Copyright
©The Author(s) 2022.
World J Gastrointest Oncol. Dec 15, 2022; 14(12): 2380-2392
Published online Dec 15, 2022. doi: 10.4251/wjgo.v14.i12.2380
Published online Dec 15, 2022. doi: 10.4251/wjgo.v14.i12.2380
Table 1 Patient characteristics
| Study population (n = 414) | Training cohort (n = 289) | Testing cohort (n = 125) | P value | |
| Age, yr | 53.00 (45.00- 60.00) | 52.059 ± 12.190 | 53.216 ± 11.380 | 0.1988 |
| Gender, n (%) | ||||
| Male | 375 (90.6) | 262 (90.7) | 113 (90.4) | 0.9196 |
| BMI, kg/m2 | 24.50 ± 4.20 | 24.10 ± 3.20 | 24.70 ± 3.40 | 0.1889 |
| HBsAg-positive, n (%) | 375 (90.6) | 264 (91.3) | 111 (88.8) | 0.5274 |
| AFP > 7 ng/mL, n (%) | 292 (70.5) | 205 (70.9) | 87 (69.6) | 0.8761 |
| CEA > 5 ng/ml, n (%) | 31 (7.5) | 24 (8.3) | 7 (5.6) | 0.4494 |
| CA125 > 40 ng/mL, n (%) | 15 (3.6) | 8 (2.8) | 7 (5.6) | 0.2588 |
| CA199 > 34 ng/mL, n (%) | 46 (11.1) | 295 (10.0) | 17 (13.6) | 0.3738 |
| WBC count, /μL | 6262 ± 1985 | 6232 ± 1756 | 6354 ± 2125 | 0.5668 |
| ALT, U/L | 49 ± 36 | 48 ± 39 | 51 ± 41 | 0.1654 |
| AST, U/L | 51 ± 35 | 49 ± 36 | 53 ± 42 | 0.2358 |
| Liver cirrhosis, n (%) | 345 (83.3) | 244 (84.4) | 101 (80.8) | 0.3630 |
| Microvascular invasion, n (%) | 312 (75.4) | 211 (73.0) | 101 (80.8) | 0.0910 |
| Tumor size, cm | ||||
| x | 2.40 [1.70-3.68] | 2.957 ± 1.850 | 3.120 ± 2.050 | 0.3689 |
| y | 2.00 [1.42-3.10] | 2.480 ± 1.490 | 2.670 ± 1.960 | 0.4820 |
| Gray-scale echogenicity | 0.5954 | |||
| Hyperechoic | 46 (11.1) | 35 (12.1) | 11 (8.8) | |
| Medium | 4 (1.0) | 3 (1.0) | 1 (0.8) | |
| Hypoechoic | 364 (87.9) | 251 (86.9) | 113 (90.4) | |
| Arterial phase | 0.4639 | |||
| Hyperenhancement | 403 (97.3) | 283 (97.9) | 120 (96.0) | |
| Isoenhancement | 8 (1.9) | 4 (1.4) | 4 (3.2) | |
| Hypoenhancement | 3 (0.7) | 2 (0.7) | 1 (0.8) | |
| Portal phase | 0.6669 | |||
| Hyperenhancement | 15 (3.5) | 12 (4.2) | 3 (2.4) | |
| Isoenhancement | 232 (56.0) | 162 (56.1) | 70 (56.0) | |
| Hypoenhancement | 167 (40.3) | 115 (39.8) | 52 (41.6) | |
| Late phase | 0.1300 | |||
| Hyperenhancement | 2 (0.5) | 1 (0.3) | 1 (0.8) | |
| Isoenhancement | 79 (19.1) | 46 (15.9) | 33 (90.4) | |
| Hypoenhancement | 333 (80.4) | 232 (80.3) | 101 (80.8) | |
| Enhancing capsules | 45 (10.9) | 36 (12.5) | 9 (7.2) | 0.1598 |
| Unsmooth margins | 97 (23.4) | 64 (22.19) | 33 (26.4) | 0.4168 |
| Retreatment after recurrence | 168 (40.3) | 118 (40.5) | 50 (40.0) | 0.9270 |
Table 2 Univariate and multivariable analyses of early recurrence of hepatocellular carcinoma patients
| Univariate cox regression | Multivariate logistic regression | |||||||
| HR | [0.025 | 0.975] | P | HR | [0.025 | 0.975] | P | |
| Age, yr | 0.991 | 0.971 | 1.011 | 0.383 | ||||
| Gender | 1.005 | 0.463 | 2.181 | 0.990 | ||||
| HBsAg-positive | 1.138 | 0.472 | 2.740 | 0.773 | ||||
| AFP | 0.622 | 0.361 | 1.071 | 0.087 | 0.709 | 0.406 | 1.239 | 0.227 |
| CEA | 0.944 | 0.352 | 2.535 | 0.910 | ||||
| CA125 | 1.811 | 0.424 | 7.752 | 0.423 | ||||
| CA19-9 | 1.636 | 0.727 | 3.684 | 0.234 | ||||
