RESUMO
Interpretive artificial intelligence (AI) tools are poised to change the future of radiology. However, certain pitfalls may pose particular challenges for optimal AI interpretative performance. These include anatomic variants, age-related changes, postoperative changes, medical devices, image artifacts, lack of integration of prior and concurrent imaging examinations and clinical information, as well as the satisfaction-of-search effect. Model training and development should account for such pitfalls, to minimize errors and optimize interpretation accuracy. More broadly, AI algorithms should be exposed to diverse and complex training data sets, to yield a holistic interpretation that considers all relevant information beyond the individual examination. Successful clinical deployment of AI tools will require that radiologist end-users recognize these pitfalls and other limitations of the available models. Furthermore, developers should incorporate explainable AI techniques (e.g., heat maps) into their tools, to improve radiologists' understanding of model outputs and to enable radiologists to provide feedback for guiding continuous learning and iterative refinement. In this article, we provide an overview of common pitfalls that radiologists may encounter when using interpretive AI products in daily practice. We present how such pitfalls lead to AI errors and offer potential strategies that AI developers may use for their mitigation.
RESUMO
Spectral CT represents a novel imaging approach that can noninvasively visualize, quantify, and characterize many musculoskeletal pathologies. This modality has revolutionized the field of radiology by capturing CT attenuation data across multiple energy levels and offering superior tissue characterization while potentially minimizing radiation exposure compared to traditional enhanced CT scans. Despite MRI being the preferred imaging method for many musculoskeletal conditions, it is not viable for some patients. Moreover, this technique is time-consuming, costly, and has limited availability in many healthcare settings. Thus, spectral CT has a considerable role in improving the diagnosis, characterization, and treatment of gout, inflammatory arthropathies, degenerative disc disease, osteoporosis, occult fractures, malignancies, ligamentous injuries, and other bone-marrow pathologies. This comprehensive review will delve into the diverse capabilities of dual-energy CT, a subset of spectral CT, in addressing these musculoskeletal conditions and explore potential future avenues for its integration into clinical practice.
RESUMO
Penetrating diaphragmatic injuries pose diagnostic and management challenges. Computed tomography (CT) scans are valuable for stable patients, but concern exists for missed injuries and complications in nonoperatively managed cases. The objective of this study was to explore the diagnostic utility of multidetector CT scan (MDCT) in identifying diaphragmatic injuries resulting from penetrating trauma. A systematic review and meta-analysis were conducted, following established guidelines, by searching PubMed, Scopus, Web of Science, and Embase databases up to July 6, 2023. Eligible studies reporting MDCT's diagnostic accuracy in detecting penetrating diaphragmatic injuries were included. Relevant data elements were extracted and analyzed using STATA software. The study included 9 articles comprising 294 patients with confirmed penetrating diaphragmatic injuries through surgical procedures. MDCT's diagnostic performance revealed a pooled sensitivity of 74% (95% CI: 56%-87%) and a pooled specificity of 92% (95% CI: 79%-97%) (Fig. two), with significant heterogeneity in both sensitivity and specificity across the studies. The Fagan plot demonstrated that higher pre-test probabilities correlated with higher positive post-test probabilities for penetrating diaphragmatic injury diagnosis using MDCT, but even with negative results, there remained a small chance of having the injury, especially in cases with higher pre-test probabilities. This study highlights MDCT's effectiveness in detecting diaphragmatic injury from penetrating trauma, with moderate to high diagnostic accuracy. However, larger sample sizes, multicenter collaborations, and prospective designs are needed to address observed heterogeneity, enhancing understanding and consistency in MDCT's diagnostic capabilities in this context.
Assuntos
Traumatismos Abdominais , Traumatismos Torácicos , Ferimentos Penetrantes , Humanos , Tomografia Computadorizada Multidetectores , Ferimentos Penetrantes/diagnóstico por imagem , Ferimentos Penetrantes/cirurgia , Diafragma/diagnóstico por imagem , Diafragma/lesões , Traumatismos Abdominais/cirurgia , Sensibilidade e Especificidade , Estudos Multicêntricos como AssuntoRESUMO
Globally, many hospitalized COVID-19 patients can experience an unexpected acute change in status, prompting rapid and expert clinical assessment. Superimposed infections can be a significant cause of clinical and radiologic deviations in this patient population, further worsening clinical outcome and muddling the differential diagnosis. As thrombotic, inflammatory, and medication-induced complications can also trigger an acute change in COVID-19 patient status, imaging early and often plays a vital role in distinguishing the cause of patient decline and monitoring patient outcome. While the common radiologic findings of COVID-19 infection are now widely reported, little is known about the clinical manifestations and imaging findings of superimposed infection. By discussing case studies of patients who developed bacterial, fungal, parasitic, and viral co-infections and identifying the most frequently reported imaging findings of superimposed infections, physicians will be more familiar with common infectious presentations and initiate a directed workup sooner. Ultimately, any abrupt changes in the expected COVID-19 imaging presentation, such as the presence of new consolidations or cavitation, should prompt further workup to exclude superimposed opportunistic infection.
