Introduction:

solitary pulmonary nodules are one of the most frequent problems in radiographic practice. They are a common incidental finding in chest studies conducted during routine clinical work.

Objective:

implement a computer-assisted diagnostic system facilitating detection of solitary pulmonary nodules in multicut computerized tomography image series.

Methods:

Matlab was used to develop and evaluate a set of algorithms constituting necessary components of a computer-assisted diagnostic system. The order was the following: an algorithm to extract regions of interest, another to extract characteristics, and another to detect solitary pulmonary nodules, for which several classifiers were tested. Evaluation of the algorithms was based on notes taken by specialists on the LIDC-IDRI (Lung Image Database Consortium) image collection.

Results:

the segmentation method used for extraction of regions of interest made it possible to create a suitable division of the original images into significant regions. The algorithm used for detection found that the test set exhibited good accuracy (96.4%), a good sensitivity balance (91.5%), and a 0.84 rate of false positives per image.

Conclusions:

the research and implementation work done is reflected in the construction of a Matlab graphic interface serving as a prototype for a computer-assisted diagnostic system which may facilitate detection of SPNs.

        · abstract in Spanish     · text in Spanish     · Spanish ( pdf )