Skip to main content

Table 5 Comparison of clinical test set images analyzed by the AI-IQA system and experts

From: Effectiveness and clinical impact of using deep learning for first-trimester fetal ultrasound image quality auditing

Plane

AI-IQA

Experts

Cohen’ Kappa [95%CI]

Standard

Nonstandard

Standard

Nonstandard

NTP (n = 637)

596 (93.6)

41 (6.4)

600 (94.2)

37 (5.8)

0.892 [0.829,0.955]

MSF (n = 662)

564 (85.2)

98 (14.8)

572 (86.4)

90(13.6)

0.879 [0.800,0.957]

AFTP (n = 624)

553 (88.6)

71 (11.4)

560 (89.7)

64(10.3)

0.850 [0.783,0.917]

AFA (n = 641)

485 (75.7)

156 (24.3)

493 (76.9)

148 (23.1)

0.857 [0.761,0.953]

  1. Data are expressed as number (percentage). AI-IQA: artificial intelligence-based image quality audit, NTP: nuchal translucency plane, MSF: midsagittal view of the fetus, AFTP: axial view of fetal head in the transventricular plane, AFA: axial view of fetal abdomen
Back to article page

BMC Pregnancy and Childbirth

ISSN: 1471-2393

Contact us