Purpose: To evaluate the evolution of morphologic features of autoimmune pancreatitis (AIP) at computed tomography (CT) and to identify imaging features that can predict AIP response to corticosteroid therapy (CST).
Materials And Methods: This HIPAA-compliant retrospective study had institutional review board approval. From among a cohort of 63 patients with AIP, 15 patients (12 men, three women; mean age, 64.7 years; age range, 30-84 years) who underwent sequential CT examinations before treatment were included to assess the evolution of disease by reviewing pancreatic, peripancreatic, and ductal changes. Of these patients, 13 received CST and underwent posttreatment CT; these CT studies were evaluated to determine if there were imaging features that could predict response to CST.
Results: The disease evolved from changes of diffuse (14 of 15 patients) or focal (one of 15 patients) parenchymal swelling, peripancreatic stranding (10 of 15 patients), "halo" (nine of 15 patients), pancreatic duct changes (15 of 15 patients), and distal common bile duct narrowing (12 of 15 patients) to either resolution or development of ductal strictures and/or focal masslike swelling. In 13 patients treated with CST, favorable response to treatment was seen in those with diffuse pancreatic and peripancreatic changes. Suboptimal response was seen in patients with ductal stricture formation (two of 13 patients) and in those in whom focal masslike swellings persisted after resolution of diffuse changes (seven of 13 patients).
Conclusion: CT features like diffuse swelling and halo respond favorably to CST and likely reflect an early inflammatory phase, whereas features like ductal strictures and focal masslike swelling are predictive of a suboptimal response and symbolize a late stage with predominance of fibrosis.
Download full-text PDF |
Source |
---|---|
http://dx.doi.org/10.1148/radiol.2493080279 | DOI Listing |
PLoS Comput Biol
January 2025
School of Software, Taiyuan University of Technology, Taiyuan, China.
Personalized cancer drug treatment is emerging as a frontier issue in modern medical research. Considering the genomic differences among cancer patients, determining the most effective drug treatment plan is a complex and crucial task. In response to these challenges, this study introduces the Adaptive Sparse Graph Contrastive Learning Network (ASGCL), an innovative approach to unraveling latent interactions in the complex context of cancer cell lines and drugs.
View Article and Find Full Text PDFPLoS One
January 2025
Shanghai Xinhao Information Technology Co., Ltd., Shanghai, China.
Machine learning techniques and computer-aided methods are now widely used in the pre-discovery tasks of drug discovery, effectively improving the efficiency of drug development and reducing the workload and cost. In this study, we used multi-source heterogeneous network information to build a network model, learn the network topology through multiple network diffusion algorithms, and obtain compressed low-dimensional feature vectors for predicting drug-target interactions (DTIs). We applied the metropolis-hasting random walk (MHRW) algorithm to improve the performance of the random walk with restart (RWR) algorithm, forming the basis by which the self-loop probability of the current node is removed.
View Article and Find Full Text PDFPLoS One
January 2025
School of Industrial and Management Engineering, Korea University, Seongbuk-gu, Seoul, Republic of Korea.
A medical specialty prediction system for remote diagnosis can reduce the unexpected costs incurred by first-visit patients who visit the wrong hospital department for their symptoms. To develop medical specialty prediction systems, several researchers have explored clinical predictive models using real medical text data. Medical text data include large amounts of information regarding patients, which increases the sequence length.
View Article and Find Full Text PDFPLoS One
January 2025
Aston Institute of Health and Neurodevelopment, Aston University, Birmingham, United Kingdom.
Survivors of pediatric brain tumours are at a high risk of cognitive morbidity. Reliable individual-level predictions regarding the likelihood, degree, and affected domains of cognitive impairment would be clinically beneficial. While established risk factors exist, quantitative MRI analysis may enhance predictive value, above and beyond current clinical risk models.
View Article and Find Full Text PDFJ Chem Theory Comput
January 2025
Department of Chemical and Biomolecular Engineering, University of Notre Dame, Notre Dame, Indiana 46556, United States.
Algorithmic reaction explorations based on transition state searches can now routinely predict relatively short reaction sequences involving small molecules. However, applying these algorithms to deeper chemical reaction network (CRN) exploration still requires the development of more efficient and accurate exploration policies. Here, an exploration algorithm, which we name yet another kinetic strategy (YAKS), is demonstrated that uses microkinetic simulations of the nascent network to achieve cost-effective, deep network exploration.
View Article and Find Full Text PDFEnter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!