Autosegmentation of cardiac substructures in respiratory-gated, non-contrasted computed tomography images

Figure 1 Project workflow of initial multi-atlas library construction, MIM autosegmentation, and subsequent edits of generated structures to add to the MIM atlas library.

Figure 2 Physician-based evaluation of generated structures using atlas libraries comprised of 20-, 30-, and 40-patient samples (mean, standard deviation). Scale: 0 = No changes made; 1 = Minor changes made, 2 = Moderate changes required by structure was salvageable, 3 = Structure required deletion and replacement, 4 = Structure failed autosegmentation.

Figure 3 Analysis comparing the volumes of autosegmented structures (MIM) vs subsequent physician-edited sister (RO) (mean ± SD).