Virtual Scanning for NSCLC Histology: Investigating the Discriminatory Power of Synthetic PET

TL;DR

This study explores using synthetic PET images generated from CT scans via GANs to improve histological classification of NSCLC, demonstrating significant performance gains in a multi-center dataset.

Contribution

It introduces a novel framework combining GAN-based synthetic PET with CT data within a multi-stage fusion architecture for better NSCLC subtype classification.

Findings

Synthetic PET features significantly improved classification metrics.

AUC increased from 0.489 to 0.591 with synthetic PET inclusion.

The approach offers a potential alternative when physical PET scans are unavailable.

Abstract

Accurate histological differentiation between adenocarcinoma (ADC) and squamous cell carcinoma (SCC) is critical for personalized treatment in non-small cell lung cancer (NSCLC). While [$^{18}$F]FDG PET/CT is a standard tool for the clinical evaluation of lung cancer, its utility is often limited by high costs and radiation exposure. In this paper, we investigate the feasibility of "virtual scanning" as a feature-enhancement strategy by evaluating whether synthetic PET data can provide complementary feature representations to supplement anatomical CT scans in histological subtype classification. We propose a framework that leverages a 3D Pix2Pix Generative Adversarial Network (GAN), pretrained on the FDG-PET/CT Lesions dataset, to synthesize pseudo-PET volumes from anatomical CT scans. These synthetic volumes are integrated with structural CT data within the MINT framework, a multi-stage intermediate fusion architecture. Our experiments, conducted on a multi-center dataset of 714 subjects, demonstrate that the inclusion of synthetic metabolic features significantly improves classification performance over a CT-only baseline. The multimodal approach achieved a statistically significant increase in the Area Under the Curve (AUC) from 0.489 to 0.591 and improved the Geometric Mean (GMean) from 0.305 to 0.524. These results suggest that synthetic PET scans provide discriminatory metabolic cues that enable deep learning models to exploit complementary cross-modal information, offering a potential feature-enhancement strategy for clinical scenarios where physical PET scans are unavailable.