2020/12/15 by Michael Gadermayr, Maximilian Tschuchnig, Gadermayr, Michael +11
Biochemistry, Genetics and Molecular Biology · Computer Science · #AI in cancer detection #Biomedical Text Mining and Ontologies #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #FOS: Electrical engineering #Image and Video Processing (eess.IV) #Machine Learning (cs.LG) #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2012.08158
openalex publication_date 2020/12/15 · openalex created_date 2022/10/01 · openalex updated_date 2026/07/28
In contrast to paraffin sections, frozen sections can be quickly generated\nduring surgical interventions. This procedure allows surgeons to wait for\nhistological findings during the intervention to base intra-operative decisions\non the outcome of the histology. However, compared to paraffin sections, the\nquality of frozen sections is typically lower, leading to a higher ratio of\nmiss-classification. In this work, we investigated the effect of the section\ntype on automated decision support approaches for classification of thyroid\ncancer. This was enabled by a data set consisting of pairs of sections for\nindividual patients. Moreover, we investigated, whether a frozen-to-paraffin\ntranslation could help to optimize classification scores. Finally, we propose a\nspecific data augmentation strategy to deal with a small amount of training\ndata and to increase classification accuracy even further.\n