Visionerves: Automatic and Reproducible Hybrid AI for Peripheral Nervous System Recognition Applied to Endometriosis Cases

2025-09-18

AI Summary

Endometriosis frequently involves extrapelvic peripheral nerves, yet conventional MRI lacks the capability for noninvasive, precise nerve identification. To address this, we propose a novel automated nerve segmentation and tracking framework integrating deep learning with symbolic spatial reasoning—introducing, for the first time, fuzzy spatial relationship modeling for anatomical knowledge encoding, eliminating the need for manual ROI delineation. The method leverages multimodal MRI (high-resolution morphological imaging plus multi-gradient diffusion-weighted imaging) and jointly incorporates neuroanatomical priors with data-driven features. Validated on 10 clinical cases, it achieves a 25% improvement in Dice coefficient over conventional methods and sub-5-mm spatial localization error. This framework significantly enhances the accuracy and reproducibility of imaging-based visualization of endometriosis-related neural involvement, thereby enabling deeper mechanistic investigation and supporting personalized diagnosis and treatment planning.

Technology Category

• Machine Learning: Neuro-Symbolic Learning
• Computer Vision: Segmentation
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization

Abstract

Endometriosis often leads to chronic pelvic pain and possible nerve involvement, yet imaging the peripheral nerves remains a challenge. We introduce Visionerves, a novel hybrid AI framework for peripheral nervous system recognition from multi-gradient DWI and morphological MRI data. Unlike conventional tractography, Visionerves encodes anatomical knowledge through fuzzy spatial relationships, removing the need for selection of manual ROIs. The pipeline comprises two phases: (A) automatic segmentation of anatomical structures using a deep learning model, and (B) tractography and nerve recognition by symbolic spatial reasoning. Applied to the lumbosacral plexus in 10 women with (confirmed or suspected) endometriosis, Visionerves demonstrated substantial improvements over standard tractography, with Dice score improvements of up to 25% and spatial errors reduced to less than 5 mm. This automatic and reproducible approach enables detailed nerve analysis and paves the way for non-invasive diagnosis of endometriosis-related neuropathy, as well as other conditions with nerve involvement.

Problem

• Automating peripheral nervous system recognition from MRI data for endometriosis cases
• Eliminating manual ROI selection through fuzzy spatial relationship encoding
• Improving nerve tractography accuracy over conventional methods for neuropathy diagnosis

Innovation

• Hybrid AI framework combining deep learning segmentation
• Symbolic spatial reasoning for nerve recognition
• Fuzzy spatial relationships encoding anatomical knowledge