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

Computer Science > Computer Vision and Pattern Recognition [Submitted on 6 May 2024 (v1), last revised 6 Mar 2025 (this version, v2)] Implantable Adaptive Cells: A Novel Enhancement for Pre-Trained U-Nets in Medical Image Segmentation Emil Benedykciuk, Marcin Denkowski, Grzegorz Wójcik 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 models for performance upgrades but also indicate the potential applicability of our method to other architectures and problem domains. Subjects: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI) Cite as: arXiv:2405.03420 [cs.CV]   (or arXiv:2405.03420v2 [cs.CV] for this version)   https://doi.org/10.48550/arXiv.2405.03420 Focus to learn more Submission history From: Marcin Denkowski [view email] [v1] Mon, 6 May 2024 12:40:15 UTC (2,732 KB) [v2] Thu, 6 Mar 2025 12:52:29 UTC (1,991 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CV < prev   |   next > new | recent | 2024-05 Change to browse by: cs cs.AI References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)