A Few-shot Learning Approach for Multi-Task CT Image Classification

Habıb M. E. H., Küçükmanisa A., Urhan O.

14th INTERNATIONAL CONFERENCE on ELECTRICAL and ELECTRONICS ENGINEERING, Bursa, Türkiye, 30 Kasım - 02 Aralık 2023, ss.1-4

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Basıldığı Şehir: Bursa
  • Basıldığı Ülke: Türkiye
  • Sayfa Sayıları: ss.1-4
  • Kocaeli Üniversitesi Adresli: Evet

Özet

Few-Shot Learning (FSL) demonstrates significant promise in addressing the limitations of traditional deep learning, especially those pertaining to data scarcity. This specific limitation is a common issue in the medical field, especially in the case of new diseases. In this study, we employed an FSL approach by training it on a custom medical dataset comprised of Computed Temography (CT) images encompassing diverse medical tasks. To showcase the efficacy of Few-Shot Learning (FSL) in the medical domain, we utilized the ProtoNet both with and without LASTShot. Furthermore, we conducted training using the ISIC 2018 dataset to evaluate their performance on a different type of medical imagery. For the CT multi-task dataset, the ProtoNet method delivered promising outcomes, achieving accuracy rates of 80%, 96%, and 92% in 1-shot, 5-shot, and 10-shot scenarios, respectively. Additionally, our results on the ISIC dataset underscored the significance of a broader range of tasks for robust FSL performance.