A Computer-based Method of Segmenting Ground Glass Nodules in Pulmonary CT Images: Comparison to Expert Radiologists’ Interpretations

摘要

Ground glass nodules (GGNs) have proved especially problematic in lung cancer diagnosis, as despite frequently beingmalignant they have extremely slow growth rates. In this work, the GGN segmentation results of a computer-basedmethod were compared with manual segmentation performed by two dedicated chest radiologists. CT volumes of 8patients were acquired by multi-slice CT. 21 pure or mixed GGNs were identified and independently segmented by thecomputer-based method and by two readers. The computer-based method is initialized by a click point, and uses aMarkov random field (MRF) model for segmentation. While the intensity distribution varies for different GGNs, theintensity model used in MRF is adapted for each nodule based on initial estimates. This method was run three times foreach nodule using different click points to evaluate consistency. In this work, consistency was defined by the overlapratio (overlap volume/mean volume). The consistency of the computer-based method with different initial points, with amean overlap ratio of 0.96±0.02 (95% confidence interval on mean), was significantly higher than the inter-observerconsistency between the two radiologists, indicated by a mean overlap ratio of 0.73±0.04. The computer consistencywas also significantly higher than the intra-observer consistency of two measurements from the same radiologist,indicated by an overlap ratio of 0.69±0.05 (p-value < 1E-05). The concordance of the computer with the expertinterpretation demonstrated a mean overlap ratio of 0.69±0.05. As shown by our data, the consistency provided by thecomputer-based method is significantly higher than between observers, and the accuracy of the method is no worse thanthat of one physician’s accuracy with respect to another, allowing more reproducible assessment of nodule growth.