PurposeThe purpose of this study was to determine whether computed tomography (CT)-based machine learning of radiomics features could help distinguish autoimmune pancreatitis (AIP) from pancreatic ductal adenocarcinoma (PDAC).Materials and MethodsEighty-nine patients with AIP (65 men, 24 women; mean age, 59.7 ± 13.9 [SD] years; range: 21–83 years) and 93 patients with PDAC (68 men, 25 women; mean age, 60.1 ± 12.3 [SD] years; range: 36–86 years) were retrospectively included. All patients had dedicated dual-phase pancreatic protocol CT between 2004 and 2018. Thin-slice images (0.75/0.5 mm thickness/increment) were compared with thick-slices images (3 or 5 mm thickness/increment). Pancreatic regions involved by PDAC or AIP (areas of enlargement, altered enhancement, effacement of pancreatic duct) as well as uninvolved parenchyma were segmented as three-dimensional volumes. Four hundred and thirty-one radiomics features were extracted and a random forest was used to distinguish AIP from PDAC. CT data of 60 AIP and 60 PDAC patients were used for training and those of 29 AIP and 33 PDAC independent patients were used for testing.ResultsThe pancreas was diffusely involved in 37 (37/89; 41.6%) patients with AIP and not diffusely in 52 (52/89; 58.4%) patients. Using machine learning, 95.2% (59/62; 95% confidence interval [CI]: 89.8–100%), 83.9% (52:67; 95% CI: 74.7–93.0%) and 77.4% (48/62; 95% CI: 67.0–87.8%) of the 62 test patients were correctly classified as either having PDAC or AIP with thin-slice venous phase, thin-slice arterial phase, and thick-slice venous phase CT, respectively. Three of the 29 patients with AIP (3/29; 10.3%) were incorrectly classified as having PDAC but all 33 patients with PDAC (33/33; 100%) were correctly classified with thin-slice venous phase with 89.7% sensitivity (26/29; 95% CI: 78.6–100%) and 100% specificity (33/33; 95% CI: 93–100%) for the diagnosis of AIP, 95.2% accuracy (59/62; 95% CI: 89.8–100%) and area under the curve of 0.975 (95% CI: 0.936–1.0).ConclusionsRadiomic features help differentiate AIP from PDAC with an overall accuracy of 95.2%. 相似文献
BackgroundCoronary artery bypass grafting (CABG) improves survival in patients with heart failure and severely reduced left ventricular systolic function (LVEF). Limited data exist regarding adverse cardiovascular event rates after CABG in patients with heart failure with midrange ejection fraction (HFmrEF; LVEF > 40% and < 55%).MethodsWe analyzed data on isolated CABG patients from the Veterans Affairs national database (2010-2019). We stratified patients into control (normal LVEF and no heart failure), HFmrEF, and heart failure with reduced LVEF (HFrEF) groups. We compared all-cause mortality and heart failure hospitalization rates between groups with a Cox model and recurrent events analysis, respectively.ResultsIn 6533 veterans, HFmrEF and HFrEF was present in 1715 (26.3%) and 566 (8.6%) respectively; the control group had 4252 (65.1%) patients. HFrEF patients were more likely to have diabetes mellitus (59%), insulin therapy (36%), and previous myocardial infarction (31%). Anemia was more prevalent in patients with HFrEF (49%) as was a lower serum albumin (mean, 3.6 mg/dL). Compared with the control group, a higher risk of death was observed in the HFmrEF (hazard ratio [HR], 1.3 [1.2-1.5)] and HFrEF (HR, 1.5 [1.2-1.7]) groups. HFmrEF patients had the higher risk of myocardial infarction (subdistribution HR, 1.2 [1-1.6]; P = .04). Risk of heart failure hospitalization was higher in patients with HFmrEF (HR, 4.1 [3.5-4.7]) and patients with HFrEF (HR, 7.2 [6.2-8.5]).ConclusionsHeart failure with midrange ejection fraction negatively affects survival after CABG. These patients also experience higher rates myocardial infarction and heart failure hospitalization. 相似文献
Purpose: To study, with computational models, the utility of power modulation to reduce tissue temperature heterogeneity for variable nanoparticle distributions in magnetic nanoparticle hyperthermia.
