MSDTCN-Net: A Multi-Scale Dual-Encoder Network for Skin Lesion Segmentation

<b>Background/Objectives:</b> Accurate segmentation of skin lesions is essential for early skin cancer detection. However, traditional CNNs are limited in modeling long-range dependencies, leading to poor performance on lesions with complex shapes. <b>Methods:</b> We propose MSDTCN-Net, a dual-encod...

Celý popis

Podrobná bibliografie

Hlavní autoři:	Da Li, Xinyang Wu, Qin Wei
Médium:	Artigo
Jazyk:	Inglês
Vydáno:	MDPI AG 2025-11-01
Edice:	Diagnostics
Témata:	skin lesion segmentation convolutional neural networks transformer multi-scale receptive field hierarchical feature transfer
On-line přístup:	https://www.mdpi.com/2075-4418/15/22/2924
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!