Abstract
Vessel contour detection (VCD) in intravascular images is important for the quantitative assessment of vessels. However, it is still a challenging task due to a high degree of morphology variability. Images from a single modality lack sufficient information on the vessel morphology due to the natural limitation of the imaging capability. Therefore, the single-modality VCD methods have difficulty extracting sufficient morphological information. Cross-modality methods have the potential to overcome morphology variability by extracting more information from different modalities. However, they still face the difficulty of the domain discrepancy, i.e. feature space discrepancy and label space inconsistency. In this paper, we aims to address this domain discrepancy for VCD. To overcome label space inconsistency, our method divides the label space into private label space and shared label space. It constructs subdomains for the private label space and the shared label space, and then minimizes the task risk at the subdomain level. To overcome feature space discrepancy, it extracts domain-invariant features via domain adaptation between the subdomains. Finally, it uses the domain-invariant features as auxiliary information for each subdomain. Extensive experiments on 130 IVUS sequences (135663 images) and 124 OCT sequences (39857 images) show that our method is effective (e.g., the Dice index $\geqslant$ 0.949), and superior to the nineteen state-of-the-art VCD methods.
Funding Information
  • National Natural Science Foundation of China (62101606, 62276282, 62271511, U1908211)
  • Basic and Applied Basic Research Foundation of Guangdong Province (2022A1515011384)
  • Guangdong Natural Science Funds for Distinguished Young Scholar (2019B151502031)
  • National Youth Talent Support Program (RC2020-01)

This publication has 33 references indexed in Scilit: