System and method of pulmonary emboli detection for computed tomography

A method comprising:

• using a computed tomography (CT) scanner to perform the following steps:
• accessing a set of CT image data corresponding to a plurality of image voxels;
• applying a lung mask to the plurality of image voxels;
• isolating a set of pulmonary emboli candidates in the lung mask;
• assigning unscaled contrast values to the set of pulmonary emboli candidates;
• manipulating the set of pulmonary emboli candidates using a non-linear contrast enhancement;
• assigning scaled contrast values to the manipulated set of pulmonary emboli candidates;
• identifying a first set of false positive pulmonary emboli candidates from the unscaled contrast values, the first set of false positive pulmonary emboli candidates having unscaled contrast values outside a gray scale range of the set of CT image data;
• identifying a second set of false positive pulmonary emboli candidates from the scaled contrast values;
• removing the first and second sets of false positive pulmonary emboli candidates from the set of pulmonary emboli candidates to generate a final set of pulmonary emboli candidates;
• and
• reconstructing an image using the final set of pulmonary emboli candidates.

An imaging system comprising:

• a rotatable gantry having an opening for receiving an object to be scanned;
• an x-ray source coupled to the rotatable gantry and configured to project x-rays through the opening;
• a generator configured to energize the x-ray source to an energy level to generate x-rays corresponding to the energy level;
• a detector having pixels therein, the detector attached to the rotatable gantry and positioned to receive x-rays projected from the x-ray source;
• and
• a computer programmed to:
• acquire a CT image dataset corresponding to a plurality of image voxels;
• apply a plurality of masks to the CT image dataset to identify an initial set of pulmonary emboli candidates within the CT image data set;
• apply a non-linear contrast enhancement only to image data corresponding to the initial set of pulmonary emboli candidates;
• generate a contrast-enhanced set of pulmonary emboli candidates based on the applied non-linear contrast enhancement;
• identify a first set of false positive pulmonary emboli candidates within the contrast-enhanced set of pulmonary emboli candidates;
• identify a second set of false positive pulmonary emboli candidates within the initial set of pulmonary emboli candidates, the second set of false positive pulmonary emboli candidates distinct from the first set of false positive pulmonary emboli candidates;
• remove the first and second sets of false positive pulmonary emboli candidates from the initial set of pulmonary emboli candidates to generate a final set of pulmonary emboli candidates;
• and
• output the final set of pulmonary emboli candidates.