Predicting Patient Survival with Airway Biomarkers using nn-Unet/Radiomics

2025-06-13

AI Summary

This study investigates the prognostic value of airway-related imaging biomarkers for survival prediction in idiopathic pulmonary fibrosis (IPF). To address this, we propose a three-stage analytical framework: (1) high-precision airway segmentation using nn-UNet; (2) extraction of airway-specific radiomic features—including morphological, textural, and intensity-based statistics—from the trachea and its minimal bounding box; and (3) integration of multimodal features into a support vector machine (SVM)-based survival risk classification model. To our knowledge, this is the first systematic investigation of tracheal morphology and texture as discriminative imaging biomarkers for IPF prognosis, establishing a novel airway-centric radiomic modeling paradigm. In the AIIB 2023 challenge, our method achieved a Dice score of 0.8601 for airway segmentation and an AUC of 0.7346 for survival risk classification—both significantly outperforming baseline approaches.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Large Multimodal Models (LMMs)
• Data Mining & Knowledge Management: Representing, Reasoning, and Using Provenance, Trust

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

The primary objective of the AIIB 2023 competition is to evaluate the predictive significance of airway-related imaging biomarkers in determining the survival outcomes of patients with lung fibrosis.This study introduces a comprehensive three-stage approach. Initially, a segmentation network, namely nn-Unet, is employed to delineate the airway's structural boundaries. Subsequently, key features are extracted from the radiomic images centered around the trachea and an enclosing bounding box around the airway. This step is motivated by the potential presence of critical survival-related insights within the tracheal region as well as pertinent information encoded in the structure and dimensions of the airway. Lastly, radiomic features obtained from the segmented areas are integrated into an SVM classifier. We could obtain an overall-score of 0.8601 for the segmentation in Task 1 while 0.7346 for the classification in Task 2.

Problem

• Predicting lung fibrosis patient survival using airway biomarkers
• Segmenting airway structures with nn-Unet for radiomic analysis
• Classifying survival outcomes via SVM with radiomic features

Innovation

• Uses nn-Unet for airway segmentation
• Extracts radiomic features from trachea
• Applies SVM classifier for survival prediction