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

2026-05-04

AI Summary

This study addresses the challenge of accurately distinguishing between adenocarcinoma and squamous cell carcinoma subtypes in non-small cell lung cancer (NSCLC) when real PET scans are unavailable. To this end, the authors propose a cross-modal enhancement approach based on generative adversarial networks. Specifically, a pretrained 3D Pix2Pix GAN synthesizes pseudo-PET images from CT scans, which are then fused with the original CT data using the MINT multi-stage intermediate fusion architecture to enable multimodal feature integration. The work demonstrates for the first time that synthesized PET images can provide discriminative metabolic information, significantly improving classification performance without requiring actual PET scans. Evaluated on a multicenter cohort of 714 cases, the method increased the AUC from 0.489 to 0.591 and substantially improved the geometric mean from 0.305 to 0.524.

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.

Problem

• NSCLC histology
• adenocarcinoma vs squamous cell carcinoma
• synthetic PET
• virtual scanning
• histological subtype classification

Innovation

• virtual scanning
• synthetic PET
• 3D Pix2Pix GAN
• multi-modal fusion
• histological classification