Assuntos
COVID-19 , Fungos , Humanos , SARS-CoV-2RESUMO
After GE Healthcare, one of the major producers of iodinated contrast dye, was forced to close their Shanghai factory due to a recent COVID-19 outbreak, iodinated contrast media shortages have rocked healthcare systems to their core. Clinicians nationwide are now caught between the desire to provide patients with optimal care and the need to conserve the minimal remaining supplies of iodinated contrast media. While GE Healthcare has reopened their factory and other sources of contrast agents have become available, experts report that levels may not return to normal through June 2022. Thankfully and ironically, radiology departments are all too familiar with COVID-19 associated operational disruptions and have been quick to adapt and implement novel protocols to evade this and other crises. Overall, this shortage emphasizes the importance of interprofessional communication, adaptation, and preparation for future emergent situations as this is not the first iodinated contrast material shortage and it likely would not be the last.
Assuntos
COVID-19 , Meios de Contraste , China , HumanosRESUMO
Imaging in the emergent setting carries high stakes. With increased demand for dedicated on-site service, emergency radiologists face increasingly large image volumes that require rapid turnaround times. However, novel artificial intelligence (AI) algorithms may assist trauma and emergency radiologists with efficient and accurate medical image analysis, providing an opportunity to augment human decision making, including outcome prediction and treatment planning. While traditional radiology practice involves visual assessment of medical images for detection and characterization of pathologies, AI algorithms can automatically identify subtle disease states and provide quantitative characterization of disease severity based on morphologic image details, such as geometry and fluid flow. Taken together, the benefits provided by implementing AI in radiology have the potential to improve workflow efficiency, engender faster turnaround results for complex cases, and reduce heavy workloads. Although analysis of AI applications within abdominopelvic imaging has primarily focused on oncologic detection, localization, and treatment response, several promising algorithms have been developed for use in the emergency setting. This article aims to establish a general understanding of the AI algorithms used in emergent image-based tasks and to discuss the challenges associated with the implementation of AI into the clinical workflow.
RESUMO
Diseases of pleura are not only common but also have a significant impact on patients' outcomes. While early detection and treatment are imperative in reducing this burden, many pleural entities present similarly, thus posing a diagnostic dilemma for radiologists requiring critical further workup. While chest radiography, CT, and image-guided thoracentesis are primarily utilized as the initial imaging techniques for the workup of pleural diseases, MRI, and FDG-PET/CT are also frequently employed to investigate the root cause of pleural abnormalities. By elucidating the common imaging features of neoplastic, inflammatory, and infectious pleural pathologies, clinicians can quickly and easily differentiate the various pleural diseases, rapidly reach the correct diagnosis, and ultimately improve patient outcomes.
Assuntos
Pleura , Doenças Pleurais , Humanos , Pleura/patologia , Fluordesoxiglucose F18 , Tomografia por Emissão de Pósitrons combinada à Tomografia Computadorizada/efeitos adversos , Tomografia Computadorizada por Raios X , Doenças Pleurais/diagnóstico por imagem , Doenças Pleurais/etiologia , Doenças Pleurais/patologiaRESUMO
Recent studies have focused on the development of total-body PET scanning in a variety of fields such as clinical oncology, cardiology, personalized medicine, drug development and toxicology, and inflammatory/infectious disease. Given its ultrahigh detection sensitivity, enhanced temporal resolution, and long scan range (1940 mm), total-body PET scanning can not only image faster than traditional techniques with less administered radioactivity but also perform total-body dynamic acquisition at a longer delayed time point. These unique characteristics create several opportunities to improve image quality and can provide a deeper understanding regarding disease detection, diagnosis, staging/restaging, response to treatment, and prognostication. By reviewing the advantages of total-body PET scanning and discussing the potential clinical applications for this innovative technology, we can address specific issues encountered in routine clinical practice and ultimately improve patient care.
