Published December 6, 2022 | Version v1
Conference paper Open

Accurate Real-time Polyp Detection in Videos from Concatenation of Latent Features Extracted from Consecutive Frames

  • 1. Intervention Centre, Oslo University Hospital, Oslo, Norway
  • 2. Department of Computer Engineering, Mokpo National University, Mokpo, South Korea


An efficient deep learning model that can be implemented in real-time for polyp detection is crucial to reducing polyp miss-rate during screening procedures. Convolutional neural networks (CNNs) are vulnerable to small changes in the input image. A CNN-based model may miss the same polyp appearing in a series of consecutive frames and produce unsubtle detection output due to changes in camera pose, lighting condition, light reflection, etc. In this study, we attempt to tackle this problem by integrating temporal information among neighboring frames. We propose an efficient feature concatenation method for a CNN-based encoder-decoder model without adding complexity to the model. The proposed method incorporates extracted feature maps of previous frames to detect polyps in the current frame. The experimental results demonstrate that the proposed method of feature concatenation improves the overall performance of automatic polyp detection in videos. The following results are obtained on a public video dataset: sensitivity 90.94%, precision 90.53%, and specificity 92.46%. 


Accurate Real-time Polyp Detection in Videosfrom Concatenation of Latent Features Extractedfrom Consecutive Frames.pdf

Additional details


5G-HEART – 5G HEalth AquacultuRe and Transport validation trials 857034
European Commission