Deep Learning for Pneumothorax Detection on Chest Radiograph: A Diagnostic Test Accuracy Systematic Review and Meta Analysis.

BACKGROUND: Pneumothorax is a common acute presentation in healthcare settings. A chest radiograph (CXR) is often necessary to make the diagnosis, and minimizing the time between presentation and diagnosis is critical to deliver optimal treatment. Deep learning (DL) algorithms have been developed to rapidly identify pathologic findings on various imaging modalities. PURPOSE: The purpose of this systematic review and meta-analysis was to evaluate the overall performance of studies utilizing DL algorithms to detect pneumothorax on CXR. METHODS: A study protocol was created and registered a priori (PROSPERO CRD42023391375). The search strategy included studies published up until January 10, 2023. Inclusion criteria were studies that used adult patients, utilized computer-aided detection of pneumothorax on CXR, dataset was evaluated by a qualified physician, and sufficient data was present to create a 2 × 2 contingency table. Risk of bias was assessed using the QUADAS-2 tool. Bivariate random effects meta-analyses and meta-regression modeling were performed. RESULTS: Twenty-three studies were selected, including 34 011 patients and 34 075 CXRs. The pooled sensitivity and specificity were 87% (95% confidence interval, 81%, 92%) and 95% (95% confidence interval, 92%, 97%), respectively. The study design, use of an institutional/public data set and risk of bias had no significant effect on the sensitivity and specificity of pneumothorax detection. CONCLUSIONS: The relatively high sensitivity and specificity of pneumothorax detection by deep-learning showcases the vast potential for implementation in clinical settings to both augment the workflow of radiologists and assist in more rapid diagnoses and subsequent patient treatment.

The Role of Twitter in Radiology Medical Education and Research: A Review of Current Practices and Drawbacks.

The trends in society have provided favourable conditions for the rapid growth of radiology on social media, specifically there has been an expanding presence on Twitter. Currently, simple searches on Twitter yield a plethora of radiology education resources, that may be suited for medical students, residents or practicing radiologists. Educators have many tools at their disposal to deliver effective teaching. Over time, strategies such as including images and scrollable stacks often are more successful at gaining popularity or clicks online. Journals and authors can use Twitter to promote their new scientific work and potentially reach audiences they couldn't have prior. Attendees at conferences can get involved in the conversation by tweeting about the meeting and engaging with other attendees with mutual interests. Interested medical students, residents and even practicing radiologists can use Twitter as a means of networking and connecting with other scholars all around the globe. Within its glory, Twitter does carry some drawbacks including privacy concerns, equality, and risk of misinformation. Above all, the future of Twitter is bright and promising for all who are currently on it and plan to use it for their education, research, or professional advancement.

Artificial intelligence in emergency radiology: A review of applications and possibilities.

Artificial intelligence (AI) applications in radiology have been rising exponentially in the last decade. Although AI has found usage in various areas of healthcare, its utilization in the emergency department (ED) as a tool for emergency radiologists shows great promise towards easing some of the challenges faced daily. There have been numerous reported studies examining the application of AI-based algorithms in identifying common ED conditions to ensure more rapid reporting and in turn quicker patient care. In addition to interpretive applications, AI assists with many of the non-interpretive tasks that are encountered every day by emergency radiologists. These include, but are not limited to, protocolling, image quality control and workflow prioritization. AI continues to face challenges such as physician uptake or costs, but is a long-term investment that shows great potential to relieve many difficulties faced by emergency radiologists and ultimately improve patient outcomes. This review sums up the current advances of AI in emergency radiology, including current diagnostic applications (interpretive) and applications that stretch beyond imaging (non-interpretive), analyzes current drawbacks of AI in emergency radiology and discusses future challenges.

A strongly Lewis-acidic and fluorescent borenium cation supported by a tridentate formazanate ligand.

Lewis acids are highly sought after for their applications in sensing, small-molecule activation, and catalysis. When combined with π-conjugated molecular frameworks, Lewis acids with unique optoelectronic properties can be realized. Here, we use a tridentate formazanate ligand to create a planar, redox-active, fluorescent, and strongly Lewis-acidic borenium cation. We also demonstrate that this compound can act as a colourimetric probe for reactivity.

