Ho C.-JCalderon-Delgado MLin M.-YTjiu J.-WHuang S.-LHOMER H. CHEN2022-04-252022-04-25202108956111https://www.scopus.com/inward/record.uri?eid=2-s2.0-85116513776&doi=10.1016%2fj.compmedimag.2021.101992&partnerID=40&md5=aefaac39b7ab847e21268075e1a05a2dhttps://scholars.lib.ntu.edu.tw/handle/123456789/607100We investigate the speed and performance of squamous cell carcinoma (SCC) classification from full-field optical coherence tomography (FF-OCT) images based on the convolutional neural network (CNN). Due to the unique characteristics of SCC features, the high variety of CNN, and the high volume of our 3D FF-OCT dataset, progressive model construction is a time-consuming process. To address the issue, we develop a training strategy for data selection that makes model training 16 times faster by exploiting the dependency between images and the knowledge of SCC feature distribution. The speedup makes progressive model construction computationally feasible. Our approach further refines the regularization, channel attention, and optimization mechanism of SCC classifier and improves the accuracy of SCC classification to 87.12% at the image level and 90.10% at the tomogram level. The results are obtained by testing the proposed approach on an FF-OCT dataset with over one million mouse skin images. ? 2021 Elsevier LtdConvolutional neural networkDeep learningOptical coherence tomographyRegularizationSquamous cell carcinomaTraining strategyConvolutionConvolutional neural networksData reductionDeep neural networksImage classificationImage enhancementLarge datasetStatistical testsData SelectionFull-field optical coherence tomographiesImage dataModel constructionProgressive modelsRegularisationOptical tomographyArticlecancer classificationcancer diagnosisclassification algorithmclassifiercomparative studycomputer assisted diagnosisconvolutional neural networkdeep learningdiagnostic accuracyfeature selectionfull field optical coherence tomographyhumanoptical coherence tomographyresidual neural networksquamous cell skin carcinomathree-dimensional imaginganimaldiagnostic imagingmousesquamous cell carcinomaAnimalsCarcinoma, Squamous CellMiceNeural Networks, ComputerTomography, Optical Coherence[SDGs]SDG3journal article10.1016/j.compmedimag.2021.101992346269082-s2.0-85116513776