Transferring Feature Extractors for Interpretable Cancer Image Classification

Publish Year: 1400
نوع سند: مقاله کنفرانسی
زبان: English
View: 533

This Paper With 9 Page And PDF Format Ready To Download

  • Certificate
  • من نویسنده این مقاله هستم

این Paper در بخشهای موضوعی زیر دسته بندی شده است:

استخراج به نرم افزارهای پژوهشی:

لینک ثابت به این Paper:

شناسه ملی سند علمی:

ECMCONF05_066

تاریخ نمایه سازی: 29 خرداد 1400

Abstract:

In recent years, plenty of image datasets have been created and shared from different areas like robotic, medical, and social media. This great plenty of datasets has some challenges. Content based image retrieval is a method to search similar contents for real-time retrieval. Supervised classification methods are accurate, and search-based methods are interpretable for medical experts. In this article, we implement the two methods to use the benefits them. First, the proposed method is trained on an ImageNet dataset with the same image sizes. After that, the network is trained on the textures dataset that its nature is close to the two cancer datasets. Finally, the proposed method is validated based on three criteria using the k-NN classifier. We compare our results with related work, and the results show that the proposed method has better performance than the other method.

Keywords:

Content Based Image Retrieval (CBIR) , Deep Learning , Medical Image Search , Medical Image Classification

Authors

Mohammadreza Parvizimosaed

Department of Computer Engineering, K. N. Toosi University of Technology, Tehran, Iran

Mohammadreza Noei

Department of Electrical and Computer Engineering, Tarbiat Modares University, Tehran, Iran