AI Paper Atlas

Research map / Detection and segmentation / CNN features

M-Net: MRI Brain Tumor Sequential Segmentation Network via Mesh-Cast

Jiacheng Lu, Hui Ding, Shiyu Zhang, Guoping Huo

ICCV 2025 · Detection and segmentation › CNN features · approach: Context modeling for semantic segmentation · 5 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add Mamba SSM Mesh-Cast sequential module with TPS training (ablation)M-Net backbone · BraTS 2019Dice ET (%): 90.41 -> 91.43Improved
add Transformer Mesh-Cast module (slice input) (ablation)M-Net backbone · BraTS 2019Dice ET (%): 90.41 -> 90.29No clear effect
add LSTM Mesh-Cast module (slice input) (ablation)M-Net backbone · BraTS 2019Dice WT (%): 87.17 -> 87.59Improved
train with TPS instead of slice input (ablation)M-Net with Mamba SSM · BraTS 2019Dice ET (%): 90.65 -> 91.43Improved
train with TPS instead of slice input (ablation)M-Net with Transformer · BraTS 2019Dice WT (%): 87.24 -> 87.56Improved
train with TPS instead of slice input (ablation)M-Net with LSTM · BraTS 2019Dice WT (%): 87.59 -> 88.06Improved
add temporal modeling (T) to channel modeling (T+C) (ablation)Mesh-Cast · BraTS 2019Dice TC (%): 89.28 -> 90.21Improved
add second ordered phase to shuffled-only training (ablation)M-Net T+C · BraTS 2019Dice WT (%): 88.07 -> 88.38Improved
add shuffled first phase to ordered-only training (ablation)M-Net T+C · BraTS 2019Dice ET (%): 90.65 -> 91.43Improved
shuffle first then order, instead of order then shuffle (ablation)M-Net T+C · BraTS 2019Dice ET (%): 91.29 -> 91.43Improved
shuffled training on backbone without sequential module (ablation)Backbone · BraTS 2019Dice WT (%): 87.17 -> 88.21Improved
add shuffled training and Mesh-Cast to backbone (ablation)Backbone shuffled · BraTS 2019Dice WT (%): 88.21 -> 88.07No clear effect

Later papers that compared with this method

2 later accepted papers report M-Net as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy