首页|Pontifical University Javeriana Reports Findings in Malaria (CAM:a novel aid sy stem to analyse the coloration quality of thick bloodsmears using image process ing and machine learning techniques)
Pontifical University Javeriana Reports Findings in Malaria (CAM:a novel aid sy stem to analyse the coloration quality of thick bloodsmears using image process ing and machine learning techniques)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews Daily News – New research on Mosquito-Borne Disease s - Malaria is the subject of a report.According to news reporting out of Bogot a, Colombia, by NewsRx editors, research stated, “Battlingmalaria’s morbidity a nd mortality rates demands innovative methods related to malaria diagnosis. Thic kblood smears (TBS) are the gold standard for diagnosing malaria, but their col oration quality is dependenton supplies and adherence to standard protocols.”Funders for this research include Facebook Inc., CV4GC 2019 RFP Research Award, Pontificia UniversidadJaveriana, M.Sc. program in Bioengineering at Pontificia Universidad Javeriana.Our news journalists obtained a quote from the research from Pontifical Universi ty Javeriana, “Machinelearning has been proposed to automate diagnosis, but the impact of smear coloration on parasite detectionhas not yet been fully explore d. To develop Coloration Analysis in Malaria (CAM), an image databasecontaining 600 images was created. The database was randomly divided into training (70% ), validation (15%), and test (15%) sets. Nineteen fea ture vectors were studied based on variances, correlation coefficients,and hist ograms (specific variables from histograms, full histograms, and principal compo nents from thehistograms). The Machine Learning Matlab Toolbox was used to sele ct the best candidate featurevectors and machine learning classifiers. The cand idate classifiers were then tuned for validation andtested to ultimately select the best one. This work introduces CAM, a machine learning system designedfor automatic TBS image quality analysis. The results demonstrated that the cubic SV M classifieroutperformed others in classifying coloration quality in TBS, achie ving a true negative rate of 95% anda true positive rate of 97% . An image-based approach was developed to automatically evaluate thecoloration quality of TBS. This finding highlights the potential of image-based analysis t o assess TBScoloration quality.”
BogotaColombiaSouth AmericaCyborgsEmerging TechnologiesHealth and MedicineMachine LearningMalariaMosquit o-Borne DiseasesProtozoan Infections
NETL
NSTL