RESUMO
While not conventionally used as the first-line modality, [18F]-2-fluoro-2-deoxy-D-glucose (FDG) - positron emission tomography/computed tomography (PET/CT) can identify infection and inflammation both earlier and with higher sensitivity than anatomic imaging modalities [including chest X-ray (CXR), computed tomography (CT), and magnetic resonance imaging (MRI)]. The extent of inflammation and, conversely, recovery within the lungs, can be roughly quantified on FDG-PET/CT using maximum standardized uptake value (SUVmax) values. The Coronavirus disease 2019 (COVID-19) pandemic has highlighted the value of FDG-PET/CT in diagnosis, elucidation of acute pulmonary and extrapulmonary manifestations, and long-term follow up. Similarly, many other pulmonary infections such as previously documented coronaviruses, aspergillosis, blastomycosis, candidiasis, coccidioidomycosis, cryptococcosis, histoplasmosis, mucormycosis, and typical/atypical mycobacterial infections have all been identified and characterized using FDG-PET/CT imaging. The goal of this review is to summarize the actual and potential benefits of FDG-PET/CT in the imaging of COVID-19 and other lung infections. Further research is necessary to determine the best indications and clinical applications of FDG-PET/CT, improve its specificity, and ultimately ascertain how this modality can best be utilized in the diagnostic work up of infectious pathologies.
Assuntos
COVID-19 , Tomografia por Emissão de Pósitrons combinada à Tomografia Computadorizada , Fluordesoxiglucose F18 , Humanos , Pulmão , Tomografia por Emissão de Pósitrons , Compostos Radiofarmacêuticos , SARS-CoV-2RESUMO
INTRODUCTION: Limited data exist regarding the long-term pulmonary sequelae of COVID-19. Identifying features utilizing multiple imaging modalities engenders a clearer picture of the illness's long-term consequences. AREAS COVERED: This review encompasses the common pulmonary findings associated with different imaging modalities during acute and late remission stages of COVID-19 pneumonia. EXPERT OPINION: Chest x-ray, a common preliminary diagnostic imaging technique, is not optimal for extended care due to limited tissue contrast resolution providing suboptimal assessment of pulmonary pathology and subtle interval changes. Ultrasound may be utilized on a case-by-case basis in certain patient populations, or in countries with limited resources. Chest CT's accessibility, high tissue contrast and spatial resolution make it the foremost modality for long-term COVID-19 follow-up. While MRI can viably monitor extrapulmonary disease due to its lack of radiation and high inherent soft-tissue contrast, it has limited pulmonary utility due to motion artifact and alveolar gas decreasing lung signal. Although 18F-FDG-PET/CT is costly and has limited specificity, it can provide molecular level data and inflammation quantification. Lung perfusion scintigraphy may also explain COVID-19 induced thromboembolic events and persistent dyspnea despite normal structural imaging and testing results. Correlating the long-term pulmonary findings of COVID-19 with each imaging modality is essential in elucidating the post-recovery course.
Assuntos
COVID-19 , Humanos , Pulmão/diagnóstico por imagem , Tomografia por Emissão de Pósitrons combinada à Tomografia Computadorizada , SARS-CoV-2 , Tomografia Computadorizada por Raios XRESUMO
Transforming growth factor beta-activated kinase 1 (TAK1) has been implicated for its role in inflammatory signaling and as an important mediator of cellular apoptosis and necroptosis in various cell types. Our recent discovery of a first-in-class, potent and selective TAK1 inhibitor, takinib, represents a novel pharmacological tool to evaluate TAK1's role in cancer. In this study we evaluated the potential therapeutic capacity of TAK1 inhibition on tumor growth and on tumor microenvironment remodeling. In a screen of 16 cancer cell lines, takinib in combination with tumor necrosis factor (TNF) was found to induce cell death (>20%) in 6 out of 16 cell lines. Furthermore, knocking out of TAK1 in MDA-MB-231 cells dramatically increased their sensitization to TNF-mediated apoptosis. In vivo xenographs of MDA-MB-231 TAK1KO tumors displayed delayed tumor growth and increased overall survival compared to TAK1WT controls. Histological and proteomic analysis of TAK1KO tumors showed altered angiogenic signaling and inflammatory signaling via immune cells. Overall, these findings suggest that the targeting of TAK1 in immune mediated cancers may be a novel therapeutic axis.
