English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

We present MedicDeepLabv3+, a convolutional neural network that is the firstcompletely automatic method to segment cerebral hemispheres in magneticresonance (MR) volumes of rats with lesions. MedicDeepLabv3+ improves thestate-of-the-art DeepLabv3+ with an advanced decoder, incorporating spatialattention layers and additional skip connections that, as we show in ourexperiments, lead to more precise segmentations. MedicDeepLabv3+ requires no MRimage preprocessing, such as bias-field correction or registration to atemplate, produces segmentations in less than a second, and its GPU memoryrequirements can be adjusted based on the available resources. We optimizedMedicDeepLabv3+ and six other state-of-the-art convolutional neural networks(DeepLabv3+, UNet, HighRes3DNet, V-Net, VoxResNet, Demon) on a heterogeneoustraining set comprised by MR volumes from 11 cohorts acquired at differentlesion stages. Then, we evaluated the trained models and two approachesspecifically designed for rodent MRI skull stripping (RATS and RBET) on a largedataset of 655 MR rat brain volumes. In our experiments, MedicDeepLabv3+outperformed the other methods, yielding an average Dice coefficient of 0.952and 0.944 in the brain and contralateral hemisphere regions. Additionally, weshow that despite limiting the GPU memory and the training data, ourMedicDeepLabv3+ also provided satisfactory segmentations. In conclusion, ourmethod, publicly available at https://github.com/jmlipman/MedicDeepLabv3Plus,yielded excellent results in multiple scenarios, demonstrating its capabilityto reduce human workload in rat neuroimaging studies.

Automatic cerebral hemisphere segmentation in rat MRI with lesions via attention-based convolutional neural networks