PET-CT–Based Auto-Contouring in Non–Small-Cell Lung Cancer Correlates With Pathology and Reduces Interobserver Variability in the Delineation of the Primary Tumor and Involved Nodal Volumes

• Published in: International journal of radiation oncology, biology, physics Vol. 68; no. 3; pp. 771 - 778
• Main Authors: van Baardwijk, Angela, M.D, Bosmans, Geert, M.Sc, Boersma, Liesbeth, M.D., Ph.D, Buijsen, Jeroen, M.D, Wanders, Stofferinus, M.D, Hochstenbag, Monique, M.D., Ph.D, van Suylen, Robert-Jan, M.D., Ph.D, Dekker, André, M.Sc., Ph.D, Dehing-Oberije, Cary, M.Sc, Houben, Ruud, M.Sc, Bentzen, Søren M., Ph.D., D.Sc, van Kroonenburgh, Marinus, M.D., Ph.D, Lambin, Philippe, M.D., Ph.D, De Ruysscher, Dirk, M.D., Ph.D
• Format: Journal Article
• Language: English
• Published: United States Elsevier Inc 01.07.2007
• Subjects: Artificial Intelligence; Auto-contouring; Carcinoma, Non-Small-Cell Lung - diagnosis; CARCINOMAS; COMPUTERIZED TOMOGRAPHY; Female; Fluorodeoxyglucose F18; Hematology, Oncology and Palliative Medicine; Humans; Image Enhancement - methods; Imaging, Three-Dimensional - methods; Interobserver variability; Lung Neoplasms - diagnosis; LUNGS; LYMPH NODES; Male; NSCLC; Observer Variation; PATHOLOGY; PATIENTS; Pattern Recognition, Automated - methods; PET-CT; Positron-Emission Tomography - methods; Radiology; RADIOLOGY AND NUCLEAR MEDICINE; Radiopharmaceuticals; Reproducibility of Results; SENSITIVITY; Sensitivity and Specificity; SPECIFICITY; Subtraction Technique; Tomography, X-Ray Computed - methods; Pathology; PET-CT; NSCLC; Auto-contouring; Interobserver variability
• ISSN: 0360-3016; 1879-355X
• DOI: 10.1016/j.ijrobp.2006.12.067

Purpose: To compare source-to-background ratio (SBR)-based PET-CT auto-delineation with pathology in non–small-cell lung cancer (NSCLC) and to investigate whether auto-delineation reduces the interobserver variability compared with manual PET-CT–based gross tumor volume (GTV) delineation. Methods and Materials: Source-to-background ratio–based auto-delineation was compared with macroscopic tumor dimensions to assess its validity in 23 tumors. Thereafter, GTVs were delineated manually on 33 PET-CT scans by five observers for the primary tumor (GTV-1) and the involved lymph nodes (GTV-2). The delineation was repeated after 6 months with the auto-contour provided. This contour was edited by the observers. For comparison, the concordance index (CI) was calculated, defined as the ratio of intersection and the union of two volumes (A∩B)/(A∪B). Results: The maximal tumor diameter of the SBR-based auto-contour correlated strongly with the macroscopic diameter of primary tumors (correlation coefficient = 0.90) and was shown to be accurate for involved lymph nodes (sensitivity 67%, specificity 95%). The median auto-contour–based target volumes were smaller than those defined by manual delineation for GTV-1 (31.8 and 34.6 cm3 , respectively; p = 0.001) and GTV-2 (16.3 and 21.8 cm3 , respectively; p = 0.02). The auto-contour–based method showed higher CIs than the manual method for GTV-1 (0.74 and 0.70 cm3 , respectively; p < 0.001) and GTV-2 (0.60 and 0.51 cm3 , respectively; p = 0.11). Conclusion: Source-to-background ratio–based auto-delineation showed a good correlation with pathology, decreased the delineated volumes of the GTVs, and reduced the interobserver variability. Auto-contouring may further improve the quality of target delineation in NSCLC patients.