RESUMO
OBJECTIVES: To examine the ability of takinib, a selective transforming growth factor beta-activated kinase 1 (TAK1) inhibitor, to reduce the severity of murine type II collagen-induced arthritis (CIA), and to affect function of synovial cells. METHODS: Following the induction of CIA, mice were treated daily with takinib (50 mg/kg) and clinical scores assessed. Thirty-six days post-CIA induction, histology was performed on various joints of treated and vehicle-treated animals. Inflammation, pannus, cartilage damage, bone resorption, and periosteal bone formation were quantified. Furthermore, pharmacokinetics of takinib were evaluated by LC-MS in various tissues. Rheumatoid arthritis fibroblast-like synoviocytes (RA-FLS) cells were cultured with 10 µM takinib and cytokine secretion analyzed by cytokine/chemokine proteome array. Cytotoxicity of takinib for RA-FLS was measured with 24 to 48 h cultures in the presence or absence of tumor necrosis factor (TNF). RESULTS: Here, we show takinib's ability to reduce the clinical score in the CIA mouse model of rheumatoid arthritis (RA) (p < 0.001). TAK1 inhibition reduced inflammation (p < 0.01), cartilage damage (p < 0.01), pannus, bone resorption, and periosteal bone formation and periosteal bone width in all joints of treated mice compared to vehicle treated. Significant reduction of inflammation (p < 0.004) and cartilage damage (p < 0.004) were observed in the knees of diseased treated animals, with moderate reduction seen in the forepaws and hind paws. Furthermore, the pharmacokinetics of takinib show rapid plasma clearance (t½ = 21 min). In stimulated RA-FLS cells, takinib reduced GROα, G-CSF, and ICAM-1 pro-inflammatory cytokine signaling. CONCLUSION: Our findings support the hypothesis that TAK1 targeted therapy represents a novel therapeutic axis to treat RA and other inflammatory diseases.
Assuntos
Artrite Experimental/prevenção & controle , Benzamidas/farmacologia , Benzimidazóis/farmacologia , MAP Quinase Quinase Quinases/antagonistas & inibidores , Sinoviócitos/efeitos dos fármacos , Animais , Artrite Experimental/metabolismo , Artrite Experimental/patologia , Artrite Reumatoide/metabolismo , Artrite Reumatoide/patologia , Artrite Reumatoide/prevenção & controle , Benzamidas/farmacocinética , Benzimidazóis/farmacocinética , Células Cultivadas , Citocinas/metabolismo , Modelos Animais de Doenças , Fibroblastos/efeitos dos fármacos , Fibroblastos/metabolismo , Humanos , Inflamação/metabolismo , Inflamação/prevenção & controle , Articulação do Joelho/efeitos dos fármacos , Articulação do Joelho/metabolismo , Articulação do Joelho/patologia , MAP Quinase Quinase Quinases/metabolismo , Camundongos Endogâmicos DBA , Inibidores de Proteínas Quinases/farmacologia , Índice de Gravidade de Doença , Sinoviócitos/metabolismoRESUMO
Immune challenge of invading macrophages at sites of infection is associated with release of TNF, which triggers a local cytokine storm as part of the normal inflammatory response. Whereas this response maybe beneficial in fighting off infections, similar responses triggered in autoimmune diseases contribute significantly to the underlying damaging pathology associated with these diseases. Here we show that Takinib, a highly discriminatory inhibitor of transforming growth factor Beta- activated kinase 1 (TAK1), selectively and potently reduces TNF production in pro-inflammatory THP-1 macrophages. A complete survey of 110 cytokines, showed robust loss of proinflammatory cytokine responsiveness to lipopolysaccharide (LPS) and interferon gamma (IFNγ) challenge in response to Takinib. The mechanisms of action of Takinib was recapitulated in TAK1 KO macrophages. TAK1 KO cells showed significant loss of TNF production as well as release of IL-6 in response to LPS challenge. Furthermore, Takinib blocked the ability of exogenously added LPS to promote phosphorylation of, c-Jun, p38 protein kinases as well as downstream transcription factors regulated by nuclear factor κ-light-chain-enhancer of activated B cells (NFκB). In a mouse LPS challenge model, Takinib significantly reduced TNF serum levels. Our findings demonstrate that Takinib has utility in the treatment inflammatory disease by locally suppressing TNF production from invading macrophages.
Assuntos
MAP Quinase Quinase Quinases/genética , Macrófagos/efeitos dos fármacos , Fator de Necrose Tumoral alfa/metabolismo , Animais , Feminino , Macrófagos/metabolismo , Masculino , Camundongos , Camundongos Endogâmicos C57BLRESUMO
Tumor necrosis factor alpha (TNF-α) has both positive and negative roles in human disease. In certain cancers, TNF-α is infused locally to promote tumor regression, but dose-limiting inflammatory effects limit broader utility. In autoimmune disease, anti-TNF-α antibodies control inflammation in most patients, but these benefits are offset during chronic treatment. TAK1 acts as a key mediator between survival and cell death in TNF-α-mediated signaling. Here, we describe Takinib, a potent and selective TAK1 inhibitor that induces apoptosis following TNF-α stimulation in cell models of rheumatoid arthritis and metastatic breast cancer. We demonstrate that Takinib is an inhibitor of autophosphorylated and non-phosphorylated TAK1 that binds within the ATP-binding pocket and inhibits by slowing down the rate-limiting step of TAK1 activation. Overall, Takinib is an attractive starting point for the development of inhibitors that sensitize cells to TNF-α-induced cell death, with general implications for cancer and autoimmune disease treatment.