Login / Signup

Modified U-Net for liver cancer segmentation from computed tomography images with a new class balancing method.

Yodit Abebe AyalewKinde Anlay FanteMohammed Aliy Mohammed
Published in: BMC biomedical engineering (2021)
This work proposed a liver and a tumor segmentation method using a UNet architecture as a baseline. Modification regarding the number of filters and network layers were done on the original UNet model to reduce the network complexity and improve segmentation performance. A new class balancing method is also introduced to minimize the class imbalance problem. Through these, the algorithm attained better segmentation results and showed good improvement. However, it faced difficulty in segmenting small and irregular tumors.
Keyphrases
  • deep learning
  • convolutional neural network
  • computed tomography
  • machine learning
  • positron emission tomography
  • network analysis
  • dual energy
  • image quality