Twist-Net: A multi-modality transfer learning network with the hybrid bilateral encoder for hypopharyngeal cancer segmentation. (March 2023)

• Record Type: Journal Article
• Authors: Zhang, Shuo; Miao, Yang; Chen, Jun; Zhang, Xiwei; Han, Lei; Ran, Dongsheng; Huang, Zehao; Pei, Ning; Liu, Haibin; An, Changming
• Is Part Of: Computers in biology and medicine. Volume 154(2023)
• Publication Date: 2023-03
• Subjects: Hypopharyngeal cancer -- Bilateral segmentation network -- Transfer learning -- Multiple modalities; Medicine -- Data processing -- Periodicals; Biology -- Data processing -- Periodicals; 610.285
• DOI: 10.1016/j.compbiomed.2023.106555
• Languages: English
• ISSNs: 0010-4825

Abstract

Abstract: Hypopharyngeal cancer (HPC) is a rare disease. Therefore, it is a challenge to automatically segment HPC tumors and metastatic lymph nodes (HPC risk areas) from medical images with the small-scale dataset. Combining low-level details and high-level semantics from feature maps in different scales can improve the accuracy of segmentation. Herein, we propose a Multi-Modality Transfer Learning Network with Hybrid Bilateral Encoder (Twist-Net) for Hypopharyngeal Cancer Segmentation. Specifically, we propose a Bilateral Transition (BT) block and a Bilateral Gather (BG) block to twist (fuse) high-level semantic feature maps and low-level detailed feature maps. We design a block with multi-receptive field extraction capabilities, M Block, to capture multi-scale information. To avoid overfitting caused by the small scale of the dataset, we propose a transfer learning method that can transfer priors experience from large computer vision datasets to multi-modality medical imaging datasets. Compared with other methods, our method outperforms other methods on HPC dataset, achieving the highest Dice of 82.98%. Our method is also superior to other methods on two public medical segmentation datasets, i.e., the CHASE_DB1 dataset and BraTS2018 dataset. On these two datasets, the Dice of our method is 79.83% and 84.87%, respectively. The code is available at: https://github.com/zhongqiu1245/TwistNet . Highlights: A hybrid network with multi-modality inputs. Fusing high-level semantic and low-level detailed feature maps. Deformable convolution is used to flexibly adjust the receptive field. Transferring priors experience from large computer vision datasets to multi-modality medical image datasets.