analiza aiqbench
MedPlex advances medical image segmentation by integrating textual clinical knowledge into the visual encoder through bidirectional fusion, moving beyond late-stage conditioning to create a jointly learned vision-language representation. This approach achieves state-of-the-art results on CT and MR benchmarks for organ and tumor segmentation while utilizing real free-text supervision. The method demonstrates that structured language guidance throughout the encoding hierarchy significantly improves alignment between anatomical concepts and visual evidence.
MedPlex: Deep Vision-Language Co-Adaptation for Clinically Grounded Medical Segmentation
arXiv:2608.13690v1 Announce Type: cross Abstract: Medical image segmentation is still largely treated as a vision-only problem, although clinical interpretation often relies on textual knowledge of anatomy, location, appearance, and surrounding context. Existing text-guided segmentation methods within the Vision-Language Model (VLM) paradigm often use language only as a late conditioning signal, limiting its influence on visual representation learning. We introduce MedPlex (Medical Plexus of Vision and Language), an end-to-end VLM framework that makes text guidance a continuous, clinically grounded component of segmentation learning. Through Bi-Fusion (Bidirectional Fusion), visual and textual representations evolve jointly across the encoding hierarchy. MedPlex further introduces class-level and region-level concept alignment to organize the shared representation at complementary granularities. Class-level alignment anchors each anatomical target to an aggregated clinical concept profile, while region-level alignment preserves individual concepts, such as shape, location, appearance, and texture, through class-specific visual evidence. In this way, language provides structured supervision throughout the encoder rather than serving only as a late-stage cue. MedPlex achieves state-of-the-art performance across CT and MR benchmarks for multi-organ, cardiac substructure, and tumor segmentation, including settings with real free-text clinical supervision. Code: https://github.com/rafiibnsultan/MedPlex.
Abstract:Medical image segmentation is still largely treated as a vision-only problem, although clinical interpretation often relies on textual knowledge of anatomy, location, appearance, and surrounding context. Existing text-guided segmentation methods within the Vision-Language Model (VLM) paradigm often use language only as a late conditioning signal, limiting its influence on visual representation learning. We introduce MedPlex (Medical Plexus of Vision and Language), an end-to-end VLM framework that makes text guidance a continuous, clinically grounded component of segmentation learning. Through Bi-Fusion (Bidirectional Fusion), visual and textual representations evolve jointly across the encoding hierarchy. MedPlex further introduces class-level and region-level concept alignment to organize the shared representation at complementary granularities. Class-level alignment anchors each anatomical target to an aggregated clinical concept profile, while region-level alignment preserves individual concepts, such as shape, location, appearance, and texture, through class-specific visual evidence. In this way, language provides structured supervision throughout the encoder rather than serving only as a late-stage cue. MedPlex achieves state-of-the-art performance across CT and MR benchmarks for multi-organ, cardiac substructure, and tumor segmentation, including settings with real free-text clinical supervision. Code: this https URL.
Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
arXiv:2608.13690 [cs.CV]
(or arXiv:2608.13690v1 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2608.13690 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 · 281 cuvinte
Subiecte conexe
Reducing medical claims review time with AI on AWS: The EXL Medical IDP solution
AWS · 21 sept. 2026
Biomedical Imaging's Real Bottleneck Is the Data, Not the Model
Databricks · 8 oct. 2026
Deep Expert Injection for Anchoring Retinal VLMs with Domain-Specific Knowledge
arXiv · 31 iul. 2026
SGMCE: Segment-Grounded Morphological Concept Explanation for Malaria Parasite Species Identification in Thick Blood Smears
arXiv · 21 iul. 2026