Cationic Boron Formazanate Dyes*.

Incorporation of cationic boron atoms into molecular frameworks is an established strategy for creating chemical species with unusual bonding and reactivity but is rarely thought of as a way of enhancing molecular optoelectronic properties. Using boron formazanate dyes as examples, we demonstrate that the wavelengths, intensities, and type of the first electronic transitions in BN heterocycles can be modulated by varying the charge, coordination number, and supporting ligands at the cationic boron atom. UV-vis absorption spectroscopy measurements and density-functional (DFT) calculations show that these modulations are caused by changes in the geometry and extent of π-conjugation of the boron formazanate ring. These findings suggest a new strategy for designing optoelectronic materials based on π-conjugated heterocycles containing boron and other main-group elements.

New Histologic Finding of Amyloid Insulin Bodies at an Insulin Injection Site in a Patient With Diabetes.

Amyloidosis is a heterogeneous group of protein deposition diseases with more than 40 known clinical presentations. Localized amyloidosis occurs when the protein deposits exist in a singular location. Patients with diabetes mellitus who inject insulin at the same site can develop localized insulin-derived amyloidosis (AIns) at the injection site, which can be confused clinically with lipoma, lipohyperplasia, lipoatrophy, and fat necrosis. Histologic examination is performed to confirm localized AIns. We report a case of a patient with a long history of type 2 diabetes who presented with a subcutaneous mass in the abdomen at a preferred insulin injection site. Examination by light microscopy revealed diffuse deposition of eosinophilic material. Two of the tissue fragments contained numerous 30-40 µm spherical bodies within the eosinophilic material. The bodies had dark centers with peripheral eosinophilic material. Polarized sections stained with Congo red showed apple green birefringence, a characteristic of amyloid. Immunohistochemistry was positive for insulin antibodies in the dark spherules and the surrounding matrix. Proteomic analysis by mass spectrometry showed that the Congo red-positive material was insulin. Electron microscopy showed a background matrix consisting of nonbranching protein fibrils measuring 8.8-16.1 nm, consistent with amyloid; the spherules contained dark globular proteins in the center surrounded by nonbranching fibrillary proteins. Because these spherules were positive for insulin by immunohistochemistry and showed amyloid ultrastructurally, we refer to them as amyloid insulin bodies. The identification of AIns, specifically with amyloid insulin bodies, is important for diagnosis and treatment and may further our understanding of amyloidogenesis.

Aluminum Complexes of N2O23- Formazanate Ligands Supported by Phosphine Oxide Donors.

The synthesis and characterization of a new family of phosphine oxide supported aluminum formazanate complexes (7a,b, 8a, 9a) are reported. X-ray diffraction studies showed that the aluminum atoms in the complexes adopt an octahedral geometry in the solid state. The equatorial positions are occupied by an N2O23- formazanate ligand, and the axial positions are occupied by L-type phosphine oxide donors. UV-vis absorption spectroscopy revealed that the complexes were strongly absorbing (ε ≈ 30000 M-1 cm-1) between 500 and 700 nm. The absorption maxima in this region were simulated using time-dependent density functional theory. With the exception of 3-cyano-substituted complex 7b, which showed maximum luminescence intensity in the presence of excess phosphine oxide, the title complexes are nonemissive in solution and the solid state. The electrochemical properties of the complexes were probed using cyclic voltammetry. Each complex underwent sequential one-electron oxidations in potential ranges of -0.12 to 0.29 V and 0.62 to 0.97 V, relative to the ferrocene/ferrocenium redox couple. Electrochemical reduction events were observed at potentials between -1.34 and -1.75 V. In combination with tri-n-propylamine as a coreactant, complex 7b acted as an electrochemiluminescence emitter with a maximum electrochemiluminescence intensity at a wavelength of 735 nm, red-shifted relative to the photoluminescence maximum of the same compound.