters and was tested with phantom images acquired in a variety of different scan conditions, as well as publicly available chest CT images to produce clinical noise SD maps. RESULTS: Noise SD maps predicted by the CNN agreed well with the ground truth both visually and numerically in the phantom dataset (errors of < 5 HU for most scan parameter combinations). In addition, the noise SD estimates obtained from clinical chest CT images were similar to running-average based reference estimates in areas without prominent tissue interfaces. CONCLUSIONS: Predicting local noise magnitudes without the need for repeated scans is feasible using DL. Our implementation trained with phantom data was successfully applied to open-source clinical data with heterogeneous tissue borders and textures. We suggest that automatic DL noise mapping from clinical patient images could be used as a tool for objective CT image quality estimation and protocol optimization.

Novel therapeutic approaches for pleural mesothelioma identified by functional ex vivo drug sensitivity testing.

OBJECTIVES: Pleural mesothelioma (PM) is an aggressive malignancy with limited treatment options. The first-line therapy has remained unchanged for two decades and consists of pemetrexed in combination with cisplatin. Immune-checkpoint inhibitors (nivolumab plus ipilimumab) have high response rates, resulting in recent updates in treatment recommendations by the U.S. Food and Drug Administration. However, the overall benefits of combination treatment are modest, suggesting that other targeted therapy options should be investigated. MATERIALS AND METHODS: We employed high-throughput drug sensitivity and resistance testing on five established PM cell lines using 527 cancer drugs in a 2D setting. Drugs of the greatest potential (n = 19) were selected for further testing in primary cell models derived from pleural effusions of seven PM patients. RESULTS: All established and primary patient-derived PM cell models were sensitive to the mTOR inhibitor AZD8055. Furthermore, another mTOR inhibitor (temsirolimus) showed efficacy in most of the primary patient-derived cells, although a less robust effect was observed when compared with the established cell lines. Most of the established cell lines and all patient-derived primary cells exhibited sensitivity to the PI3K/mTOR/DNA-PK inhibitor LY3023414. The Chk1 inhibitor prexasertib showed activity in 4/5 (80%) of the established cell lines and in 2/7 (29%) of the patient-derived primary cell lines. The BET family inhibitor JQ1 showed activity in four patient-derived cell models and in one established cell line. CONCLUSION: mTOR and Chk1 pathways had promising results with established mesothelioma cell lines in an ex vivo setting. In patient-derived primary cells, drugs targeting mTOR pathway in particular showed efficacy. These findings may inform novel treatment strategies for PM.

Lung function and exercise capacity 6 months after hospital discharge for critical COVID-19.

BACKGROUND: The significant morbidity caused by COVID-19 necessitates further understanding of long-term recovery. Our aim was to evaluate long-term lung function, exercise capacity, and radiological findings in patients after critical COVID-19. METHODS: Patients who received treatment in ICU for COVID-19 between March 2020 and January 2021 underwent pulmonary function tests, a 6MWD and CXR 6 months after hospital discharge. RESULTS: A restrictive ventilatory defect was found in 35% (23/65) and an impaired diffusing capacity in 52% (32/62) at 6 months. The 6-minute walk distance was reduced in 33% (18/55), and 7% (4/55) of the patients had reduced exercise capacity. Chest X-ray was abnormal in 78% (52/67) at 6 months after hospital discharge. CONCLUSION: A significant number of patients had persisting lung function impairment and radiological abnormalities at 6 months after critical COVID-19. Reduced exercise capacity was rare.

Platelet function and filamin A expression in two families with novel FLNA gene mutations associated with periventricular nodular heterotopia and panlobular emphysema.

Pathogenic variants of the X-linked FLNA gene encoding filamin A protein have been associated with a wide spectrum of symptoms, including the recently described pulmonary phenotype with childhood-onset panlobular emphysema. We describe three female patients from two families with novel heterozygous FLNA variants c.5837_2del and c.508C > T. Analysis of immunofluorescence of peripheral blood smears and platelet function was performed for all patients. FLNA-negative platelets were observed, suggesting that these variants result in the loss of a functional protein product. All three patients also had periventricular nodular heterotopia and panlobular emphysema. However, they had considerably milder symptoms and later age of onset than in the previously reported cases. Therefore, patients with pathogenic FLNA variants should be studied actively for lung involvement even in the absence of pronounced respiratory symptoms. Conversely, any patient with unexplained panlobular emphysema should be analyzed for pathogenic FLNA variants. We also suggest that immunofluorescence analysis is a useful tool for investigating the pathogenicity of novel FLNA variants.

Low skeletal muscle mass in stented esophageal cancer predicts poor survival: A retrospective observational study.

BACKGROUND: In esophageal cancer, nutritional challenges are extremely common. Malignant obstruction resulting from esophageal cancer (EC) is often treated by the insertion of expandable stents, but little is known as to the role and evolution of sarcopenia in this patient population. The aim of this article was to determine the effects of body mass parameters on survival of advanced EC patients who received a stent for palliation of malignant obstruction. METHODS: This was a retrospective observational study of 238 EC patients who had a stent inserted for palliation of malignant obstruction between 2005 and 2013. Skeletal muscle mass was calculated from abdominal computed tomography scans, and the patients were divided into sarcopenic and non-sarcopenic groups. A follow-up computed tomography scan was available in 118 patients. The primary outcome was survival, and complication rates and the need for an alternative enteral feeding route were secondary outcomes. RESULTS: Sarcopenia occurred in 199 (85%) patients. Median survival was 146 (range: 76-226) days in the sarcopenia group and 152 (range: 71-249) days in the non-sarcopenic group (P = 0.61). Complication rates between the groups were not significantly different (P = 0.85). In Cox regression analysis, the skeletal muscle index was inversely correlated with overall survival (hazard ratio 0.98, 95% confidence interval 0.97-0.99; P = 0.033). CONCLUSIONS: Sarcopenia, defined by consensus thresholds, at the time of stent insertion cannot effectively predict poor survival in this patient cohort, but a lower skeletal muscle index correlates with poor prognosis as a continuous variable.