Purpose Accurate classification of pulmonary pure ground-glass nodules (pGGNs) is essential for distinguishing invasive adenocarcinoma (IVA) from adenocarcinoma in situ (AIS) and minimally invasive adenocarcinoma (MIA), which significantly influences treatment decisions. This study aims to develop a high-precision integrated strategy by combining radiomics-based feature extraction, Quantum Machine Learning (QML) models, and SHapley Additive exPlanations (SHAP) analysis to improve diagnostic accuracy and interpretability in pGGN classification. Methods A total of 322 pGGNs from 275 patients were retrospectively analyzed. The CT images was randomly divided into training and testing cohorts (80:20), with radiomic features extracted from the training cohort. Three QML models-Quantum Support Vector Classifier (QSVC), Pegasos QSVC, and Quantum Neural Network (QNN)-were developed and compared with a classical Support Vector Machine (SVM). SHAP analysis was applied to interpret the contribution of radiomic features to the models’ predictions. Results All three QML models outperformed the classical SVM, with the QNN model achieving the highest improvements (<InlineEquation ID="IEq1"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="12880_2025_1813_Article_IEq1.gif" Format="GIF" Height="16" Rendition="HTML" Resolution="72" Type="Linedraw" Width="62" /> </InlineMediaObject> <EquationSource Format="TEX">\(p < 0.05\)</EquationSource> </InlineEquation>) in classification metrics, including accuracy (89.23<InlineEquation ID="IEq2"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="12880_2025_1813_Article_IEq2.gif" Format="GIF" Height="16" Rendition="HTML" Resolution="72" Type="Linedraw" Width="15" /> </InlineMediaObject> <EquationSource Format="TEX">\(\%\)</EquationSource> </InlineEquation>, 95<InlineEquation ID="IEq3"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="12880_2025_1813_Article_IEq2.gif" Format="GIF" Height="16" Rendition="HTML" Resolution="72" Type="Linedraw" Width="15" /> </InlineMediaObject> <EquationSource Format="TEX">\(\%\)</EquationSource> </InlineEquation> CI: 81.54<InlineEquation ID="IEq4"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="12880_2025_1813_Article_IEq2.gif" Format="GIF" Height="16" Rendition="HTML" Resolution="72" Type="Linedraw" Width="15" /> </InlineMediaObject> <EquationSource Format="TEX">\(\%\)</EquationSource> </InlineEquation> − 95.38<InlineEquation ID="IEq5"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="12880_2025_1813_Article_IEq2.gif" Format="GIF" Height="16" Rendition="HTML" Resolution="72" Type="Linedraw" Width="15" /> </InlineMediaObject> <EquationSource Format="TEX">\(\%\)</EquationSource> </InlineEquation>), sensitivity (96.55<InlineEquation ID="IEq6"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="12880_2025_1813_Article_IEq2.gif" Format="GIF" Height="16" Rendition="HTML" Resolution="72" Type="Linedraw" Width="15" /> </InlineMediaObject> <EquationSource Format="TEX">\(\%\)</EquationSource> </InlineEquation>, 95<InlineEquation ID="IEq7"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="12880_2025_1813_Article_IEq2.gif" Format="GIF" Height="16" Rendition="HTML" Resolution="72" Type="Linedraw" Width="15" /> </InlineMediaObject> <EquationSource Format="TEX">\(\%\)</EquationSource> </InlineEquation> CI: 89.66<InlineEquation ID="IEq8"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="12880_2025_1813_Article_IEq2.gif" Format="GIF" Height="16" Rendition="HTML" Resolution="72" Type="Linedraw" Width="15" /> </InlineMediaObject> <EquationSource Format="TEX">\(\%\)</EquationSource> </InlineEquation> − 100.00<InlineEquation ID="IEq9"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="12880_2025_1813_Article_IEq2.gif" Format="GIF" Height="16" Rendition="HTML" Resolution="72" Type="Linedraw" Width="15" /> </InlineMediaObject> <EquationSource Format="TEX">\(\%\)</EquationSource> </InlineEquation>), specificity (83.33<InlineEquation ID="IEq10"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="12880_2025_1813_Article_IEq2.gif" Format="GIF" Height="16" Rendition="HTML" Resolution="72" Type="Linedraw" Width="15" /> </InlineMediaObject> <EquationSource Format="TEX">\(\%\)</EquationSource> </InlineEquation>, 95<InlineEquation ID="IEq11"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="12880_2025_1813_Article_IEq2.gif" Format="GIF" Height="16" Rendition="HTML" Resolution="72" Type="Linedraw" Width="15" /> </InlineMediaObject> <EquationSource Format="TEX">\(\%\)</EquationSource> </InlineEquation> CI: 69.44<InlineEquation ID="IEq12"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="12880_2025_1813_Article_IEq2.gif" Format="GIF" Height="16" Rendition="HTML" Resolution="72" Type="Linedraw" Width="15" /> </InlineMediaObject> <EquationSource Format="TEX">\(\%\)</EquationSource> </InlineEquation> − 94.44<InlineEquation ID="IEq13"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="12880_2025_1813_Article_IEq2.gif" Format="GIF" Height="16" Rendition="HTML" Resolution="72" Type="Linedraw" Width="15" /> </InlineMediaObject> <EquationSource Format="TEX">\(\%\)</EquationSource> </InlineEquation>), and area under the curve (AUC) (0.937, 95<InlineEquation ID="IEq14"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="12880_2025_1813_Article_IEq2.gif" Format="GIF" Height="16" Rendition="HTML" Resolution="72" Type="Linedraw" Width="15" /> </InlineMediaObject> <EquationSource Format="TEX">\(\%\)</EquationSource> </InlineEquation> CI: 0.871 - 0.983), respectively. SHAP analysis identified Low Gray Level Run Emphasis (LGLRE), Gray Level Non-uniformity (GLN), and Size Zone Non-uniformity (SZN) as the most critical features influencing classification. Conclusion This study demonstrates that the proposed integrated strategy, combining radiomics, QML models, and SHAP analysis, significantly enhances the accuracy and interpretability of pGGN classification, particularly in small-sample datasets. It offers a promising tool for early, non-invasive lung cancer diagnosis and helps clinicians make more informed treatment decisions. Clinical trial number Not applicable.

