Journal of Healthcare Engineering / 2019 / Article / Tab 2

Research Article

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

Table 2

The runtime (in seconds) comparison on images of different sizes from to .

Method1x2x3x4x5x6x7x8x9x

DC [43]2079
MCG [44]727
Liu et al. [7]1059
DNN-SNM [14]26410562376422466009504129361689621384
DNN-SNM[45]31115242431675974132517382160
U-net [30]1.23.99.016.124.636.848.263.379.2
Our approach1.11.85.38.813.920.927.836.446.8

The first three methods cannot handle images with 3x and larger sizes on our machine (represented with “—” in the table). DNN-SNM is a fast scanning implementation for prediction speed acceleration.

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.