Author Contributions
Conceptualization, L.B., V.M.A. and A.A.T.; methodology, V.M.A.; software, L.B.; validation, D.L.M.; formal analysis, L.B. and V.M.A.; investigation, L.B., A.A.T. and V.M.A.; resources, E.-R.S., D.L.M. and C.-I.O.; data curation, E.-R.S.; image sample selection: A.A.T., C.-I.O., D.L.M. and E.-R.S.; writing—original draft preparation, L.B., A.A.T. and V.M.A.; writing—review and editing, L.B., A.A.T. and V.M.A.; visualization, L.B., V.M.A. and E.-R.S.; supervision, H.C., C.-I.O. and D.L.M.; project administration, C.-I.O. All authors have read and agreed to the published version of the manuscript.
Figure 1.
Axial thin-section CT scans, injury patterns: high density (1, 2, 3), low density (4, 5, 6), reticular (7, 8), nodular pattern (9, 10), and overlapping (11, 12, 13, 14). Scans belong to the ‘Dr. Victor Babes’ Infectious Diseases and Pneumoftiziology Clinical Hospital Timisoara database.
Figure 1.
Axial thin-section CT scans, injury patterns: high density (1, 2, 3), low density (4, 5, 6), reticular (7, 8), nodular pattern (9, 10), and overlapping (11, 12, 13, 14). Scans belong to the ‘Dr. Victor Babes’ Infectious Diseases and Pneumoftiziology Clinical Hospital Timisoara database.
Figure 2.
Splitting CT sample into layers (a) original CT, (b) sample crop, (c) combined Emphysema, GGO, and Consolidation layers, (d) Emphysema layer, (e) GGO layer, (f) Consolidation layer.
Figure 2.
Splitting CT sample into layers (a) original CT, (b) sample crop, (c) combined Emphysema, GGO, and Consolidation layers, (d) Emphysema layer, (e) GGO layer, (f) Consolidation layer.
Figure 3.
Degree distributions for various Rd.
Figure 3.
Degree distributions for various Rd.
Figure 4.
Algorithm step 1—sample selection (a) Normal sample (b) DILD (IFP) sample.
Figure 4.
Algorithm step 1—sample selection (a) Normal sample (b) DILD (IFP) sample.
Figure 5.
Emphysema processing (a) HU filtered layer for the normal sample; (b) HU filtered layer for the DILD sample (c) Complex network built according to the proposed algorithm corresponding to the normal sample, Fruchterman–Reingold render layout, node sizes proportional to node degrees, edge width invariant (1.5 pixels). (d) Complex network built according to the proposed algorithm corresponding to the DILD sample, Fruchterman–Reingold render layout, node sizes proportional to node degrees, edge width invariant (1.5 pixels). (e) Degree distribution of the normal sample network (f) Degree distribution of the DILD sample network.
Figure 5.
Emphysema processing (a) HU filtered layer for the normal sample; (b) HU filtered layer for the DILD sample (c) Complex network built according to the proposed algorithm corresponding to the normal sample, Fruchterman–Reingold render layout, node sizes proportional to node degrees, edge width invariant (1.5 pixels). (d) Complex network built according to the proposed algorithm corresponding to the DILD sample, Fruchterman–Reingold render layout, node sizes proportional to node degrees, edge width invariant (1.5 pixels). (e) Degree distribution of the normal sample network (f) Degree distribution of the DILD sample network.
Figure 6.
GGO processing (a) HU filtered layer for the normal sample; (b) HU filtered layer for the DILD sample (c) Complex network built according to the proposed algorithm corresponding to the normal sample, Fruchterman–Reingold render layout, node sizes proportional to node degrees, edge width invariant (1.5 pixels). (d) Complex network built according to the proposed algorithm corresponding to the DILD sample, Fruchterman–Reingold render layout, node sizes proportional to node degrees, edge width invariant (1.5 pixels). (e) Degree distribution of the normal sample network (f) Degree distribution of the DILD sample network. Equations for curve fit and R2 are also presented for the relevant distributions.
Figure 6.
GGO processing (a) HU filtered layer for the normal sample; (b) HU filtered layer for the DILD sample (c) Complex network built according to the proposed algorithm corresponding to the normal sample, Fruchterman–Reingold render layout, node sizes proportional to node degrees, edge width invariant (1.5 pixels). (d) Complex network built according to the proposed algorithm corresponding to the DILD sample, Fruchterman–Reingold render layout, node sizes proportional to node degrees, edge width invariant (1.5 pixels). (e) Degree distribution of the normal sample network (f) Degree distribution of the DILD sample network. Equations for curve fit and R2 are also presented for the relevant distributions.
Figure 7.
Consolidation processing (a) HU filtered layer for the normal sample; (b) HU filtered layer for the DILD sample (c) Complex network built according to the proposed algorithm corresponding to the normal sample, Fruchterman–Reingold render layout, node sizes proportional to node degrees, edge width invariant (1.5 pixels). (d) Complex network built according to the proposed algorithm corresponding to the DILD sample, Fruchterman–Reingold render layout, node sizes proportional to node degrees, edge width invariant (1.5 pixels). (e) Degree distribution of the normal sample network (f) Degree distribution of the DILD sample network. Equations for curve fit and R2 are also presented for the relevant distributions.
Figure 7.
