analiza aiqbench
This paper introduces MID, a novel distribution-level metric for medical image segmentation that evaluates the joint consistency between images and masks without requiring sample-wise ground-truth pairing. By addressing limitations of traditional metrics like Dice and Hausdorff distance, it enables robust model ranking and detection of distributional shifts across diverse modalities such as CT, MRI, and MRA. The method offers a significant advancement in evaluation protocols for unsupervised or semi-supervised segmentation scenarios where annotations are scarce.
MID: Mask-Image Distributional Divergence for Evaluating Medical Image Segmentation
arXiv:2610.17354v1 Announce Type: cross Abstract: Current evaluation protocols for medical image segmentation remain largely anchored in sample-wise comparisons, e.g., Dice and Hausdorff distance, which require each prediction to be paired with a ground-truth mask. Yet two limitations arise in practice: they are inapplicable when predictions are made on unlabeled data; and even when annotations are available, they cannot assess whether a collection of predictions matches the distributional structure of the ground-truth population. We introduce MID (Mask-Image Distributional Divergence), a distribution-level evaluation metric for medical image segmentation. MID builds upon the observation that segmentation quality is a property of the joint image-mask distribution: a mask may be anatomically plausible in isolation yet incorrect for the image it accompanies. MID compares the joint distribution of images and masks between a reference set and a set of predictions, without requiring sample-wise correspondence. This captures both mask realism and image-mask consistency. We evaluate MID across 13 publicly available datasets spanning CT, MRI, and MRA. Under anatomically realistic corruptions across 56 organ groups, MID tracks mean Dice and Hausdorff distance without per-sample ground-truth pairing. MID also detects distributional shifts across modalities and anatomies, identifies image-mask misalignment through controlled shuffling experiments, and produces reliable model rankings across real segmentation models. Official implementation available at github.com/erc-caravel/pytorch-mid
Abstract:Current evaluation protocols for medical image segmentation remain largely anchored in sample-wise comparisons, e.g., Dice and Hausdorff distance, which require each prediction to be paired with a ground-truth mask. Yet two limitations arise in practice: they are inapplicable when predictions are made on unlabeled data; and even when annotations are available, they cannot assess whether a collection of predictions matches the distributional structure of the ground-truth population. We introduce MID (Mask-Image Distributional Divergence), a distribution-level evaluation metric for medical image segmentation. MID builds upon the observation that segmentation quality is a property of the joint image-mask distribution: a mask may be anatomically plausible in isolation yet incorrect for the image it accompanies. MID compares the joint distribution of images and masks between a reference set and a set of predictions, without requiring sample-wise correspondence. This captures both mask realism and image-mask consistency. We evaluate MID across 13 publicly available datasets spanning CT, MRI, and MRA. Under anatomically realistic corruptions across 56 organ groups, MID tracks mean Dice and Hausdorff distance without per-sample ground-truth pairing. MID also detects distributional shifts across modalities and anatomies, identifies image-mask misalignment through controlled shuffling experiments, and produces reliable model rankings across real segmentation models. Official implementation available at this http URL
Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
arXiv:2610.17354 [cs.CV]
(or arXiv:2610.17354v1 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2610.17354 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
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 · 306 cuvinte
Subiecte conexe
DualDiT: A Conditional Dual-Output Diffusion Transformer for Joint OCT Image and Segmentation Mask Generation
arXiv · 3 aug. 2026
WoundAmbit: Bridging State-of-the-Art Semantic Segmentation and Real-World Wound Care
arXiv · 12 oct. 2026
FedDermaSeg: Federated Learning for Dermatological Image Segmentation
arXiv · 7 oct. 2026
Synthesize Realistic 3D Medical Images at Scale to Ship Pre‑Trained Models
NVIDIA · 22 mai 2026