A Deep Learning Onion Peeling Approach to Measure Oral Epithelium Layer Number
Zhang X, Gleber-Netto F, Wang S, Jin K, Yang D, Gillenwater A, Myers J, Ferrarotto R, Pickering C, Xiao G. A Deep Learning Onion Peeling Approach to Measure Oral Epithelium Layer Number. Cancers 2023, 15: 3891. PMID: 37568707, PMCID: PMC10416878, DOI: 10.3390/cancers15153891.Peer-Reviewed Original ResearchOral epitheliumNeck squamous cell carcinomaSquamous cell carcinomaPatients' qualityCell carcinomaDysplasia severityEarly diagnosisPathologist's examinationOral cavityComplex cancersClinical relevanceDysplasia diagnosisSurvival analysisEpithelium layerDiagnostic potentialCell layerIntra-observer variationDiagnosisEpitheliumClose correlationPotential additionPrognosisCarcinomaCancerDeep learning‐based pathology image analysis predicts cancer progression risk in patients with oral leukoplakia
Zhang X, Gleber‐Netto F, Wang S, Martins‐Chaves R, Gomez R, Vigneswaran N, Sarkar A, William W, Papadimitrakopoulou V, Williams M, Bell D, Palsgrove D, Bishop J, Heymach J, Gillenwater A, Myers J, Ferrarotto R, Lippman S, Pickering C, Xiao G. Deep learning‐based pathology image analysis predicts cancer progression risk in patients with oral leukoplakia. Cancer Medicine 2023, 12: 7508-7518. PMID: 36721313, PMCID: PMC10067069, DOI: 10.1002/cam4.5478.Peer-Reviewed Original ResearchConceptsLow-risk groupOral leukoplakiaOL patientsProgression riskOral mucosaHigh-risk patientsOral cancer developmentRisk stratification modelCancer progression riskLarge interobserver variabilityEarly diagnosisHigh riskDysplasia gradingAbnormal morphological featuresOral epitheliumOC developmentEarly interventionLow-risk onesPatientsStratification modelCancer developmentCancer progressionInterobserver variabilityLeukoplakiaRisk