The Deep Hybrid Neural Network and an Application on Polyp Detection

Yi Ta Wu, Frank Y. Shih, Cheng Long Wang, Kuang Ting Hsiao, You Cheng Liu, Fu Chieh Chang, En Da Yu

Research output: Contribution to journalArticlepeer-review


Mathematical morphology and convolution operators are two different methods to extract the characteristics and structures of images. Over the past decades, Deep Convolutional Neural Networks (DCNN) have been proven to be more powerful than traditional image-processing approaches. In this paper, we propose a novel structure called Deep Hybrid Neural Network (DHNN) by taking advantage of the convolution and morphological neural layers. Its practical application to polyp detection in medical images is illustrated. For experimental completeness, we adopt nine polyp image datasets, including publicly available data and our own collected data. For performance comparisons, we select three backbone models. Experimental results show that our DHNN achieves the best performance in comparisons in terms of computational complexity and accurate performance.

Original languageEnglish (US)
Article number2452009
JournalInternational Journal of Pattern Recognition and Artificial Intelligence
Issue number4
StatePublished - Mar 30 2024

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence


  • Deep convolutional neural network
  • deep hybrid neural network
  • deep morphological neural network
  • polyp detection


Dive into the research topics of 'The Deep Hybrid Neural Network and an Application on Polyp Detection'. Together they form a unique fingerprint.

Cite this