Peripheral bronchial identification on chest CT using unsupervised machine learning

Purpose

To automatically identify small- to medium-diameter bronchial segments distributed throughout the lungs.

Methods

We segment the peripheral pulmonary vascular tree and construct cross-sectional images perpendicular to the lung vasculature. The bronchi running with pulmonary arteries appear as concentric rings, and potential center points that lie within the bronchi are identified by looking for circles (using the circular Hough transform) and rings (using a novel variable ring filter). The number of candidate bronchial center points are further reduced by using agglomerative hierarchical clustering applied to the points represented with 18 features pertaining to their 3D position, orientation and appearance of the surrounding cross-sectional image. Resulting clusters corresponded to bronchial segments. Parameters of the algorithm are varied and applied to two experimental data sets to find the best values for bronchial identification. The optimized algorithm was then applied to a further 21 CT studies obtained using two different CT vendors.

Results

The parameters that result in the most number of true positive bronchial center points with > 95% precision are a tolerance of 0.15 for the hierarchical clustering algorithm and a threshold of 75 HU with 10 spokes for the ring filter. Overall, the performance on all 21 test data sets from CT scans from both vendors demonstrates a mean number of 563 bronchial points detected per CT study, with a mean precision of 96%. The detected points across this group of test data sets are relatively uniformly distributed spatially with respect to spherical coordinates with the origin at the center of the test imaging data sets.

Conclusion

We have constructed a robust algorithm for automatic detection of small- to medium-diameter bronchial segments throughout the lungs using a combination of knowledge-based approaches and unsupervised machine learning. It appears robust over two different CT vendors with similar acquisition parameters.

     

SGLT2 inhibitors: are they safe?

Sodium–glucose linked transporter type 2 (SGLT2) inhibitors are a relatively new class of antidiabetic drugs with positive cardiovascular and kidney effects. The aim of this review is to present the safety issues associated with SGLT2 inhibitors. Urogenital infections are the most frequently encountered adverse events, although tend to be mild to moderate and are easily manageable with standard treatment. Although no increased acute kidney injury risk was evident in the major trials, the mechanism of action of these drugs requires caution when they are administered in patients with extracellular volume depletion or with drugs affecting renal hemodynamics. Canagliflozin raised the risk of amputations and the rate of fractures in the CANVAS trial, although more data are necessary before drawing definite conclusions. The risk of euglycemic diabetic ketoacidosis seems to be minimal when the drugs are prescribed properly. Regarding other adverse events, SGLT2 inhibitors do not increase the risk of hypoglycemia even when co-administered with insulin, but a decrease in the dose of sulphonylureas may be needed. The available data do not point to a causative role of SGLT2 inhibitors on malignancy risk, however, these drugs should be used with caution in patients with known hematuria or history of bladder cancer. SGLT2 inhibitors seem to be safe and effective in the treatment of diabetes but more studies are required to assess their long-term safety.     

Role of the endothelium in modulating neointimal formation: vasculoprotective approaches to attenuate restenosis after percutaneous coronary interventions

Restenosis at the site of an endoluminal procedure remains a significant problem in the practice of interventional cardiology. We present current data on intimal hyperplasia, which identify the major role of endothelial cells (ECs) in the development of restenosis. Considering endothelial denudation as one of the most important mechanisms contributing to restenosis, we focus more attention on methods of accelerating restoration of endothelial continuity. Prevention of restenosis may be achieved by promoting endothelial regeneration through the use of growth factors, EC seeding, vessel reconstruction with autologous EC/fibrin matrix, and the use of estrogen-loaded stents and stents designed to capture progenitor ECs.     

Vascular remodeling and plaque composition between focal and diffuse coronary lesions assessed by intravascular ultrasound

Coronary remodeling and plaque composition were compared between focal and diffuse coronary lesions. Negative remodeling and fibrous and calcified plaque compositions contribute to stenosis development in diffuse lesions more frequently than in focal lesions.     

Valve injury and repair in balloon aortic valvuloplasty

Aortic valves 0.5, and 4.5 months after successful percutaneous balloon aortic valvuloplasty (BAV) were examined. BAV caused macroscopic and microscopic fractures in calcific deposits. An inflammatory response was identified that may lead to valvular scarring. This process may be an important factor in the development of restenosis after BAV.