Consolidation processing (a) HU filtered layer for the normal sample; (b) HU filtered layer for the DILD sample (c) Complex network built according to the proposed algorithm corresponding to the normal sample, Fruchterman–Reingold render layout, node sizes proportional to node degrees, edge width invariant (1.5 pixels). (d) Complex network built according to the proposed algorithm corresponding to the DILD sample, Fruchterman–Reingold render layout, node sizes proportional to node degrees, edge width invariant (1.5 pixels). (e) Degree distribution of the normal sample network (f) Degree distribution of the DILD sample network. Equations for curve fit and R2 are also presented for the relevant distributions.
Figure 8.
Population distribution comparisons according to specific complex network parameters: (a) Total count (b) Average count (c) Maximum degree Class 0 (fuchsia) represents normal lungs, while class 1 (yellow) is formed of DILD affected lungs.
Figure 8.
Population distribution comparisons according to specific complex network parameters: (a) Total count (b) Average count (c) Maximum degree Class 0 (fuchsia) represents normal lungs, while class 1 (yellow) is formed of DILD affected lungs.
Figure 9.
(a) Normal population plotted based on the average degree. Class 0 is the normal population investigated prior COVID-19, class 1 are cases diagnosed as normal in the pandemic era (b) DILD population plotted based on the average degree. Class 2 is UIP, 3 probable UIP, 4 UIP and emphysema, 5 organizing pneumonitis (OP), 6 hypersensitivity pneumonitis (HP), and 7 sarcoidosis.
Figure 9.
(a) Normal population plotted based on the average degree. Class 0 is the normal population investigated prior COVID-19, class 1 are cases diagnosed as normal in the pandemic era (b) DILD population plotted based on the average degree. Class 2 is UIP, 3 probable UIP, 4 UIP and emphysema, 5 organizing pneumonitis (OP), 6 hypersensitivity pneumonitis (HP), and 7 sarcoidosis.
Figure 10.
Average coefficient of determination (R2) for logarithmic and power distributions, relative to radial distance (Rd).
Figure 10.
Average coefficient of determination (R2) for logarithmic and power distributions, relative to radial distance (Rd).
Figure 11.
Relative percentage of standard deviation for DILD vs. normal lungs on all the pathological HU bands, taking into account maximum degree, total count, and average degree. Absolute values are also given for each data point.
Figure 11.
Relative percentage of standard deviation for DILD vs. normal lungs on all the pathological HU bands, taking into account maximum degree, total count, and average degree. Absolute values are also given for each data point.
Figure 12.
(a) HRCT slice under analysis (b) Sample 1 (c) Sample 2 (d) Degree distribution for sample 1 on the emphysema layer (e) Degree distribution for sample 2 on the emphysema layer (f) Degree distribution for sample 1 on the GGO layer (g) Degree distribution for sample 2 on the GGO layer.
Figure 12.
(a) HRCT slice under analysis (b) Sample 1 (c) Sample 2 (d) Degree distribution for sample 1 on the emphysema layer (e) Degree distribution for sample 2 on the emphysema layer (f) Degree distribution for sample 1 on the GGO layer (g) Degree distribution for sample 2 on the GGO layer.
Figure 13.
Box plot for DILD (left) vs. normal (right) for complex network parameters of (a) maximum degree (b) total count (c) average degree.
Figure 13.
Box plot for DILD (left) vs. normal (right) for complex network parameters of (a) maximum degree (b) total count (c) average degree.
Table 1.
HU intervals from the reports of Lin Li et al. and Maria Paola Belfiore et al. [
26,
27,
28]. These values are specific to the General Electric Healthcare Optima 520.
Table 1.
HU intervals from the reports of Lin Li et al. and Maria Paola Belfiore et al. [
26,
27,
28]. These values are specific to the General Electric Healthcare Optima 520.
Pulmonary Zones | HU Intervals |
---|
Emphysema | [−1024, −977) |
Normal pulmonary parenchyma | [−977, −703) |
Ground-glass opacities | [−703, −368) |
Others (crazy-paving, pleural fat) | [−368, −100) |
Consolidations | [−100, 5) |
Others (interstitial vessels) | >5 HU |
Table 2.
Statistical comparisons.
Table 2.
Statistical comparisons.
| Maximum Degree | Total Count | Average Count |
---|
| DILD | Normal | DILD | Normal | DILD | Normal |
---|
Mean | 15.96875 | 7.032258 | 846.5692 | 7.1 | 51.65253 | 32.53397 |
Variance | 39.45933 | 3.365591 | 206,084.5 | 3.334483 | 362.9068 | 113.4483 |
Observations | 30 | 30 | 30 | 30 | 30 | 30 |
Hypothesized Mean Difference | 0 | | 0 | | 0 | |
Df | 82 | | 64 | | 92 | |
t Stat | 10.49451 | | 14.9084 | | 6.288591 | |
P(T ≤ t) one-tail | 3.97 × 10−17 | | 8.52 × 10−23 | | 5.31 × 10−9 | |
t Critical one-tail | 1.663649 | | 1.669013 | | 1.661585 | |
P(T ≤ t) two-tail | 7.93 × 10−17 | | 1.7 × 10−22 | | 1.06 × 10−8 | |
t Critical two-tail | 1.989319 | | 1.99773 | | 1.986086 | |
Table 3.
Methodology compariso.ns.
Table 3.
Methodology compariso.ns.
| Just HRCT | Analytical | Empirical | Works Alone | Measurement |
---|
Doctor | N | Y | Y (“clinical sense”) | Y | Subjective |
Caliper [21] | N, PFT | Y | N | Y | Yes, one dimensional size |
Zrimec [22,23] | Y | Y | N | Mostly | Maybe |
Machine learning | Y | N | Y | Maybe | Maybe |
Proposed model | Y | Y | N | N | Yes, three dimensional size |