A multiple anatomical landmark detection system for body CT images

Automatic detection of anatomical landmarks has wide range of application in medical image analysis. In this short paper, we present a two-stage method to detect 181 landmarks simultaneously. In the first stage, each landmark is independently searched by a dedicated detector which outputs a list of candidate positions for the target landmark. Each detector is composed of an appearance-based initial detector and a classifier ensemble to estimate the probabilities of detected candidates and to eliminate false positives. Here, the appearance shape used in each detector is optimized by a cross-validation-based variable selection algorithm in advance. Then, in the following second stage, a single combination of all landmark positions is determined from all the candidate lists. The determination is performed by maximum a posteriori (MAP) estimation in which the posterior probability is calculated from both the likelihoods of detected candidates (estimated by the classifier ensemble) and a statistical spatial distribution model of the all landmarks. This MAP estimation process can also determine whether each landmark is within the given CT volume or out of the imaging range. The proposed system was trained for 181 landmarks with 60 human torso CT datasets and evaluated with another 60 datasets. The datasets include both plain CT and contrast enhanced CT volumes with various imaging ranges. In the result, 69.0% and 87.9% of the landmarks were successfully detected within 1 and 2 cm from the ground truth point, respectively. The average detection error was 9.58 mm. From these results, applicability of the proposed system to various CT datasets was verified.