AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Diagnose Like a Radiologist: Hybrid Neuro-Probabilistic Reasoning for Attribute-Based Medical Image Diagnosis

Gangming Zhao, Quanlong Feng, Chaoqi Chen, Zhen Zhou, Yizhou Yu

TPAMI 2021 · Label-efficient and robust learning › Recognition and long-tail · approach: Loss design and classifier theory · 57 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 cross-network attention and residual fusion (CNA-RES) (ablation)Hybrid BN+GCN (EfficientNet-B4) · LIDC-IDRIaccuracy (%): 93.64 -> 95.31Improved
add first BN module (BN-1) and its coupling with GCN (ablation)Hybrid (EfficientNet-B4) · LIDC-IDRIaccuracy (%): 92.41 -> 95.31Improved
add second BN module (BN-2) (ablation)Hybrid (EfficientNet-B4) · LIDC-IDRIaccuracy (%): 94.74 -> 95.31Improved
add SE channel attention in GCN (ablation)Hybrid (EfficientNet-B4) · LIDC-IDRIaccuracy (%): 94.01 -> 95.31Improved
add gradient backpropagation through BN modules (ablation)Hybrid (EfficientNet-B4) · LIDC-IDRIaccuracy (%): 93.81 -> 95.31Improved
add alternating training strategy (ablation)Hybrid (EfficientNet-B4) · LIDC-IDRIaccuracy (%): 94.31 -> 95.31Improved
replace relational network after GCN with two BN modules (ablation)Relation network variant · LIDC-IDRIaccuracy (%): 92.15 -> 95.31Improved
add standard data augmentationOur-Efficient-B4-FPN · LIDC-IDRIaccuracy (%): 95.31 -> 95.36Improved
add FPN to EfficientNet-B4 backboneEfficient-B4 · LIDC-IDRIaccuracy (%): 89.21 -> 90.91Improved
add hybrid BN+GCN reasoning on top of ResNet-50-FPNResNet-50-FPN · LIDC-IDRIaccuracy (%): 90.01 -> 93.74Improved
add hybrid BN+GCN reasoning on top of EfficientNet-B4-FPNEfficient-B4-FPN · TB-Xattaccuracy (%): 94.19 -> 97.13Improved
add cross-network attention and residual fusion (CNA-RES) (ablation)Hybrid (EfficientNet-B4) · TB-Xattaccuracy (%): 96.21 -> 97.13Improved

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