Fig 1.
The proposed framework for kidney segmentation.
Fig 2.
Typical coronal cross-section DW-MRI samples showing (a) low contrast between the kidney and surrounding abdominal tissues at b0; (b) inter-patient anatomical differences at b0, (c) low signal-to-noise ratio (SNR), especially, at higher b-values (e.g., b1000); (d) image artifacts; and (e) geometric distortion/diffused boundaries.
Fig 3.
3D zero-level set of a function Φ(p = [x, y, z], t).
Fig 4.
The nearest 26-neighborhood of a voxel for the 4th-order spatial model and examples of its 2nd-order cliques (upper raw), 3rd-order cliques (middle raw), and 4th-order cliques (lower raw).
Note that the central voxel is shown in yellow, while its neighbors are shown (i) in red for the same plane and (ii) in blue and purple for the adjacent planes.
Fig 5.
3D co-alignment of training DW-MRI datasets (S1:SN) to a single reference: The first and second rows present the overlapped 3D kidney volumes before and after the alignment, respectively.
Note that the reference subject appears in magenta, while the targets are shown cyan.
Fig 6.
Our segmentation (red) with respect to the expert’s manual ground truth (green): The coronal (left), axial (middle), and sagittal (right) cross-sections for two different subjects in the first and second rows.
Fig 7.
Our segmentation (red) with respect to the expert’s manual ground truth (green) using the 4th-order MGRF (first row) compared to our previous segmentation using the 2nd-order MGRF (second row) [54], [55] for three different subjects (columns), where the first, second, and third columns show large, moderate, and small differences in yellow regions (false positive (FP)) and blue regions (false negative (FN)), respectively.
Table 1.
Our segmentation accuracy by the DSC, MHD (mm), and PKVD (%).
All metrics are represented by the minimum (Min), maximum (Max), and mean±standard deviation (SD) values.
Fig 8.
Comparative cross-sectional segmentation results for our approach (a), the vector level sets [35] (b), the segmentation using the Random Forest classifier [42] (c), and the traditional CV [31] level set (d) for two independent subjects (rows).
The model segmentation is shown in red with respect to the manual ground truth (green) from an expert.
Table 2.
Segmentation performance comparison between the presented approach against three other well-known segmentation methods (vector level-sets (VLS), random forest classifier (RFC), and Chan and Vese (CV)) using DSC, MHD (mm), and PKVD (%).
All metrics are represented by the mean± standard deviation (SD).
Fig 9.
Our 3D segmentation (red) with respect to the expert’s manual ground truth (green) for three subjects with the associated accuracy scores.
Fig 10.
Comparative coronal cross-sectional segmentation results for the proposed approach (a), the vector level sets [35] (b), the segmentation using the Random Forest classifier [42] (c), and the traditional CV [31] level set (d) for one subjects at b0 (first row) and higher bi values (b500 (second raw) and b1000 (third raw)).
The model segmentation is shown in red with respect to the manual ground truth (green) from an expert.