An Explainable Neural Radiomic Sequence Model with Spatiotemporal Continuity for Quantifying 4DCT-based Pulmonary Ventilation

2025-03-31

AI Summary

To address radiation exposure, high cost, and prolonged acquisition time associated with nuclear medicine techniques (e.g., DTPA-SPECT/Ga-68 PET) for pulmonary ventilation assessment in lung cancer patients, this study proposes a non-invasive, 4DCT-based neuroradiomics temporal model. We innovatively design a temporally salient LSTM architecture that integrates voxel-wise 56-dimensional radiomic features with expiratory-phase dynamics, generating interpretable spatiotemporal saliency maps. These maps reveal a dual-feature pattern of ventilation impairment: elevated expiratory-phase intensity coupled with reduced textural homogeneity. Evaluated on 45 patients, the model achieves a Dice coefficient of 0.78 for ventilation defect segmentation against PET/SPECT ground truth. Furthermore, three physiologically meaningful temporal biomarkers are identified and validated. This work establishes a quantitative, interpretable, and low-burden paradigm for personalized therapeutic evaluation.

Technology Category

• Data Mining & Knowledge Management: Mining of Spatial, Temporal or Spatio-Temporal Data
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Accurate evaluation of regional lung ventilation is essential for the management and treatment of lung cancer patients, supporting assessments of pulmonary function, optimization of therapeutic strategies, and monitoring of treatment response. Currently, ventilation scintigraphy using nuclear medicine techniques is widely employed in clinical practice; however, it is often time-consuming, costly, and entails additional radiation exposure. In this study, we propose an explainable neural radiomic sequence model to identify regions of compromised pulmonary ventilation based on four-dimensional computed tomography (4DCT). A cohort of 45 lung cancer patients from the VAMPIRE dataset was analyzed. For each patient, lung volumes were segmented from 4DCT, and voxel-wise radiomic features (56-dimensional) were extracted across the respiratory cycle to capture local intensity and texture dynamics, forming temporal radiomic sequences. Ground truth ventilation defects were delineated voxel-wise using Galligas-PET and DTPA-SPECT. To identify compromised regions, we developed a temporal saliency-enhanced explainable long short-term memory (LSTM) network trained on the radiomic sequences. Temporal saliency maps were generated to highlight key features contributing to the model's predictions. The proposed model demonstrated robust performance, achieving average (range) Dice similarity coefficients of 0.78 (0.74-0.79) for 25 PET cases and 0.78 (0.74-0.82) for 20 SPECT cases. The temporal saliency map explained three key radiomic sequences in ventilation quantification: during lung exhalation, compromised pulmonary function region typically exhibits (1) an increasing trend of intensity and (2) a decreasing trend of homogeneity, in contrast to healthy lung tissue.

Problem

• Quantify pulmonary ventilation using 4DCT and neural radiomics
• Replace costly nuclear medicine techniques for lung ventilation assessment
• Identify compromised lung regions via explainable LSTM and saliency maps

Innovation

• Explainable neural radiomic sequence model
• Temporal saliency-enhanced LSTM network
• 4DCT-based pulmonary ventilation quantification