Lymph node detection and segmentation in chest CT data using discriminative learning and a spatial prior

Johannes Feulner, Shaohua Kevin Zhou, Matthias Hammon, Joachim Hornegger, Dorin Comaniciu

Abstract: Lymph nodes have high clinical relevance and routinely need to be considered in clinical practice. Automatic detection is, however, challenging due to clutter and low contrast. In this paper, a method is presented that fully automatically detects and segments lymph nodes in 3-D computed tomography images of the chest. Lymph nodes can easily be confused with other structures, it is therefore vital to incorporate as much anatomical prior knowledge as possible in order to achieve a good detection performance. Here, a learned prior of the spatial distribution is used to model this knowledge. Different prior types with increasing complexity are proposed and compared to each other. This is combined with a powerful discriminative model that detects lymph nodes from their appearance. It first generates a number of candidates of possible lymph node center positions. Then, a segmentation method is initialized with a detected candidate. The graph cuts method is adapted to the problem of lymph nodes segmentation. We propose a setting that requires only a single positive seed and at the same time solves the small cut problem of graph cuts. Furthermore, we propose a feature set that is extracted from the segmentation. A classifier is trained on this feature set and used to reject false alarms. Cross-validation on 54 CT datasets showed that for a fixed number of four false alarms per volume image, the detection rate is well more than doubled when using the spatial prior. In total, our proposed method detects mediastinal lymph nodes with a true positive rate of 52.0% at the cost of only 3.1 false alarms per volume image and a true positive rate of 60.9% with 6.1 false alarms per volume image, which compares favorably to prior work on mediastinal lymph node detection. Graphical abstract Lymph node detection and segmentation system. Download : Download high-res image (143KB) Download : Download full-size image Highlights ► A method for lymph node detection and segmentation in CT is presented. ► A discriminative model of the lymph node appearance is combined with a spatial prior. ► The spatial prior more than doubles the detection rate for fixed false alarms. ► Combining segmentation with detection further improves the detection performance.