TY - GEN
T1 - PCA-Enhanced Probabilistic U-Net for Effective Ambiguous Medical Image Segmentation
AU - Li, Xiangyu
AU - Wang, Chenglin
AU - Shen, Qiantong
AU - Li, Fanding
AU - Wang, Wei
AU - Wang, Kuanquan
AU - Shen, Yi
AU - Zhao, Baochun
AU - Luo, Gongning
N1 - Publisher Copyright:
© 2026 IEEE.
PY - 2026
Y1 - 2026
N2 - Ambiguous Medical Image Segmentation (AMIS) is significant to address the challenges of inherent uncertainties from image ambiguities, noise, and subjective annotations. Existing conditional variational autoencoder (cVAE)-based methods effectively capture uncertainty but face limitations including redundancy in high-dimensional latent spaces and limited expressiveness of single posterior networks. To overcome these issues, we introduce a novel PCA-Enhanced Probabilistic U-Net (PEP U-Net). Our method effectively incorporates Principal Component Analysis (PCA) for dimensionality reduction in the posterior network to mitigate redundancy and improve computational efficiency. Additionally, we further employ an inverse PCA operation to reconstruct critical information, enhancing the latent space's representational capacity. Compared to conventional generative models, our method preserves the ability to generate diverse segmentation hypotheses while achieving a superior balance between segmentation accuracy and predictive variability, thereby advancing the performance of generative modeling in medical image segmentation.
AB - Ambiguous Medical Image Segmentation (AMIS) is significant to address the challenges of inherent uncertainties from image ambiguities, noise, and subjective annotations. Existing conditional variational autoencoder (cVAE)-based methods effectively capture uncertainty but face limitations including redundancy in high-dimensional latent spaces and limited expressiveness of single posterior networks. To overcome these issues, we introduce a novel PCA-Enhanced Probabilistic U-Net (PEP U-Net). Our method effectively incorporates Principal Component Analysis (PCA) for dimensionality reduction in the posterior network to mitigate redundancy and improve computational efficiency. Additionally, we further employ an inverse PCA operation to reconstruct critical information, enhancing the latent space's representational capacity. Compared to conventional generative models, our method preserves the ability to generate diverse segmentation hypotheses while achieving a superior balance between segmentation accuracy and predictive variability, thereby advancing the performance of generative modeling in medical image segmentation.
KW - Ambiguous medical image segmentation
KW - principal component analysis
KW - uncertainty estimation
UR - https://www.scopus.com/pages/publications/105041600900
U2 - 10.1109/ISBI61048.2026.11515603
DO - 10.1109/ISBI61048.2026.11515603
M3 - 会议稿件
AN - SCOPUS:105041600900
T3 - Proceedings - International Symposium on Biomedical Imaging
BT - ISBI 2026 - 23rd IEEE International Symposium on Biomedical Imaging
PB - IEEE Computer Society
T2 - 23rd IEEE International Symposium on Biomedical Imaging, ISBI 2026
Y2 - 8 April 2026 through 11 April 2026
ER -