Anatomy-Informed Deep Learning and Radiomics for Automated Neurofibroma Segmentation in Whole-Body MRI

2025-02-21

AI Summary

Automatic segmentation of neurofibromas (NFs) in whole-body MRI of neurofibromatosis type 1 (NF1) patients remains highly challenging due to extreme inter-tumoral heterogeneity in size, morphology, and anatomical location. Method: We propose an anatomy-guided, three-stage fully automated framework: (1) anatomical region masking and high-risk zone prior generation using MRSegmentator, integrated into a 3D anisotropic U-Net; (2) tumor confidence map estimation; and (3) false-positive suppression via radiomic features extracted using PyRadiomics. Contribution/Results: This work introduces the first synergistic paradigm integrating anatomical modeling, multi-scale segmentation, and radiomics-based post-classification—significantly enhancing robustness under low-tumor-burden and multi-center acquisition protocols. On high-burden cases, it achieves +68% scan-level Dice, +21% lesion-level Dice, and a twofold increase in F1-score. The code and a 3D Slicer plugin are publicly available and clinically deployed.

Technology Category

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

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Web Mining and Content Analysis: Normalization, clustering, classification, and summarization of Web text
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Neurofibromatosis Type 1 is a genetic disorder characterized by the development of neurofibromas (NFs), which exhibit significant variability in size, morphology, and anatomical location. Accurate and automated segmentation of these tumors in whole-body magnetic resonance imaging (WB-MRI) is crucial to assess tumor burden and monitor disease progression. In this study, we present and analyze a fully automated pipeline for NF segmentation in fat-suppressed T2-weighted WB-MRI, consisting of three stages: anatomy segmentation, NF segmentation, and tumor candidate classification. In the first stage, we use the MRSegmentator model to generate an anatomy segmentation mask, extended with a high-risk zone for NFs. This mask is concatenated with the input image as anatomical context information for NF segmentation. The second stage employs an ensemble of 3D anisotropic anatomy-informed U-Nets to produce an NF segmentation confidence mask. In the final stage, tumor candidates are extracted from the confidence mask and classified based on radiomic features, distinguishing tumors from non-tumor regions and reducing false positives. We evaluate the proposed pipeline on three test sets representing different conditions: in-domain data (test set 1), varying imaging protocols and field strength (test set 2), and low tumor burden cases (test set 3). Experimental results show a 68% improvement in per-scan Dice Similarity Coefficient (DSC), a 21% increase in per-tumor DSC, and a two-fold improvement in F1 score for tumor detection in high tumor burden cases by integrating anatomy information. The method is integrated into the 3D Slicer platform for practical clinical use, with the code publicly accessible.

Problem

• Automated neurofibroma segmentation in whole-body MRI
• Assessing tumor burden in Neurofibromatosis Type 1
• Improving accuracy with anatomy-informed deep learning

Innovation

• Anatomy-informed U-Nets ensemble
• Radiomics for tumor classification
• MRSegmentator for anatomy segmentation