Journal of Healthcare Engineering / 2019 / Article / Tab 1

Research Article

Towards Fine Whole-Slide Skeletal Muscle Image Segmentation through Deep Hierarchically Connected Networks

Table 1

The segmentation results compared with state-of-the-art methods.

Method-score ()Precision ()Recall ()
FTDTFTDTFTDT

DC [43]48 ± 0.09360 ± 0.13841 ± 0.06654 ± 0.16467 ± 0.19473 ± 0.148
MCG [44]63 ± 0.20171 ± 0.10553 ± 0.13664 ± 0.13880 ± 0.30382 ± 0.091
DNN-SNM [14]76 ± 0.03378 ± 0.08083 ± 0.04285 ± 0.08970 ± 0.05873 ± 0.087
U-Net [30]80 ± 0.14381 ± 0.05487 ± 0.15586 ± 0.07674 ± 0.12677 ± 0.055
Liu et al. [7]82 ± 0.17284 ± 0.06181 ± 0.04384 ± 0.07185 ± 0.20285 ± 0.068
Our approach86 ± 0.18489 ± 0.04891 ± 0.17493 ± 0.05082 ± 0.17686 ± 0.058

σ is the standard deviation.

We are committed to sharing findings related to COVID-19 as quickly and safely as possible. Any author submitting a COVID-19 paper should notify us at help@hindawi.com to ensure their research is fast-tracked and made available on a preprint server as soon as possible. We will be providing unlimited waivers of publication charges for accepted articles related to COVID-19. Sign up here as a reviewer to help fast-track new submissions.