Methods: Tumour and surrounding tissue were modeled by elliptical two- and three-dimensional computational phantoms having six different nanoparticle distributions. Nanoparticles were modeled as point heat sources having amplitude-dependent loss power. The total number of nanoparticles was fixed, and their spatial distribution and heat output were varied. Heat transfer was computed by solving the Pennes’ bioheat equation using finite element methods (FEM) with temperature-dependent blood perfusion. Local temperature was regulated using a proportional-integral-derivative (PID) controller. Tissue temperature, thermal dose and tissue damage were calculated. The required minimum thermal dose delivered to the tumor was kept constant, and heating power was adjusted for comparison of both the heating methods.
Results: Modulated power heating produced lower and more homogeneous temperature distributions than did constant power heating for all studied nanoparticle distributions. For a concentrated nanoparticle distribution, located off-center within the tumor, the maximum temperatures inside the tumor were 16% lower for modulated power heating when compared to constant power heating. This resulted in less damage to surrounding normal tissue. Modulated power heating reached target thermal doses up to nine-fold more rapidly when compared to constant power heating.
Conclusions: Controlling the temperature at the tumor-healthy tissue boundary by modulating the heating power of magnetic nanoparticles demonstrably compensates for a variable nanoparticle distribution to deliver effective treatment. 相似文献
ObjectiveSystematically review the abnormalities in event related potential (ERP) recorded in Rett Syndrome (RTT) patients and animals in search of translational biomarkers of deficits related to the particular neurophysiological processes of known genetic origin (MECP2 mutations).MethodsPubmed, ISI Web of Knowledge and BIORXIV were searched for the relevant articles according to PRISMA standards.ResultsERP components are generally delayed across all sensory modalities both in RTT patients and its animal model, while findings on ERPs amplitude strongly depend on stimulus properties and presentation rate. Studies on RTT animal models uncovered the abnormalities in the excitatory and inhibitory transmission as critical mechanisms underlying the ERPs changes, but showed that even similar ERP alterations in auditory and visual domains have a diverse neural basis. A range of novel approaches has been developed in animal studies bringing along the meaningful neurophysiological interpretation of ERP measures in RTT patients.ConclusionsWhile there is a clear evidence for sensory ERPs abnormalities in RTT, to further advance the field there is a need in a large-scale ERP studies with the functionally-relevant experimental paradigms.SignificanceThe review provides insights into domain-specific neural basis of the ERP abnormalities and promotes clinical application of the ERP measures as the non-invasive functional biomarkers of RTT pathophysiology. 相似文献
Additive manufacturing is a rapidly emerging technology which is being successfully implemented in the various field of medicine as well as in orthopaedics, where it has applications in reducing cartilage defects and treatments of bones. The technology helps through systematic collection of information about the shape of the "defects" and precise fabrication of complex 3D constructs such as cartilage, heart valve, trachea, myocardial bone tissue and blood vessels. In this paper, a large number of the relevant research papers on the additive manufacturing and its application in medical specifically orthopaedics are identified through Scopus had been studied using Bibliometric analysis and application analysis is undertaken. The bibliometric analysis shows that there is an increasing trend in the research reports on additive manufacturing applications in the field of orthopaedics. Discussions are on using technological advancement like scanning techniques and various challenges of the orthopaedic being met by additive manufacturing technology. For patient-specific orthopaedic applications, these techniques incorporate clinical practice and use for effective planning. 3D printed models printed by this technology are accepted for orthopaedic surgery such as revision of lumbar discectomy, pelvic surgery and large scapular osteochondroma. The applications of additive manufacturing in orthopaedics will experience a rapid translation in future. An orthopaedic surgeon can convert need/idea into a reality by using computer-aided design (CAD) software, analysis software to facilitate the manufacturing. Thus, AM provides a comprehensive opportunity to manufacture orthopaedic implantable medical devices. 相似文献