Adaptive Affinity-Based Generalization For MRI Imaging Segmentation Across Resource-Limited Settings
This work addresses the challenge of data heterogeneity and domain shift in MRI segmentation for resource-limited medical settings, offering an incremental improvement through a novel distillation framework.
The paper tackles the problem of medical imaging segmentation across diverse data sources by proposing a lightweight model that uses adaptive affinity-based and kernel-based distillation to improve performance while reducing computational demands. The results show significant enhancement in segmentation on multi-source prostate MRI data, with reduced inference time and storage usage.
The joint utilization of diverse data sources for medical imaging segmentation has emerged as a crucial area of research, aiming to address challenges such as data heterogeneity, domain shift, and data quality discrepancies. Integrating information from multiple data domains has shown promise in improving model generalizability and adaptability. However, this approach often demands substantial computational resources, hindering its practicality. In response, knowledge distillation (KD) has garnered attention as a solution. KD involves training light-weight models to emulate the behavior of more resource-intensive models, thereby mitigating the computational burden while maintaining performance. This paper addresses the pressing need to develop a lightweight and generalizable model for medical imaging segmentation that can effectively handle data integration challenges. Our proposed approach introduces a novel relation-based knowledge framework by seamlessly combining adaptive affinity-based and kernel-based distillation through a gram matrix that can capture the style representation across features. This methodology empowers the student model to accurately replicate the feature representations of the teacher model, facilitating robust performance even in the face of domain shift and data heterogeneity. To validate our innovative approach, we conducted experiments on publicly available multi-source prostate MRI data. The results demonstrate a significant enhancement in segmentation performance using lightweight networks. Notably, our method achieves this improvement while reducing both inference time and storage usage, rendering it a practical and efficient solution for real-time medical imaging segmentation.