Frozen-to-Paraffin: Categorization of Histological Frozen Sections by the Aid of Paraffin Sections and Generative Adversarial Networks
This work addresses the problem of lower quality frozen sections leading to higher miss-classification rates in automated decision support for thyroid cancer diagnosis during surgery, which is an incremental improvement for pathologists and surgeons.
This paper investigates the impact of histological section type (frozen vs. paraffin) on automated thyroid cancer classification and explores whether translating frozen sections to paraffin-like images can improve classification scores. They found that a frozen-to-paraffin translation, combined with a specific data augmentation strategy, increased classification accuracy.
In contrast to paraffin sections, frozen sections can be quickly generated during surgical interventions. This procedure allows surgeons to wait for histological findings during the intervention to base intra-operative decisions on the outcome of the histology. However, compared to paraffin sections, the quality of frozen sections is typically lower, leading to a higher ratio of miss-classification. In this work, we investigated the effect of the section type on automated decision support approaches for classification of thyroid cancer. This was enabled by a data set consisting of pairs of sections for individual patients. Moreover, we investigated, whether a frozen-to-paraffin translation could help to optimize classification scores. Finally, we propose a specific data augmentation strategy to deal with a small amount of training data and to increase classification accuracy even further.