Cascaded deep learning for automated lung cancer tumour burden quantification on [<sup>18</sup>F]FDG PET/CT.
Authors
Affiliations (2)
Affiliations (2)
- Department of Nuclear Medicine, The First Affiliated Hospital of Guangzhou Medical University, Guangzhou, China.
- Medical AI Lab, School of Biomedical Engineering, Shenzhen University Medical School, Shenzhen, China.
Abstract
Accurate assessment of tumour burden in lung cancer is critical for diagnosis, prognosis, and treatment planning. To enhance segmentation accuracy and reduce false positives (FPs), we developed a cascaded deep learning framework that combines lesion segmentation and subsequent classification, aiming to enable reliable automated tumour burden estimation on positron emission tomography/computed tomography (PET/CT). In this retrospective single-centre study, we collected 593 fluorine-18 fluorodeoxyglucose ([<sup>18</sup>F]FDG) PET/CT scans from lung cancer patients with two scanners. Scanner 1 data (N=496) were split for five-fold cross-validation (training/validation) and internal testing; Scanner 2 data (N=97) served for external testing. The proposed cascaded framework integrated a segmentation stage with a subsequent classification stage to suppress FP findings and generate lesion-level tumour segmentation for tumour burden quantification. We compared the cascaded model to standalone segmentation using Dice similarity coefficient (DSC), lesion-level precision/recall, and assessed metabolic tumour volume (MTV) and total lesion glycolysis (TLG) against manual annotations. On internal and external test sets, the cascaded model achieved consistent segmentation accuracy (DSC =0.82) with improved precision compared to segmentation alone (P<0.05). Tumour burden estimation showed strong correlations with manual measurements (r=0.984 for MTV, r=0.998 for TLG; both P<0.05) and moderate agreement. The proposed cascaded segmentation-classification architecture significantly reduces FPs and yields reliable tumour burden quantification on PET/CT, enhancing accuracy and clinical utility.