Saved in:
Bibliographic Details
Main Authors: Yang, Yuchen, Zhong, Shuangyang, Yu, Haijun, Suo, Langcuomu, Han, Hongbin, Putz, Florian, Huang, Yixing
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.00397
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910091618287616
author Yang, Yuchen
Zhong, Shuangyang
Yu, Haijun
Suo, Langcuomu
Han, Hongbin
Putz, Florian
Huang, Yixing
author_facet Yang, Yuchen
Zhong, Shuangyang
Yu, Haijun
Suo, Langcuomu
Han, Hongbin
Putz, Florian
Huang, Yixing
contents Background: Deep learning has demonstrated significant potential for automated brain metastases (BM) segmentation; however, models trained at a singular institution often exhibit suboptimal performance at various sites due to disparities in scanner hardware, imaging protocols, and patient demographics. The goal of this work is to create a domain adaptation framework that will allow for BM segmentation to be used across multiple institutions. Methods: We propose a VAE-MMD preprocessing pipeline that combines variational autoencoders (VAE) with maximum mean discrepancy (MMD) loss, incorporating skip connections and self-attention mechanisms alongside nnU-Net segmentation. The method was tested on 740 patients from four public databases: Stanford, UCSF, UCLM, and PKG, evaluated by domain classifier's accuracy, sensitivity, precision, F1/F2 scores, surface Dice (sDice), and 95th percentile Hausdorff distance (HD95). Results: VAE-MMD reduced domain classifier accuracy from 0.91 to 0.50, indicating successful feature alignment across institutions. Reconstructed volumes attained a PSNR greater than 36 dB, maintaining anatomical accuracy. The combined method raised the mean F1 by 11.1% (0.700 to 0.778), the mean sDice by 7.93% (0.7121 to 0.7686), and reduced the mean HD95 by 65.5% (11.33 to 3.91 mm) across all four centers compared to the baseline nnU-Net. Conclusions: VAE-MMD effectively diminishes cross-institutional data heterogeneity and enhances BM segmentation generalization across volumetric, detection, and boundary-level metrics without necessitating target-domain labels, thereby overcoming a significant obstacle to the clinical implementation of AI-assisted segmentation.
format Preprint
id arxiv_https___arxiv_org_abs_2604_00397
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Improving Generalization of Deep Learning for Brain Metastases Segmentation Across Institutions
Yang, Yuchen
Zhong, Shuangyang
Yu, Haijun
Suo, Langcuomu
Han, Hongbin
Putz, Florian
Huang, Yixing
Computer Vision and Pattern Recognition
Artificial Intelligence
Background: Deep learning has demonstrated significant potential for automated brain metastases (BM) segmentation; however, models trained at a singular institution often exhibit suboptimal performance at various sites due to disparities in scanner hardware, imaging protocols, and patient demographics. The goal of this work is to create a domain adaptation framework that will allow for BM segmentation to be used across multiple institutions. Methods: We propose a VAE-MMD preprocessing pipeline that combines variational autoencoders (VAE) with maximum mean discrepancy (MMD) loss, incorporating skip connections and self-attention mechanisms alongside nnU-Net segmentation. The method was tested on 740 patients from four public databases: Stanford, UCSF, UCLM, and PKG, evaluated by domain classifier's accuracy, sensitivity, precision, F1/F2 scores, surface Dice (sDice), and 95th percentile Hausdorff distance (HD95). Results: VAE-MMD reduced domain classifier accuracy from 0.91 to 0.50, indicating successful feature alignment across institutions. Reconstructed volumes attained a PSNR greater than 36 dB, maintaining anatomical accuracy. The combined method raised the mean F1 by 11.1% (0.700 to 0.778), the mean sDice by 7.93% (0.7121 to 0.7686), and reduced the mean HD95 by 65.5% (11.33 to 3.91 mm) across all four centers compared to the baseline nnU-Net. Conclusions: VAE-MMD effectively diminishes cross-institutional data heterogeneity and enhances BM segmentation generalization across volumetric, detection, and boundary-level metrics without necessitating target-domain labels, thereby overcoming a significant obstacle to the clinical implementation of AI-assisted segmentation.
title Improving Generalization of Deep Learning for Brain Metastases Segmentation Across Institutions
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2604.00397