Automated Multimodal Image Registration for Prostate Cancer Using Squeeze-and-Excitation ResNet with Thin Plate Spline Transformation: A Deep Learning Approach

Hua Cai; Yongxin Li; Qiang Zhao; Yun Lu

doi:10.12659/MSM.949996

19 October 2025 : Laboratory Research

Automated Multimodal Image Registration for Prostate Cancer Using Squeeze-and-Excitation ResNet with Thin Plate Spline Transformation: A Deep Learning Approach

Hua Cai^{ABCDEFG 1}, Yongxin Li^{C 2}, Qiang Zhao^{F 3*}, Yun Lu^{A 1,4}

DOI: 10.12659/MSM.949996

Med Sci Monit 2025; 31:e949996

Authors information Article notes Copyright and License information

Introduction Material and Methods Results Discussion Conclusions References

Related articles Order reprints Share article Share by email

View HTML version

Table 2 Quantitative registration results of Dice similarity coefficient and Hausdorff distance for prostate contours and cancerous regions using different registration methods.

Methods	DSC	HD (mm)
CNNGeometric	0.557 (±0.10)	6.01 (±2.08)
VoxelMorph	0.537 (±0.13)	6.54 (±2.67)
SE-ResNet-TPS	0.578 (±0.11)	4.97 (±1.42)

Back to the Article

Automated Multimodal Image Registration for Prostate Cancer Using Squeeze-and-Excitation ResNet with Thin Plate Spline Transformation: A Deep Learning Approach

Your Privacy