Leveraging machine learning with dynamic 18F-FDG PET/CT: integrating metabolic and flow features for lung cancer differential diagnosis

• Published in: European journal of nuclear medicine and molecular imaging Vol. 52; no. 10; pp. 3807 - 3819
• Main Authors: Yao, Zhiheng, Wang, Yubo, Wu, Yaping, Zhou, Jinpeng, Dang, Na, Wang, Meiyun, Liang, Ying, Sun, Tao
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.08.2025; Springer Nature B.V
• Subjects: Aged; Benign; Blood flow; Cardiology; Charts; Computed tomography; Coronary vessels; Datasets; Decision trees; Diagnosis; Diagnosis, Differential; Differential diagnosis; Ethics; Feature extraction; Female; Fluorine isotopes; Fluorodeoxyglucose F18; Hospitals; Humans; Imaging; Learning algorithms; Lesions; Liver cancer; Lung cancer; Lung Neoplasms - diagnostic imaging; Lung Neoplasms - metabolism; Machine Learning; Male; Medical imaging; Medicine; Medicine & Public Health; Metabolism; Middle Aged; Nuclear Medicine; Oncology; Original; Original Article; Orthopedics; Partial differential equations; Patients; Positron emission; Positron emission tomography; Positron Emission Tomography Computed Tomography; Radiology; Lung cancer diagnosis; SHAP interpretability; Dynamic 18F-FDG PET/CT; Time activity curves; Machine learning
• ISSN: 1619-7070; 1619-7089; 1619-7089
• DOI: 10.1007/s00259-025-07231-0

Background Dynamic 18F-fluorodeoxyglucose (18F-FDG) PET/CT imaging has been shown to provide additional information for diagnosing lung cancer. The aim of this study was to investigate whether metabolic and flow features directly extracted from time activity curves (TACs) help differentiate between benign and malignant conditions of lung lesions. Methods TACs at the primary lesion were extracted from each dynamic 18F-FDG PET/CT scan. The TAC signal was then decomposed into metabolism and blood flow components through kinetic modeling. Dynamic features including area under the curve (AUC), time-to-peak, and slopes were then extracted from each component. The extracted features from 187 patients (mean age, 60.41 ± 11.01 years; 117 males) were used to train a classification model based on bagging, a machine-learning method built with decision trees. The performance of the trained model on differentiating benign and malignant was tested using receiver operating characteristic analysis with cross-validation. External testing was then performed for an independent dataset that consisted of 42 dynamic scans. For the results, SHapley Additive exPlanations (SHAP) were used to assess the relative importance of the contributed features for individuals. Waterfall charts were also plotted, together with assessment of Cohen’s effect size to demonstrate the superiority of the proposed model over SUVmax and the net FDG influx rate K i . Results The combination of the multiple dynamic features was able to separate benign and malignant lesions. For cross-validation, the trained model had an AUC of 0.89, sensitivity of 0.80, and specificity of 0.88, which was significantly higher than that of either SUVmax (AUC = 0.79, DeLong p  <  0. 001) or K i (AUC = 0.76, DeLong test p  < 0.001). For the testing dataset, the model had an AUC of 0.86, which again was better than either SUVmax (AUC of 0.72) or K i (AUC of 0.71). The most important features that contributed to the diagnosis identified by SHAP included the slope and maximum metabolism TAC at the lesion, the AUC, and the peak time of blood TAC at the lesion. The waterfall chart illustrated that the model had significantly different prediction scores between the benign and malignant groups ( p  < 0.001) with a Cohen’s effect size of 1.71, which was higher than that of the values for SUV and K i (Cohen’s effect size 0.96 and 0.81, respectively). Conclusion An explainable machine learning model that combines dynamic FDG metabolic and flow features can predict benign or malignant lung cancer patients more accurately than conventional parameters such as SUVmax or net influx rate K i .