analiza aiqbench
This empirical study benchmarks general-purpose vision models against specialized architectures for 2D medical image segmentation, finding that modern GP-VMs achieve performance comparable to domain-specific designs without requiring explicit architectural priors. The research further utilizes linear mixed-effects models and Grad-CAM visualizations to demonstrate that these general models effectively identify clinically relevant structures, suggesting they are a viable alternative for computer-assisted diagnosis. These findings provide critical guidance for model selection in medical imaging workflows where data scarcity or computational constraints may favor versatile foundation models over highly specialized solutions.
GP-VM$\times$SMA: Benchmarking General-Purpose Vision Models and Specialized Architectures for 2D Medical Image Segmentation
arXiv:2603.13044v2 Announce Type: replace-cross Abstract: Medical image segmentation (MIS) is a fundamental component of computer-assisted diagnosis and clinical decision support. Over the past decade, numerous architectures specifically tailored to medical imaging have emerged to address domain-specific challenges such as low contrast, small anatomical structures, and limited annotated data. In parallel, rapid progress in computer vision has produced highly capable general-purpose vision models (GP-VMs) originally designed for natural images. Despite their strong performance on standard vision benchmarks, their effectiveness for MIS remains insufficiently understood. In this controlled empirical study, we examine whether specialized medical segmentation architectures (SMAs) provide systematic advantages over modern GP-VMs for 2D MIS. We compare eleven SMAs and GP-VMs using a unified training and evaluation protocol across three heterogeneous datasets, each covering different 2D imaging modalities, class structures, and data characteristics. Beyond segmentation performance, we employ linear mixed-effects models (LMMs) for statistical assessment and qualitative Grad-CAM visualizations to investigate explainability (XAI)-related model behavior. Our results imply that, for the analyzed settings, GP-VMs achieve performance comparable to that of specialized MIS models. Moreover, XAI analyses indicate that GP-VMs are capable of identifying clinically relevant structures despite the absence of explicit domain-specific architectural priors. These findings suggest that GP-VMs can represent a viable alternative to domain-specific methods for 2D MIS, highlighting the importance of informed model selection. All code and resources are available at GitHub.
Abstract:Medical image segmentation (MIS) is a fundamental component of computer-assisted diagnosis and clinical decision support. Over the past decade, numerous architectures specifically tailored to medical imaging have emerged to address domain-specific challenges such as low contrast, small anatomical structures, and limited annotated data. In parallel, rapid progress in computer vision has produced highly capable general-purpose vision models (GP-VMs) originally designed for natural images. Despite their strong performance on standard vision benchmarks, their effectiveness for MIS remains insufficiently understood. In this controlled empirical study, we examine whether specialized medical segmentation architectures (SMAs) provide systematic advantages over modern GP-VMs for 2D MIS. We compare eleven SMAs and GP-VMs using a unified training and evaluation protocol across three heterogeneous datasets, each covering different 2D imaging modalities, class structures, and data characteristics. Beyond segmentation performance, we employ linear mixed-effects models (LMMs) for statistical assessment and qualitative Grad-CAM visualizations to investigate explainability (XAI)-related model behavior. Our results imply that, for the analyzed settings, GP-VMs achieve performance comparable to that of specialized MIS models. Moreover, XAI analyses indicate that GP-VMs are capable of identifying clinically relevant structures despite the absence of explicit domain-specific architectural priors. These findings suggest that GP-VMs can represent a viable alternative to domain-specific methods for 2D MIS, highlighting the importance of informed model selection. All code and resources are available at GitHub.
Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
arXiv:2603.13044 [cs.CV]
(or arXiv:2603.13044v2 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2603.13044 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 318 cuvinte
Subiecte conexe
Academia is for Ambition — Alex Zhang, MIT
Latent Space · 2 oct. 2026
Reducing medical claims review time with AI on AWS: The EXL Medical IDP solution
AWS · 21 sept. 2026
Building a Foundation Stack for General-Purpose Robots
IEEE Spectrum · 13 iul. 2026
Presentation: From ms to µs: OSS Valkey Architecture Patterns for Modern AI
InfoQ · 6 aug. 2026