An integrated strategy based on radiomics and quantum machine learning: diagnosis and clinical interpretation of pulmonary ground-glass nodules

期刊论文
出版模式：

开放获取
发表日期：

2025年7月11日

查看全文

Xianzhi Huang,
Fangyi Xu,
Wenchao Zhu,
Lin Yao,
Jiahuan He,
Junhao Su,
Wending Zhao,
Hongjie Hu

摘要

Purpose

Accurate classification of pulmonary pure ground-glass nodules (pGGNs) is essential for distinguishing invasive adenocarcinoma (IVA) from adenocarcinoma in situ (AIS) and minimally invasive adenocarcinoma (MIA), which significantly influences treatment decisions. This study aims to develop a high-precision integrated strategy by combining radiomics-based feature extraction, Quantum Machine Learning (QML) models, and SHapley Additive exPlanations (SHAP) analysis to improve diagnostic accuracy and interpretability in pGGN classification.

Methods

A total of 322 pGGNs from 275 patients were retrospectively analyzed. The CT images was randomly divided into training and testing cohorts (80:20), with radiomic features extracted from the training cohort. Three QML models-Quantum Support Vector Classifier (QSVC), Pegasos QSVC, and Quantum Neural Network (QNN)-were developed and compared with a classical Support Vector Machine (SVM). SHAP analysis was applied to interpret the contribution of radiomic features to the models’ predictions.

Results

All three QML models outperformed the classical SVM, with the QNN model achieving the highest improvements ( \(p < 0.05\) ) in classification metrics, including accuracy (89.23 \(\%\) , 95 \(\%\) CI: 81.54 \(\%\) − 95.38 \(\%\) ), sensitivity (96.55 \(\%\) , 95 \(\%\) CI: 89.66 \(\%\) − 100.00 \(\%\) ), specificity (83.33 \(\%\) , 95 \(\%\) CI: 69.44 \(\%\) − 94.44 \(\%\) ), and area under the curve (AUC) (0.937, 95 \(\%\) CI: 0.871 - 0.983), respectively. SHAP analysis identified Low Gray Level Run Emphasis (LGLRE), Gray Level Non-uniformity (GLN), and Size Zone Non-uniformity (SZN) as the most critical features influencing classification.

Conclusion

This study demonstrates that the proposed integrated strategy, combining radiomics, QML models, and SHAP analysis, significantly enhances the accuracy and interpretability of pGGN classification, particularly in small-sample datasets. It offers a promising tool for early, non-invasive lung cancer diagnosis and helps clinicians make more informed treatment decisions.

Clinical trial number

Not applicable.