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

Autor:	Rahman, Md Mostafijur, Marculescu, Radu
Rok vydání:	2023
Předmět:	Computer Science - Computer Vision and Pattern Recognition I.4 J.3
Druh dokumentu:	Working Paper
Popis:	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. Comment: 19 pages, 4 figures, MIDL 2023
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2303.16892 Zobrazit plný text záznamu View this record from Arxiv