Skip to main content
. Author manuscript; available in PMC: 2024 Apr 1.
Published in final edited form as: IEEE Trans Artif Intell. 2022 Mar 15;4(2):383–397. doi: 10.1109/tai.2022.3159510

TABLE IV.

Comparison of multi-task learning with mixup on cortical plate segmentation. Bold type indicates statistically better results at p = 0.01.

Training/fine-tuning data Test data DSC HD95 (mm) ASSD (mm) ECE MCE
Multitask learning CP- younger fetus 0.90 ± 0.02 0.81 ± 0.01 0.18 ± 0.03 0.05±0.03 0.13±0.08
CP- older fetus 0.85 ± 0.03 0.90 ± 0.16 0.30 ± 0.05 0.04±0.02 0.09±0.05
CP- newborn 0.92 ± 0.02 0.81 ± 0.02 0.16 ± 0.02 0.03±0.01 0.07±0.02
mixup CP- younger fetus 0.89 ± 0.02 0.81 ± 0.01 0.17 ± 0.03 0.08 ± 0.03 0.18 ± 0.09
CP- older fetus 0.84 ± 0.03 0.95 ± 0.25 0.34 ± 0.07 0.08 ± 0.04 0.14 ± 0.06
CP- newborn 0.92 ± 0.02 0.84 ± 0.06 0.20 ± 0.04 0.06 ± 0.02 0.12 ± 0.03