| ALT, U/L | 1.248 | 0.697 | 2.321 | 0.267 | ||||
| AST, U/L | 1.566 | 0.397 | 2.108 | 0.675 | ||||
| FIB-4 score | 1.212 | 0.431 | 1.986 | 0.742 | ||||
| Liver cirrhosis | 1.142 | 0.506 | 2.121 | 0.657 | ||||
| Tumor size x | 1.000 | 0.882 | 1.143 | 0.951 | ||||
| Tumor size y | 0.988 | 0.856 | 1.142 | 0.873 | ||||
| Gray-scale echogenicity | 0.731 | 0.493 | 1.087 | 0.121 | ||||
| Arterial phase enhancement | 0.924 | 0.351 | 2.438 | 0.874 | ||||
| Portal phase enhancement | 1.321 | 0.832 | 2.100 | 0.238 | ||||
| Portal phase enhancement | 0.982 | 0.512 | 1.885 | 0.957 | ||||
| Enhancing capsules | 0.930 | 0.413 | 2.096 | 0.862 | ||||
| Satellite nodules | 4.843 | 1.917 | 12.244 | 0.001 | 4.194 | 1.368 | 12.871 | 0.012 |
| Unsmooth margins | 0.839 | 0.462 | 1.522 | 0.563 | ||||
| Constant | 0.990 | 0.707 | 1.387 | 0.953 | ||||
Table 3 Univariate and multivariable analyses of overall survival of hepatocellular carcinoma patients
| Univariate cox regression | Multivariate logistic regression | |||||||
| HR | [0.025 | 0.975] | P | HR | [0.025 | 0.975] | P | |
| Age, yr | 1.020 | 1.000 | 1.030 | 0.010 | 1.02 | 1.00 | 1.03 | 0.01 |
| Gender | 1.570 | 1.030 | 2.390 | 0.030 | 1.42 | 0.89 | 2.26 | 0.14 |
| HBsAg-positive | 1.600 | 1.030 | 2.490 | 0.040 | 1.32 | 0.82 | 2.12 | 0.25 |
| AFP | 1.100 | 0.830 | 1.460 | 0.500 | ||||
| CEA | 0.760 | 0.460 | 1.270 | 0.300 | ||||
| CA125 | 0.580 | 0.280 | 1.220 | 0.150 | ||||
| CA19-9 | 0.630 | 0.420 | 0.950 | 0.030 | 0.65 | 0.41 | 1.03 | 0.07 |
| ALT, U/L | 1.121 | 0.453 | 1.976 | 0.430 | ||||
| AST, U/L | 1.342 | 0.876 | 2.014 | 0.540 | ||||
| FIB-4 score | 1.012 | 0.547 | 1.743 | 0.720 | ||||
| Liver cirrhosis | 1.112 | 0.563 | 1.956 | 0.550 | ||||
| Tumor size x | 1.080 | 1.010 | 1.160 | 0.040 | 0.96 | 0.85 | 1.09 | 0.56 |
| Tumor size y | 1.090 | 1.020 | 1.170 | 0.010 | 1.17 | 1.02 | 1.33 | 0.02 |
| Gray-scale echogenicity | 0.830 | 0.670 | 1.020 | 0.080 | 0.77 | 0.60 | 0.99 | 0.04 |
| Arterial phase enhancement | 0.680 | 0.420 | 1.110 | 0.130 | ||||
| Portal phase enhancement | 1.270 | 0.990 | 1.620 | 0.060 | 1.25 | 0.95 | 1.63 | 0.11 |
| Portal phase Enhancement | 1.130 | 0.810 | 1.580 | 0.460 | ||||
| Enhancing capsules | 1.110 | 0.720 | 1.710 | 0.630 | ||||
| Satellite nodules | 1.190 | 0.780 | 1.830 | 0.420 | ||||
| Unsmooth margins | 0.720 | 0.520 | 0.990 | 0.040 | 0.79 | 0.56 | 1.13 | 0.19 |
| Early reoccurrence | 1.290 | 0.990 | 1.680 | 0.060 | 1.25 | 0.93 | 1.67 | 0.14 |
| Retreatment after recurrence | 0.710 | 0.540 | 1.160 | 0.300 | ||||
| DLR | 3.240 | 2.670 | 3.930 | < 0.005 | ||||
- Citation: Huang Z, Shu Z, Zhu RH, Xin JY, Wu LL, Wang HZ, Chen J, Zhang ZW, Luo HC, Li KY. Deep learning-based radiomics based on contrast-enhanced ultrasound predicts early recurrence and survival outcome in hepatocellular carcinoma. World J Gastrointest Oncol 2022; 14(12): 2380-2392
- URL: https://www.wjgnet.com/1948-5204/full/v14/i12/2380.htm
- DOI: https://dx.doi.org/10.4251/wjgo.v14.i12.2380
