Skip to main content

Table 2 The distribution of subtypes between the training cohort and the validation cohort

From: Ultrasound-based radiomics for predicting the five major histological subtypes of epithelial ovarian cancer

Group

All patients (n = 1209)

P

Patients with the five major histological subtypes (n = 1039)

P

 

Training cohort

Validation cohort

 

Training cohort

Validation cohort

 

HGSC

451 (53.31%)

194 (53.44%)

0.966

451 (62.04%)

194 (62.18%)

0.965

Non-HGSC

395 (46.69%)

169 (46.56%)

276 (37.96%)

118 (37.82%)

MC

55 (6.50%)

24 (6.61%)

0.943

55 (7.57%)

24 (7.69%)

0.944

Non-MC

791 (93.50%)

339 (93.39%)

672 (92.43%)

288 (92.31%)

CC

93 (10.99%)

40 (11.02%)

0.989

93 (12.79%)

40 (12.82%)

0.990

Non-CC

753 (89.01%)

323 (88.98%)

634 (87.21%)

272 (87.18%)

EN

77 (9.10%)

33 (9.09%)

0.995

77 (10.59%)

33 (10.58%)

0.994

Non-EN

769 (90.90%)

330 (90.91%)

650 (89.41%)

279 (89.42%)

LGSC

50 (5.91%)

22 (6.06%)

0.919

50 (6.88%)

22 (7.05%)

0.920

Non-LGSC

796 (94.09%)

341 (93.94%)

677 (93.12%)

290 (92.95%)

  1. Notes: HGSC, high-grade serous carcinoma; MC, mucinous carcinoma; CC, clear cell carcinoma; EN, endometrioid carcinoma; LGSC, low-grade serous carcinoma