Matches in SemOpenAlex for { <https://semopenalex.org/work/W4310209114> ?p ?o ?g. }
Showing items 1 to 94 of
94
with 100 items per page.
- W4310209114 abstract "Introduction When assessing kidney biopsies, pathologists use light microscopy, immunofluorescence, and electron microscopy to describe and diagnose glomerular lesions and diseases. These methods can be laborious, costly, fraught with inter-observer variability, and can have delays in turn-around time. Thus, computational approaches can be designed as screening and/or diagnostic tools, potentially relieving pathologist time, healthcare resources, while also having the ability to identify novel biomarkers, including subvisual features. Methods Here, we implement our recently published biomarker feature extraction (BFE) model along with 3 pre-trained deep learning models (VGG16, VGG19, and InceptionV3) to diagnose 3 glomerular diseases using PAS-stained digital pathology images alone. The BFE model extracts a panel of 233 explainable features related to underlying pathology, which are subsequently narrowed down to 10 morphological and microstructural texture features for classification with a linear discriminant analysis machine learning classifier. 45 patient renal biopsies (371 glomeruli) from minimal change disease (MCD), membranous nephropathy (MN), and thin-basement membrane nephropathy (TBMN) were split into training/validation and held out sets. For the 3 deep learningmodels, data augmentation and Grad-CAM were used for better performance and interpretability. Results The BFE model showed glomerular validation accuracy of 67.6% and testing accuracy of 76.8%. All deep learning approaches had higher validation accuracies (most for VGG16 at 78.5%) but lower testing accuracies. The highest testing accuracy at the glomerular level was VGG16 at 71.9%, while at the patient-level was InceptionV3 at 73.3%. Discussion The results highlight the potential of both traditional machine learning and deep learning-based approaches for kidney biopsy evaluation." @default.
- W4310209114 created "2022-11-30" @default.
- W4310209114 creator A5008508358 @default.
- W4310209114 creator A5025356372 @default.
- W4310209114 creator A5031948219 @default.
- W4310209114 creator A5058769828 @default.
- W4310209114 creator A5070051485 @default.
- W4310209114 date "2022-11-29" @default.
- W4310209114 modified "2023-09-27" @default.
- W4310209114 title "Machine learning in renal pathology" @default.
- W4310209114 cites W2108598243 @default.
- W4310209114 cites W2129112648 @default.
- W4310209114 cites W2766877747 @default.
- W4310209114 cites W2886857600 @default.
- W4310209114 cites W2945334889 @default.
- W4310209114 cites W2952527443 @default.
- W4310209114 cites W2964756323 @default.
- W4310209114 cites W2971487518 @default.
- W4310209114 cites W2982011997 @default.
- W4310209114 cites W2994910508 @default.
- W4310209114 cites W2997214020 @default.
- W4310209114 cites W3005621234 @default.
- W4310209114 cites W3037032032 @default.
- W4310209114 cites W3041873840 @default.
- W4310209114 cites W3044711955 @default.
- W4310209114 cites W3102320028 @default.
- W4310209114 cites W3129033913 @default.
- W4310209114 cites W3185122822 @default.
- W4310209114 cites W3212889265 @default.
- W4310209114 cites W4200059501 @default.
- W4310209114 cites W4220936506 @default.
- W4310209114 cites W4283519332 @default.
- W4310209114 doi "https://doi.org/10.3389/fneph.2022.1007002" @default.
- W4310209114 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37675000" @default.
- W4310209114 hasPublicationYear "2022" @default.
- W4310209114 type Work @default.
- W4310209114 citedByCount "0" @default.
- W4310209114 crossrefType "journal-article" @default.
- W4310209114 hasAuthorship W4310209114A5008508358 @default.
- W4310209114 hasAuthorship W4310209114A5025356372 @default.
- W4310209114 hasAuthorship W4310209114A5031948219 @default.
- W4310209114 hasAuthorship W4310209114A5058769828 @default.
- W4310209114 hasAuthorship W4310209114A5070051485 @default.
- W4310209114 hasBestOaLocation W43102091141 @default.
- W4310209114 hasConcept C108583219 @default.
- W4310209114 hasConcept C119857082 @default.
- W4310209114 hasConcept C126322002 @default.
- W4310209114 hasConcept C133397671 @default.
- W4310209114 hasConcept C142724271 @default.
- W4310209114 hasConcept C153180895 @default.
- W4310209114 hasConcept C154945302 @default.
- W4310209114 hasConcept C2776115139 @default.
- W4310209114 hasConcept C2777522853 @default.
- W4310209114 hasConcept C2780091579 @default.
- W4310209114 hasConcept C2780368995 @default.
- W4310209114 hasConcept C2781067378 @default.
- W4310209114 hasConcept C41008148 @default.
- W4310209114 hasConcept C69738355 @default.
- W4310209114 hasConcept C71924100 @default.
- W4310209114 hasConcept C95623464 @default.
- W4310209114 hasConceptScore W4310209114C108583219 @default.
- W4310209114 hasConceptScore W4310209114C119857082 @default.
- W4310209114 hasConceptScore W4310209114C126322002 @default.
- W4310209114 hasConceptScore W4310209114C133397671 @default.
- W4310209114 hasConceptScore W4310209114C142724271 @default.
- W4310209114 hasConceptScore W4310209114C153180895 @default.
- W4310209114 hasConceptScore W4310209114C154945302 @default.
- W4310209114 hasConceptScore W4310209114C2776115139 @default.
- W4310209114 hasConceptScore W4310209114C2777522853 @default.
- W4310209114 hasConceptScore W4310209114C2780091579 @default.
- W4310209114 hasConceptScore W4310209114C2780368995 @default.
- W4310209114 hasConceptScore W4310209114C2781067378 @default.
- W4310209114 hasConceptScore W4310209114C41008148 @default.
- W4310209114 hasConceptScore W4310209114C69738355 @default.
- W4310209114 hasConceptScore W4310209114C71924100 @default.
- W4310209114 hasConceptScore W4310209114C95623464 @default.
- W4310209114 hasLocation W43102091141 @default.
- W4310209114 hasLocation W43102091142 @default.
- W4310209114 hasOpenAccess W4310209114 @default.
- W4310209114 hasPrimaryLocation W43102091141 @default.
- W4310209114 hasRelatedWork W3006943036 @default.
- W4310209114 hasRelatedWork W3129898729 @default.
- W4310209114 hasRelatedWork W4206534706 @default.
- W4310209114 hasRelatedWork W4229079080 @default.
- W4310209114 hasRelatedWork W4299487748 @default.
- W4310209114 hasRelatedWork W4310880831 @default.
- W4310209114 hasRelatedWork W4380075502 @default.
- W4310209114 hasRelatedWork W4385957992 @default.
- W4310209114 hasRelatedWork W4385965371 @default.
- W4310209114 hasRelatedWork W4386025632 @default.
- W4310209114 hasVolume "2" @default.
- W4310209114 isParatext "false" @default.
- W4310209114 isRetracted "false" @default.
- W4310209114 workType "article" @default.