AI Paper Atlas

Research map / Detection and segmentation / CNN features

Segmenting Medical MRI via Recurrent Decoding Cell

Ying Wen, Kai Xie, Lianghua He

AAAI 2020 · Detection and segmentation › CNN features · approach: Context modeling for semantic segmentation · 16 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
replace U-Net decoding with recurrent decodingU-Net-like backbone · BrainWebDice: 0.9892 -> 0.9934Improved
replace U-Net decoding with recurrent decodingVGG16 · MRBrainSDice: 0.8991 -> 0.9126Improved
replace U-Net decoding with recurrent decodingVGG16 · HVSMRDice: 0.8201 -> 0.8813Improved
use a shared-parameter recurrent decoderVGG16 encoder-decoder · 240×240×3 inputnumber of parameters: 25.86M -> 14.87MImproved
use a shared-parameter recurrent decoderU-Net-like encoder-decoder · 240×240×3 inputnumber of parameters: 1.94M -> 1.23MImproved
increase noise from 1% to 9%CRDN with U-Net-like backbone · BrainWebDice coefficient reduction: 1.69%Hurt
increase intensity non-uniformity from 0% to 40%CRDN with U-Net-like backbone · BrainWebDice coefficient reduction: 0.23%Hurt
use ConvLSTM instead of ConvRNN (ablation)RDC with VGG16 · MRBrainSDice: 0.9088 -> 0.9126Improved
use ConvLSTM instead of ConvRNN (ablation)RDC with VGG16 · HVSMRDice: 0.8813 -> 0.8641Hurt
use ConvRNN instead of ConvLSTM (ablation)RDC with U-Net-like backbone · BrainWebDice: 0.9919 -> 0.9934Improved
use ConvLSTM instead of ConvRNN (ablation)RDC with U-Net-like backbone · MRBrainSDice: 0.9068 -> 0.9112Improved
use ConvRNN instead of ConvGRU (ablation)RDC with ResNet50 · HVSMRDice: 0.8696 -> 0.8641Hurt

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