Mycobacteria identification is crucial to diagnose tuberculosis. Since the bacillus is very small, finding it in Ziehl–Neelsen (ZN)-stained slides is a long task requiring significant pathologist’s effort. We developed an automated (AI-based) method of identification of mycobacteria. We prepared a training dataset of over 260,000 positive and over 700,000,000 negative patches annotated on scans of 510 whole slide images (WSI) of ZN-stained slides (110 positive and 400 negative). Several image augmentation techniques coupled with different custom computer vision architectures were used. WSIs automatic analysis was followed by a report indicating areas more likely to present mycobacteria. Our model performs AI-based diagnosis (the final decision of the diagnosis of WSI belongs to the pathologist). The results were validated internally on a dataset of 286,000 patches and tested in pathology laboratory settings on 60 ZN slides (23 positive and 37 negative). We compared the pathologists’ results obtained by separately evaluating slides and WSIs with the results given by a pathologist aided by automatic analysis of WSIs. Our architecture showed 0.977 area under the receiver operating characteristic curve. The clinical test presented 98.33% accuracy, 95.65% sensitivity, and 100% specificity for the AI-assisted method, outperforming any other AI-based proposed methods for AFB detection.
AIM:To analyze the demographic characteristics and surgical outcomes of the largest series of patients with pediatric aneurysms reported in Romania, in consideration of the primary factors that lead to good long-term outcomes. Given that all cases involved ruptured aneurysms, we also investigated the ability of microsurgical clipping to prevent massive hemorrhage andaggravation of neurological deficits. MATERIAL and METHODS:This multicenter retrospective study included 47 pediatric patients (<16 years old) who underwent operation over the 20-year period between January 1999 and January 2019. We analyzed medical records and imaging findings in each patient. Treatment consisted of open microsurgical dissection (clipping) and endovascular embolization (coiling). RESULTS:Mean patient age was 14.3 years, ranging from 5 months to 16 years, with 28 boys (59.5%) and 19 girls (40.4%). In our series, pediatric aneurysms represented 6.1% of all intracranial aneurysms (771 cases). Clinical features were dominated by headache (45 cases, 95.7%), neck stiffness (43 cases, 91.4%) and vomiting (42 cases, 89.3%). The most frequently involved locations were the anterior communicating artery (17 cases, 36.1%), middle cerebral artery (12 cases, 25.5%), and internal carotid artery bifurcation (9 cases, 19.1%). Glasgow Outcome Scale scores at 6 months indicated good recovery in 36 patients (76.5%), moderate disability in ninepatients (19.1%), severe disability in one patient (2.1%), and (preoperative) death in one patient (2.1%). CONCLUSION:Intracranial aneurysms in children are very rare. Early diagnosis based on brain imaging and microsurgical treatment is essential for attaining excellent results.Primary factors such as preoperative status, child profile, aneurysm size, treatment choice, and timing of the operation influence both short and long-term outcomes.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.