[2405.03420] Implantable Adaptive Cells: A Novel Enhancement for Pre-Trained U-Nets in Medical Image Segmentation

Computer Science > Computer Vision and Pattern Recognition arXiv:2405.03420 (cs) [Submitted on 6 May 2024 (v1), last revised 6 Mar 2025 (this version, v2)] Title:Implantable Adaptive Cells: A Novel Enhancement for Pre-Trained U-Nets in Medical Image Segmentation Authors:Emil Benedykciuk, Marcin Denkowski, Grzegorz Wójcik View a PDF of the paper titled Implantable Adaptive Cells: A Novel Enhancement for Pre-Trained U-Nets in Medical Image Segmentation, by Emil Benedykciuk and Marcin Denkowski and Grzegorz W\'ojcik View PDF HTML (experimental) Abstract:This paper introduces a novel approach to enhance the performance of pre-trained neural networks in medical image segmentation using gradient-based Neural Architecture Search (NAS) methods. We present the concept of Implantable Adaptive Cell (IAC), small modules identified through Partially-Connected DARTS based approach, designed to be injected into the skip connections of an existing and already trained U-shaped model. Unlike traditional NAS methods, our approach refines existing architectures without full retraining. Experiments on four medical datasets with MRI and CT images show consistent accuracy improvements on various U-Net configurations, with segmentation accuracy gain by approximately 5 percentage points across all validation datasets, with improvements reaching up to 11\%pt in the best-performing cases. The findings of this study not only offer a cost-effective alternative to the complete overhaul of complex model...