AutoLugano: A Deep Learning Framework for Fully Automated Lymphoma Segmentation and Lugano Staging on FDG-PET/CT

2025-12-08

AI Summary

This study addresses the clinical bottleneck of manual FDG-PET/CT interpretation for lymphoma staging. We propose the first fully automated, end-to-end deep learning framework that jointly performs lesion segmentation, anatomical localization, and Lugano staging. Methodologically, we employ a 3D nnU-Net for multimodal lesion segmentation, integrate TotalSegmentator with atlas-guided anatomical mapping, and implement a deterministic rule engine grounded in clinical guidelines to derive staging outcomes. Our key contribution lies in the first systematic incorporation of anatomical priors across the entire pipeline, yielding an interpretable, deployable, and standardized Lugano staging system. On an external validation cohort, the framework achieves an 80.80% F1-score for involved-region detection, 85.07% overall staging accuracy, and 82.61% sensitivity and 90.48% specificity for distinguishing limited-stage from advanced-stage disease—significantly enhancing diagnostic efficiency and inter-rater consistency in initial assessment.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Calibration & Uncertainty Quantification
• Natural Language Processing: Interpretability, Analysis, and Evaluation of NLP Models

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Purpose: To develop a fully automated deep learning system, AutoLugano, for end-to-end lymphoma classification by performing lesion segmentation, anatomical localization, and automated Lugano staging from baseline FDG-PET/CT scans. Methods: The AutoLugano system processes baseline FDG-PET/CT scans through three sequential modules:(1) Anatomy-Informed Lesion Segmentation, a 3D nnU-Net model, trained on multi-channel inputs, performs automated lesion detection (2) Atlas-based Anatomical Localization, which leverages the TotalSegmentator toolkit to map segmented lesions to 21 predefined lymph node regions using deterministic anatomical rules; and (3) Automated Lugano Staging, where the spatial distribution of involved regions is translated into Lugano stages and therapeutic groups (Limited vs. Advanced Stage).The system was trained on the public autoPET dataset (n=1,007) and externally validated on an independent cohort of 67 patients. Performance was assessed using accuracy, sensitivity, specificity, F1-scorefor regional involvement detection and staging agreement. Results: On the external validation set, the proposed model demonstrated robust performance, achieving an overall accuracy of 88.31%, sensitivity of 74.47%, Specificity of 94.21% and an F1-score of 80.80% for regional involvement detection,outperforming baseline models. Most notably, for the critical clinical task of therapeutic stratification (Limited vs. Advanced Stage), the system achieved a high accuracy of 85.07%, with a specificity of 90.48% and a sensitivity of 82.61%.Conclusion: AutoLugano represents the first fully automated, end-to-end pipeline that translates a single baseline FDG-PET/CT scan into a complete Lugano stage. This study demonstrates its strong potential to assist in initial staging, treatment stratification, and supporting clinical decision-making.

Problem

• Automates lymphoma lesion segmentation from FDG-PET/CT scans.
• Maps detected lesions to anatomical regions for localization.
• Translates lesion distribution into Lugano stages for treatment stratification.

Innovation

• 3D nnU-Net model segments lesions from multi-channel PET/CT scans
• Atlas-based anatomical localization maps lesions to lymph node regions
• Automated pipeline translates lesion distribution into Lugano staging