Papers › Multi-scale Hierarchical Vision Transformer with Cascaded Attention Decoding for...

Multi-scale Hierarchical Vision Transformer with Cascaded Attention Decoding for Medical Image Segmentation

29 Mar 2023arXiv:2303.16892archive 2025-07-28

Md Mostafijur Rahman, Radu Marculescu

Transformers have shown great success in medical image segmentation. However, transformers may exhibit a limited generalization ability due to the underlying single-scale self-attention (SA) mechanism. In this paper, we address this issue by introducing a Multi-scale hiERarchical vIsion Transformer (MERIT) backbone network, which improves the generalizability of the model by computing SA at multiple scales. We also incorporate an attention-based decoder, namely Cascaded Attention Decoding (CASCADE), for further refinement of multi-stage features generated by MERIT. Finally, we introduce an effective multi-stage feature mixing loss aggregation (MUTATION) method for better model training via implicit ensembling. Our experiments on two widely used medical image segmentation benchmarks (i.e., Synapse Multi-organ, ACDC) demonstrate the superior performance of MERIT over state-of-the-art methods. Our MERIT architecture and MUTATION loss aggregation can be used with downstream medical image and semantic segmentation tasks.

Paper PDF Conference PDF Code

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

SLDGroup/MERIT officialmentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Decoder Image Segmentation Medical Image Segmentation Segmentation Semantic Segmentation

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Medical Image Segmentation	Automatic Cardiac Diagnosis Challenge (ACDC)	MERIT	Avg DSC	92.32	#6 of 20	Archive leaderboard	report
Medical Image Segmentation	MICCAI 2015 Multi-Atlas Abdomen Labeling Challenge	MERIT	Avg DSC	84.90	#1 of 8	Archive leaderboard	report
Medical Image Segmentation	MICCAI 2015 Multi-Atlas Abdomen Labeling Challenge	MERIT	Avg HD	13.22	#1 of 8	Archive leaderboard	report
Medical Image Segmentation	Synapse multi-organ CT	MERIT	Avg DSC	84.90	#9 of 23	Archive leaderboard	report
Medical Image Segmentation	Synapse multi-organ CT	MERIT	Avg HD	13.22	#9 of 23	Archive leaderboard	report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Absolute Position Encodings Adam Attention BPE Dense Connections Dropout Label Smoothing Layer Normalization Linear Layer Multi-Head Attention Position-Wise Feed-Forward Layer Residual Connection Softmax Transformer Vision Transformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections