D-TrAttUnet: Toward hybrid CNN-transformer architecture for generic and subtle segmentation in medical images

Fares Bougourzi, Fadi Dornaika, Cosimo Distante, Abdelmalik Taleb-Ahmed

Abstract: Highlights•We propose an Efficient Hybrid CNN-Transformer architecture.•Our proposed approach Encoder has Transformer path and Encoders Fusion.•Our approach is designed with Multi-tasks infection-organ-attention Decoders.•The performance is evaluated for Segmenting Bone Metastases and Covid-19 infection.•The proposed Hybrid Encoder has been evaluated for Segmenting Glands and Nuclei.