Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285677614> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W4285677614 endingPage "1126" @default.
- W4285677614 startingPage "1119" @default.
- W4285677614 abstract "The diagnosis of superficial fungal infections is still mostly based on direct microscopic examination with potassium hydroxide solution. However, this method can be time consuming, and its diagnostic accuracy rates vary widely depending on the clinician's experience.This study presents a deep neural network structure that enables the rapid solutions for these problems and can perform automatic fungi detection in grayscale images without dyes.One hundred sixty microscopic full field photographs containing the fungal element, obtained from patients with onychomycosis, and 297 microscopic full field photographs containing dissolved keratin obtained from normal nails were collected. Smaller patches containing fungi (n = 1835) and keratin (n = 5238) were extracted from these full field images. In order to detect fungus and keratin, VGG16 and InceptionV3 models were developed by the use of these patches. The diagnostic performance of models was compared with 16 dermatologists by using 200 test patches.For the VGG16 model, the InceptionV3 model and 16 dermatologists, mean accuracy rates were 88.10 ± 0.8%, 88.78 ± 0.35% and 74.53 ± 8.57%, respectively; mean sensitivity rates were 75.04 ± 2.73%, 74.93 ± 4.52% and 74.81 ± 19.51%, respectively; and mean specificity rates were 92.67 ± 1.17%, 93.78 ± 1.74% and 74.25 ± 18.03%, respectively. The models were statistically superior to dermatologists according to rates of accuracy and specificity but not to sensitivity (p < .0001, p < .005 and p > .05, respectively). Area under curve values of the VGG16 and InceptionV3 models were 0.9339 and 0.9292, respectively.Our research demonstrates that it is possible to build an automated system capable of detecting fungi present in microscopic images employing the proposed deep learning models. It has great potential for fungal detection applications based on AI." @default.
- W4285677614 created "2022-07-17" @default.
- W4285677614 creator A5042761214 @default.
- W4285677614 creator A5045041208 @default.
- W4285677614 creator A5062069862 @default.
- W4285677614 creator A5084840198 @default.
- W4285677614 creator A5090462778 @default.
- W4285677614 date "2022-07-31" @default.
- W4285677614 modified "2023-09-26" @default.
- W4285677614 title "Deep convolutional neural networks for onychomycosis detection using microscopic images with <scp>KOH</scp> examination" @default.
- W4285677614 cites W1543243120 @default.
- W4285677614 cites W1959679033 @default.
- W4285677614 cites W2037608359 @default.
- W4285677614 cites W2129763285 @default.
- W4285677614 cites W2145134451 @default.
- W4285677614 cites W2516355888 @default.
- W4285677614 cites W2588978745 @default.
- W4285677614 cites W2589164862 @default.
- W4285677614 cites W2768673271 @default.
- W4285677614 cites W2785200097 @default.
- W4285677614 cites W2806178426 @default.
- W4285677614 cites W2956154093 @default.
- W4285677614 cites W2976398475 @default.
- W4285677614 cites W2979947001 @default.
- W4285677614 cites W3033941366 @default.
- W4285677614 cites W3034678801 @default.
- W4285677614 cites W3046220160 @default.
- W4285677614 cites W3125817276 @default.
- W4285677614 cites W3196142250 @default.
- W4285677614 cites W4210481870 @default.
- W4285677614 cites W4242379988 @default.
- W4285677614 doi "https://doi.org/10.1111/myc.13498" @default.
- W4285677614 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35842749" @default.
- W4285677614 hasPublicationYear "2022" @default.
- W4285677614 type Work @default.
- W4285677614 citedByCount "4" @default.
- W4285677614 countsByYear W42856776142022 @default.
- W4285677614 countsByYear W42856776142023 @default.
- W4285677614 crossrefType "journal-article" @default.
- W4285677614 hasAuthorship W4285677614A5042761214 @default.
- W4285677614 hasAuthorship W4285677614A5045041208 @default.
- W4285677614 hasAuthorship W4285677614A5062069862 @default.
- W4285677614 hasAuthorship W4285677614A5084840198 @default.
- W4285677614 hasAuthorship W4285677614A5090462778 @default.
- W4285677614 hasConcept C154945302 @default.
- W4285677614 hasConcept C178790620 @default.
- W4285677614 hasConcept C185592680 @default.
- W4285677614 hasConcept C2779439175 @default.
- W4285677614 hasConcept C2989005 @default.
- W4285677614 hasConcept C41008148 @default.
- W4285677614 hasConcept C71924100 @default.
- W4285677614 hasConcept C81363708 @default.
- W4285677614 hasConceptScore W4285677614C154945302 @default.
- W4285677614 hasConceptScore W4285677614C178790620 @default.
- W4285677614 hasConceptScore W4285677614C185592680 @default.
- W4285677614 hasConceptScore W4285677614C2779439175 @default.
- W4285677614 hasConceptScore W4285677614C2989005 @default.
- W4285677614 hasConceptScore W4285677614C41008148 @default.
- W4285677614 hasConceptScore W4285677614C71924100 @default.
- W4285677614 hasConceptScore W4285677614C81363708 @default.
- W4285677614 hasIssue "12" @default.
- W4285677614 hasLocation W42856776141 @default.
- W4285677614 hasLocation W42856776142 @default.
- W4285677614 hasOpenAccess W4285677614 @default.
- W4285677614 hasPrimaryLocation W42856776141 @default.
- W4285677614 hasRelatedWork W1531601525 @default.
- W4285677614 hasRelatedWork W1990781990 @default.
- W4285677614 hasRelatedWork W2054548548 @default.
- W4285677614 hasRelatedWork W2607424097 @default.
- W4285677614 hasRelatedWork W2748952813 @default.
- W4285677614 hasRelatedWork W2899084033 @default.
- W4285677614 hasRelatedWork W2948807893 @default.
- W4285677614 hasRelatedWork W2949888708 @default.
- W4285677614 hasRelatedWork W2950916228 @default.
- W4285677614 hasRelatedWork W2778153218 @default.
- W4285677614 hasVolume "65" @default.
- W4285677614 isParatext "false" @default.
- W4285677614 isRetracted "false" @default.
- W4285677614 workType "article" @default.