Search papers, labs, and topics across Lattice.
This paper introduces a VAE-MMD preprocessing pipeline to mitigate the impact of cross-institutional data heterogeneity on brain metastases (BM) segmentation. The pipeline combines variational autoencoders (VAE) with maximum mean discrepancy (MMD) loss, skip connections, and self-attention to align features across different institutions before nnU-Net segmentation. Results on four public datasets show that VAE-MMD significantly improves F1 score, sDice, and reduces HD95 compared to baseline nnU-Net, demonstrating enhanced generalization without target-domain labels.
Domain adaptation for medical imaging doesn't need target-domain labels: a VAE-MMD pipeline boosts brain metastases segmentation accuracy by 11% across diverse institutions.
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.
