Abstract B023: Multicenter histology image integration and multiscale deep learning for pediatric sarcoma subtype classification
Thiesen A, Domanskyi S, Foroughi pour A, Sheridan T, Neuhauser S, Stetson A, Dannheim K, Cameron D, Ahn S, Wu H, Christison-Lagay E, Bult C, Chuang J, Rubinstein J. Abstract B023: Multicenter histology image integration and multiscale deep learning for pediatric sarcoma subtype classification. Cancer Research 2024, 84: b023-b023. DOI: 10.1158/1538-7445.pediatric24-b023.Peer-Reviewed Original ResearchArtificial neural networkFeature extractionDeep learningTile sizeDeep learning feature extractionConvolutional artificial neural networksHistology datasetDeep learning backbonesTraining of artificial neural networksLearning feature extractionNon-overlapping tilesImage integrationImage format conversionFeature concatenationStain normalizationTiling parametersClassification performanceANN classifierClassification accuracyNeural networkAutomated classificationTraining modelDigitization of histology slidesFormat conversionDataset