Effectiveness of nnU-Net on three-dimensional automated breast ultrasound (ABUS) lesion segmentation
Shaode Yu, Xiaoyu Liang, Bing Zhu, Z Wang, Bo Liu, Jing Yu Shang · 2024
Automated breast ultrasound (ABUS) lesion segmentation is challenging. The nnU-Net has been recognized for its high accuracy and efficiency on medical image segmentation. However, its effectiveness on ABUS image segmentation remains unknown. This study designs four experiments using nnU-Net (NET), the net with post-processing (NETp), the net with data augmentation (NETd), and the net with data augmentation and post-processing (NETdp). On 100 cases with five-fold cross validation, the performance is assessed with the Dice coefficient (DC) and relative volume error (RVE). Experimental results suggest that NETp (DC = 0.81 ± 0.01; RVE = 0.23 ± 0.11), NETpd (DC = 0.79 ± 0.02; RVE = 0.24 ± 0.13) and NET (DC = 0.79 ± 0.01; RVE = 0.27 ± 0.12) are comparable, and NETd leads to DC = 0.64 ± 0.03 and RVE = 0.03 ± 0.00. Further investigation indicates that the nnU-Net fails on several low-quality ABUS images in consistency. In the future work, how to improve ABUS imaging quality as well as how to design effective segmentation networks become important.