CMT-BUSNet: Adaptive Fusion-Based Triple-Branch Hybrid Architecture for Explainable Breast Ultrasound Tumor Segmentation

<b>Background/Objectives:</b> This study proposes CMT-BUSNet, a hybrid architecture integrating CNN, Mamba, and Transformer branches for breast ultrasound tumor segmentation with built-in explainability. <b>Methods:</b> CMT-BUSNet employs a CNN-anchored hierarchical parallel encoder where Mamba and...

Deskribapen osoa

Xehetasun bibliografikoak

Egile Nagusiak:	Hüseyin Kutlu, Cemil Çolak
Formatua:	Artigo
Hizkuntza:	Inglês
Argitaratua:	MDPI AG 2026-04-01
Saila:	Diagnostics
Gaiak:	breast ultrasound tumor segmentation explainable artificial intelligence hybrid architecture Mamba deep learning
Sarrera elektronikoa:	https://www.mdpi.com/2075-4418/16/8/1203
Etiketak:	Etiketa erantsi Etiketarik gabe, Izan zaitez lehena erregistro honi etiketa jartzen!