# Prediction of non-small cell lung cancer subtypes is possible through restricted spectrum imaging

## TL;DR

This study shows that restricted spectrum imaging can accurately predict subtypes of non-small cell lung cancer using specific imaging parameters and a diagnostic model.

## Contribution

The novel contribution is the development of a robust diagnostic model using restricted spectrum imaging parameters to distinguish NSCLC subtypes with high accuracy.

## Key findings

- The SCC group had significantly higher SUVmax, f2, and f3 values and lower ADC and f1 values compared to the AC group.
- A combined diagnostic model using predictors like smoking status, f1, SUVmax, and ADC achieved high diagnostic accuracy (AUC = 0.909).
- Bootstrap resampling confirmed the model's robustness with an AUC of 0.895.

## Abstract

To evaluate the utility of restricted spectrum imaging (RSI) for predicting subtypes of non-small cell lung cancer (NSCLC).

A total of 97 patients with NSCLC (30 with squamous cell carcinoma (SCC) and 67 with adenocarcinoma (AC)) were included. The parameters f1, f2, f3, apparent diffusion coefficient (ADC), and maximum standardized uptake value (SUVmax) were measured and compared between the two subtypes. Logistic regression analysis was used to identify independent predictors, and a combined diagnostic model was developed. The performance of the model was assessed using receiver operating characteristic (ROC) curve analysis, calibration curves, and decision curve analysis (DCA).

Compared with the AC group, the SCC group exhibited significantly higher SUVmax, f2, and f3 values, and lower ADC and f1 values (all P < 0.05). Smoking status, f1, SUVmax, and ADC were independent predictors of NSCLC subtypes. The combined model demonstrated superior diagnostic accuracy (AUC = 0.909; sensitivity = 73.33%; specificity = 89.55%) compared with individual predictors (AUC = 0.693, 0.819, 0.767, and 0.742 for smoking status, f1, SUVmax, and ADC, respectively; all P < 0.01). Bootstrap resampling (1000 samples) validated the robustness of the model (AUC = 0.895). Calibration curves and DCA confirmed the model’s stability and clinical utility.

RSI can effectively differentiate NSCLC subtypes.