VIDETECT

videtect - detects isolated nodules from a whole lung CT scans.

videtect [if=] [ig=] [is=] [oc=] [of=] [am=] [om=] [d=] [k=] [t=] [-v] [-w]

videtect program detects isolated nodules from a whole lung CT scan.

Isolated nodules include nodules with no attachment to a large solid structure These nodules have, in general, a spherical shape. However, the spherical shape may be distorted by other small lung structures such as vessels, bronchi, scars and regions of morbidity. Typically, growing nodules appear to wrap around such structures.

Our nodule detection algorithm involves three major stages. First, lung regions are segmented from the whole lung CT scan. This is followed by a hypothesis generation stage. In this stage, nodule candidate regions are identified from the whole lung scan and their size is estimated. The nodule candidates are successively refined in the fourth stage using filters of increa sing complexity.

For isolated nodule detection algorithm, the whole lung CT scan [if=] have to be specified. In addition, the lung parenchyma mask [ig=] and [is=] streaking artifact fitlered image can be specified, otherwise the program generates the two images first. If inital isolated nodule candidates file is available, it can be specified using [oc=] option and the program goes straight to false positive reduction stage.

The program outputs potential nodule location (XYZ) including their size in a text file format [of=]. A text format feature matrix for the all nodule candidates or refined isolated nodules can be generated using [am=] and [om=] options respectively. Various debugging options are available. [-v] and [-w] provide different levels of verbose information. In addition, all intermediate files can be stored in a separate directory for debugging using [t=] option.

vdetect,vadetect

Andinet A. Enquobahrie